Retrieval-Augmented Generation (RAG) has recently gained significant attention for its enhanced ability to integrate external knowledge sources into open-domain question answering (QA) tasks. However, it remains unclear how these models address fairness concerns, particularly with respect to sensitive attributes such as gender, geographic location, and other demographic factors. First, as language models evolve to prioritize utility, like improving exact match accuracy, fairness considerations may have been largely overlooked. Second, the complex, multi-component architecture of RAG methods poses challenges in identifying and mitigating biases, as each component is optimized for distinct objectives. In this paper, we aim to empirically evaluate fairness in several RAG methods. We propose a fairness evaluation framework tailored to RAG, using scenario-based questions and analyzing disparities across demographic attributes. Our experimental results indicate that, despite recent advances in utility-driven optimization, fairness issues persist in both the retrieval and generation stages. These findings underscore the need for targeted interventions to address fairness concerns throughout the RAG pipeline. The dataset and code used in this study are publicly available at this GitHub Repository.

Retrieval-augmented generation (RAG) has become integral to large language models (LLMs), particularly for conversational AI systems where user questions may reference knowledge beyond the LLMs' training cutoff. However, many natural user questions lack well-defined answers, either due to limited domain knowledge or because the retrieval system returns documents that are relevant in appearance but uninformative in content. In such cases, LLMs often produce hallucinated answers without flagging them. While recent work has largely focused on questions with false premises, we study out-of-scope questions, where the retrieved document appears semantically similar to the question but lacks the necessary information to answer it. In this paper, we propose a guided hallucination-based approach ELOQ . https://github.com/zhiyuanpeng/ELOQ.git, for automatically generating a diverse set of out-of-scope questions from post-cutoff documents, followed by human verification to ensure quality. We use this dataset to evaluate several LLMs on their ability to detect out-of-scope questions and generate appropriate responses. Finally, we introduce an improved detection method that enhances the reliability of LLM-based question-answering systems in handling out-of-scope questions.

Dense retrieval (DR) converts queries and documents into dense embeddings and measures the similarity between queries and documents in vector space. One of the major challenges in DR is the lack of domain-specific training data. While DR models can learn from large-scale public datasets like MS MARCO through transfer learning, evidence shows that not all DR models and domains can benefit from transfer learning. Recently, researchers have resorted to large language models (LLMs) to improve the zero-shot and few-shot DR models. However, the hard prompts or human-written prompts utilized in these works are suboptimal and the generated weak queries are often sensitive to the prompts. To tackle this, we propose soft prompt tuning for augmenting DR (SPTAR): for each task, we leverage soft prompt tuning to optimize a task-specific soft prompt on limited ground truth data and then prompt the LLMs to tag unlabeled documents with weak queries, yielding weak document–query pairs to train task-specific dense retrievers. We design a filter to select high-quality example document–query pairs in the prompt to further improve the quality of weak tagged queries. To the best of our knowledge, there is no prior work utilizing soft prompt tuning to augment DR models. Moreover, unlike much of the existing work, ours is based on popular open-source LLMs to ensure reproducible and deterministic results. Our experimental results demonstrate that SPTAR outperforms both unsupervised baselines and the recently proposed LLMs-based augmentation method for DR. • First to use LLMs with soft prompt tuning for augmenting dense retrieval tasks. • Novel soft prompt filter improves weak data quality. • Experiments show our method outperforms strong baselines. • Uses open-source LLMs for reproducible, robust results.

Electric vehicles have become a trend as a replacement to gasoline-powered vehicles, and been promoted by worldwide policy makers as a solution to combat environmental problems and stimulate economy, whereas the lack of extreme fast charging infrastructure has become one main obstacle to broad adoption of electric vehicles. To promote the commercial success of electric vehicles, effective placement of electric vehicle (EV) charging stations is pivotal. While numerous studies address EV charging station placement, the integration of transportation network traffic, specifically equilibrium traffic assignment, where flows stabilize as drivers seek routes to minimize travel time, has been relatively limited. This research investigates equilibrium traffic assignment with the inclusion of extreme fast charging (XFC) stations and introduces an algorithmic solution. We assess diverse charging station placement strategies, including node-based and network-based approaches, weighing their respective advantages and drawbacks. Extensive experiments on real transportation networks of varying scales validate our algorithm and evaluate different charging station placement strategies. Many interesting findings are drawn from the study. For instance, increasing the number of XFC charging stations may not always result in reduced traffic time; the added value of extra stations beyond a certain threshold can be quite limited. The findings offer valuable insights for strategically deploying EV charging infrastructure, thus promoting electric vehicle adoption.

Supervisory signals are a critical resource for training learning to rank models. In many real-world search and retrieval scenarios, these signals may not be readily available or could be costly to obtain for some queries. The examples include domains where labeling requires professional expertise, applications with strong privacy constraints, and user engagement information that are too scarce. We refer to these scenarios as sparsely supervised queries which pose significant challenges to traditional learning to rank models. In this work, we address sparsely supervised queries by proposing a novel meta-learning to rank framework which leverages fast learning and adaption capability of meta-learning. The proposed approach accounts for the fact that different queries have different optimal parameters for their rankers, in contrast to traditional learning to rank models which only learn a global ranking model applied to all the queries. In consequence, the proposed method would yield significant advantages especially when new queries are of different characteristics with the training queries. Moreover, the proposed meta-learning to rank framework is generic and flexible. We conduct a set of comprehensive experiments on both public datasets and a real-world e-commerce dataset. The results demonstrate that the proposed meta-learning approach can significantly enhance the performance of learning to rank models with sparsely labeled queries.

Yuan Wang, Xuyang Wu, Hsin-Tai Wu, Zhiqiang Tao, Yi Fang. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Vision-language models, pre-trained on web-scale datasets, have the potential to greatly enhance the intelligence of web applications (e.g., search engines, chatbots, and art tools). Precisely, these models align disparate domains into a co-embedding space, achieving impressive zero-shot performance on multi-modal tasks (e.g., image-text retrieval, VQA). However, existing methods often rely on well-prepared data that less frequently contain noise and variability encountered in real-world scenarios, leading to severe performance drops in handling out-of-distribution (OOD) samples. This work first comprehensively analyzes the performance drop between in-distribution (ID) and OOD retrieval. Based on empirical observations, we introduce a novel approach, Evidential Language-Image Posterior (ELIP), to achieve robust alignment between web images and semantic knowledge across various OOD cases by leveraging evidential uncertainties. The proposed ELIP can be seamlessly integrated into general image-text contrastive learning frameworks, providing an efficient fine-tuning approach without exacerbating the need for additional data. To validate the effectiveness of ELIP, we systematically design a series of OOD cases (e.g., image distortion, spelling errors, and a combination of both) on two benchmark datasets to mimic noisy data in real-world web applications. Our experimental results demonstrate that ELIP improves the performance and robustness of mainstream pre-trained vision-language models facing OOD samples in image-text retrieval tasks.

Probabilistic Latent Semantic Analysis (PLSA) is a fundamental text analysis technique that models each word in a document as a sample from a mixture of topics. PLSA is the precursor of probabilistic topic models including Latent Dirichlet Allocation (LDA). PLSA, LDA and their numerous extensions have been successfully applied to many text mining and retrieval tasks. One important extension of LDA is supervised LDA (sLDA), which distinguishes itself from most topic models in that it is supervised. However, to the best of our knowledge, no prior work extends PLSA in a similar manner sLDA extends LDA by jointly modeling the contents and the responses of documents. In this paper, we propose supervised PLSA (sPLSA) which can efficiently infer latent topics and their factorized response values from the contents and the responses of documents. The major challenge lies in estimating a document’s topic distribution which is a constrained probability that is dictated by both the content and the response of the document. To tackle this challenge, we introduce an auxiliary variable to transform the constrained optimization problem to an unconstrained optimization problem. This allows us to derive an efficient Expectation and Maximization (EM) algorithm for parameter estimation. Compared to sLDA, sPLSA converges much faster and requires less hyperparameter tuning, while performing similarly on topic modeling and better in response factorization. This makes sPLSA an appealing choice for latent response analysis such as ranking latent topics by their factorized response values. We apply the proposed sPLSA model to analyze the controversy of bills from the United States Congress. We demonstrate the effectiveness of our model by identifying contentious legislative issues.

Missing data in tabular dataset is a common issue as the performance of downstream tasks usually depends on the completeness of the training dataset. Previous missing data imputation methods focus on numeric and categorical columns, but we propose a novel end-to-end approach called Table Transformers for Imputing Textual Attributes (TTITA) based on the transformer to impute unstructured textual columns using other columns in the table. We conduct extensive experiments on three datasets, and our approach shows competitive performance outperforming baseline models such as recurrent neural networks and Llama2. The performance improvement is more significant when the target sequence has a longer length. Additionally, we incorporate multi-task learning to simultaneously impute for heterogeneous columns, boosting the performance for text imputation. We also qualitatively compare with ChatGPT for realistic applications. • Proposed TTITA to impute text attributes given other heterogeneous tabular columns. • Encoded inputs into a context vector for cross-attention in the transformer decoder. • Outperformed baseline models including the GRU and Llama2 on real-world datasets. • Incorporated multi-task learning for multi-column imputation and boosting performance. • Prepared the software as an open-source package for custom applications.

In recent information retrieval systems, it is observed that the datasets used to train machine learning models can be biased, leading to systematic discrimination against certain demographic groups, which means the ranking utility of specific groups is often lower than others in a biased dataset. Training models on these datasets will further decrease the exposure of the minority groups. To address this problem, we propose a Meta Curriculum-based Fair Ranking framework (MCFR) which could alleviate the data bias issue through the weighted loss using gradient-based learning to learn. Specifically, we optimize a meta learner from a sampled dataset (meta-dataset), and meanwhile train a ranking model on the whole (biased) dataset. The meta-dataset is sampled with a curriculum learning scheduler to guide the meta learner's training to gradually mitigate the skewness towards biased attributes. The meta learner serves as a weighting function to make the ranking loss focus more on the minority group. We formulate the proposed MCFR as a bilevel optimization problem and solve it using gradients through gradients. Extensive experiments on real-world datasets demonstrate that our approach can be used as a generic framework to work with various ranking losses and fairness metrics.

Query Understanding (QU) is a fundamental process in E-commerce search engines by extracting the shopping intents of customers. It usually includes a set of different tasks such as named entity recognization and query classification. Traditional approaches often tackle each task separately by its own network, which leads to excessive workload for development and maintenance as well as increased latency and resource usage in large-scale E-commerce platforms. To tackle these challenges, this paper presents a multi-task learning approach to query understanding at Walmart. We experimented with several state-of-the-art multi-task learning architectures including MTDNN, MMoE, and PLE. Furthermore, we propose a novel large-scale entity-aware multi-task learning model (EAMT)1 by retrieving entities from engagement data as query context to augment the query representation. To the best of our knowledge, there exists no prior work on multi-task learning for E-commerce query understanding. Comprehensive offline experiments are conducted on industry-scale datasets (up to 965M queries) to illustrate the effectiveness of our approach. The results from online experiments show substantial gains in key accuracy and latency metrics. https://github.com/zhiyuanpeng/KDD2023-EAMT

Data selection bias has been a long-lasting challenge in the machine learning domain, especially in multi-stage recommendation systems, where the distribution of labeled items for model training is very different from that of the actual candidates during inference time. This distribution shift is even more prominent in the context of online advertising where the user base is diverse and the platform contains a wide range of contents. In this paper, we first investigate the data selection bias in the upper funnel (Ads Retrieval) of Pinterest's multi-cascade ads ranking system. We then conduct comprehensive experiments to assess the performance of various state-of-the-art methods, including transfer learning, adversarial learning, and unsupervised domain adaptation. Moreover, we further introduce some modifications into the unsupervised domain adaptation and evaluate the performance of different variants of this modified method. Our online A/B experiments show that the modified version of unsupervised domain adaptation (MUDA) could provide the largest improvements to the performance of Pinterest's advertisement ranking system compared with other methods and the one used in current production.

The increasing popularity of social media promotes the proliferation of misinformation, especially in the communities of Chinese-speaking diasporas, which has caused significant negative societal impacts. In addition, most of the existing efforts on misinformation mitigation have focused on English and other western languages, which makes numerous overseas Chinese a very vulnerable population to online disinformation campaigns. In this paper, we present AMICA, an information retrieval system for alleviating misinformation for Chinese Americans. AMICA dynamically collects data from popular social media platforms for Chinese Americans, including WeChat, Twitter, YouTube, and Chinese forums. The data are stored and indexed in Elasticsearch to provide advanced search functionalities. Given a user query, the ranking of social media posts considers both topical relevance and the likelihood of being misinformation.

Fairness has gained increasing importance in a variety of AI and machine learning contexts. As one of the most ubiquitous applications of machine learning, search engines mediate much of the information experiences of members of society. Consequently, understanding and mitigating potential algorithmic unfairness in search have become crucial for both users and systems. In this tutorial, we will introduce the fundamentals of fairness in machine learning, for both supervised learning such as classification and ranking, and unsupervised learning such as clustering. We will then present the existing work on fairness in search engines, including the fairness definitions, evaluation metrics, and taxonomies of methodologies. This tutorial will help orient information retrieval researchers to algorithmic fairness, provide an introduction to the growing literature on this topic, and gathering researchers and practitioners interested in this research direction.

Professional news media organizations have always touted the importance that they give to multiple perspectives. However, in practice, the traditional approach to all-sides has favored people in the dominant culture. Hence it has come under ethical critique under the new norms of diversity, equity, and inclusion (DEI). When DEI is applied to journalism, it goes beyond conventional notions of impartiality and bias and instead democratizes the journalistic practice of sourcing -- who is quoted or interviewed, who is not, how often, from which demographic group, gender, and so forth. There is currently no real-time or on-demand tool in the hands of reporters to analyze the persons they quote. In this paper, we present DIANES, a DEI Audit Toolkit for News Sources. It consists of a natural language processing pipeline on the backend to extract quotes, speakers, titles, and organizations from news articles in real time. On the frontend, DIANES offers the WordPress plugins, a Web monitor, and a DEI annotation API service, to help news media monitor their own quoting patterns and push themselves towards DEI norms.

In recent years, the fairness in information retrieval (IR) system has received increasing research attention. While the data-driven ranking models achieve significant improvements over traditional methods, the dataset used to train such models is usually biased, which causes unfairness in the ranking models. For example, the collected imbalance dataset on the subject of the expert search usually leads to systematic discrimination on the specific demographic groups such as race, gender, etc, which further reduces the exposure for the minority group. To solve this problem, we propose a Meta-learning based Fair Ranking (MFR) model that could alleviate the data bias for protected groups through an automatically-weighted loss. Specifically, we adopt a meta-learning framework to explicitly train a meta-learner from an unbiased sampled dataset (meta-dataset), and simultaneously, train a listwise learning-to-rank (LTR) model on the whole (biased) dataset governed by "fair" loss weights. The meta-learner serves as a weighting function to make the ranking loss attend more on the minority group. To update the parameters of the weighting function and the ranking model, we formulate the proposed MFR as a bilevel optimization problem and solve it using the gradients through gradients. Experimental results on several real-world datasets demonstrate that the proposed method achieves a comparable ranking performance and significantly improves the fairness metric compared with state-of-the-art methods.

Structure information extraction refers to the task of extracting structured text fields from web pages, such as extracting a product offer from a shopping page including product title, description, brand and price. It is an important research topic which has been widely studied in document understanding and web search. Recent natural language models with sequence modeling have demonstrated state-of-the-art performance on web information extraction. However, effectively serializing tokens from unstructured web pages is challenging in practice due to a variety of web layout patterns. Limited work has focused on modeling the web layout for extracting the text fields. In this paper, we introduce WebFormer, a Web-page transFormer model for structure information extraction from web documents. First, we design HTML tokens for each DOM node in the HTML by embedding representations from their neighboring tokens through graph attention. Second, we construct rich attention patterns between HTML tokens and text tokens, which leverages the web layout for effective attention weight computation. We conduct an extensive set of experiments on SWDE and Common Crawl benchmarks. Experimental results demonstrate the superior performance of the proposed approach over several state-of-the-art methods.

Product ranking is a crucial component for many e-commerce services. One of the major challenges in product search is the vocabulary mismatch between query and products, which may be a larger vocabulary gap problem compared to other information retrieval domains. While there is a growing collection of neural learning to match methods aimed specifically at overcoming this issue, they do not leverage the recent advances of large language models for product search. On the other hand, product ranking often deals with multiple types of engagement signals such as clicks, add-to-cart, and purchases, while most of the existing works are focused on optimizing one single metric such as click-through rate, which may suffer from data sparsity. In this work, we propose a novel end-to-end multi-task learning framework for product ranking with BERT to address the above challenges. The proposed model utilizes domain-specific BERT with fine-tuning to bridge the vocabulary gap and employs multi-task learning to optimize multiple objectives simultaneously, which yields a general end-to-end learning framework for product search. We conduct a set of comprehensive experiments on a real-world e-commerce dataset and demonstrate significant improvement of the proposed approach over the state-of-the-art baseline methods.

Karaoke machines have become a popular choice for many people’s daily entertainment. In this paper, we address a novel task of recommending a suitable key for a user to sing a given song to meet his or her vocal competence, by proposing the Personalized Competence-based Rating Prediction (PCRP) model. Specifically, we learn the song embedding vectors from the sequences of songs’ notes, and then design a history encoder with recurrent units to extract users’ vocal information from the history rating records and utilize a rating decoder based on the Transformer. The experimental results on a real world karaoke rating dataset demonstrate the effectiveness of the proposed approach.

Electric vehicles have become a trend as a replacement to gasoline-powered vehicles, and been promoted by worldwide policy makers as a solution to combat environmental problems and stimulate economy, whereas the lack of extreme fast charging infrastructure has become one main obstacle to broad adoption of electric vehicles. To promote the commercial success of electric vehicles, millions of extreme fast charging stations are expected to be established in the next decade in the U.S. However, the widespread of electric vehicles and extreme fast charging infrastructure would impact transportation systems, such as mobility, congestion, equity, toll revenue, and infrastructure maintenance needs. As transportation infrastructure can last for a long time, effective planning must be able to predict the impact of projects and policies decades into the future. Given the nature of transportation systems that is of multiple interacting systems, this study develops mathematical models to quantitatively analyze this complicated and important problem. In particular, we utilize game theory to understand the dependency between the choices made by travelers, and the congestion and delay in the system with respect to traffic assignment. Our research results provide insights and guidance to strategic planning of extreme fast charging infrastructure.

For short distance traveling in crowded urban areas, bike share services is becoming popular owing to the flexibility and convenience. To expand the service coverage, one of the key tasks is to seek new service ports, which requires to well understand the underlying features of the existing service ports. In this paper, we propose a new model, named for Efficient and Semantic Location Embedding (ESLE)1, which carries both geospatial and semantic information of the geo-locations. To generate ESLE, we first train a multi-label model with a deep Convolutional Neural Network (CNN) by feeding the static map-tile images and then extract location embedding vectors from the model. Compared to most recent relevant literature, ESLE is not only much cheaper in computation, but also easier to interpret via a systematic semantic analysis. Finally, we apply ESLE to seek new service ports for NTT DOCOMO’s bike share services operated in Japan. The initial results demonstrate the effectiveness of ESLE, and provide a few insights that might be difficult to discover by using the conventional approaches.

When shopping for fashion, customers often look for products which can complement their current outfit. For example, customers want to buy a jacket which can go well with their jeans and sneakers. To address the task of fashion matching, we propose a neural compatibility model for ranking fashion products based on the compatibility matching with the input outfit. The contribution of our work is twofold. First, we demonstrate that product descriptions contain rich information about product comparability which has not been fully utilized in the prior work. Secondly, we exploit such useful information from text data by taking advantages of semantic matching and lexical matching both of which are important for fashion matching. The proposed model is evaluated on a real-world fashion outfit dataset and achieves the state-of-the-art results by comparing to the competitive baselines. In the future work, we plan to extend the model by incorporating product images which are the major data source in the prior work on fashion matching.

With an ever increasing amount of data available on the web, fast similarity search has become the critical component for large-scale information retrieval systems. One solution is semantic hashing which designs binary codes to accelerate similarity search. Recently, deep learning has been successfully applied to the semantic hashing problem and produces high-quality compact binary codes compared to traditional methods. However, most state-of-the-art semantic hashing approaches require large amounts of hand-labeled training data which are often expensive and time consuming to collect. The cost of getting labeled data is the key bottleneck in deploying these hashing methods. Motivated by the recent success in machine learning that makes use of weak supervision, we employ unsupervised ranking methods such as BM25 to extract weak signals from training data. We further introduce two deep generative semantic hashing models to leverage weak signals for text hashing. The experimental results on four public datasets show that our models can generate high-quality binary codes without using hand-labeled training data and significantly outperform the competitive unsupervised semantic hashing baselines.

Recommendation systems play a vital role to keep users engaged with personalized content in modern online platforms. Deep learning has revolutionized many research fields and there is a recent surge of interest in applying it to collaborative filtering (CF). However, existing methods compose deep learning architectures with the latent factor model ignoring a major class of CF models, neighborhood or memory-based approaches. We propose Collaborative Memory Networks (CMN), a deep architecture to unify the two classes of CF models capitalizing on the strengths of the global structure of latent factor model and local neighborhood-based structure in a nonlinear fashion. Motivated by the success of Memory Networks, we fuse a memory component and neural attention mechanism as the neighborhood component. The associative addressing scheme with the user and item memories in the memory module encodes complex user-item relations coupled with the neural attention mechanism to learn a user-item specific neighborhood. Finally, the output module jointly exploits the neighborhood with the user and item memories to produce the ranking score. Stacking multiple memory modules together yield deeper architectures capturing increasingly complex user-item relations. Furthermore, we show strong connections between CMN components, memory networks and the three classes of CF models. Comprehensive experimental results demonstrate the effectiveness of CMN on three public datasets outperforming competitive baselines. Qualitative visualization of the attention weights provide insight into the model's recommendation process and suggest the presence of higher order interactions.

As the amount of textual data has been rapidly increasing over the past decade, efficient similarity search methods have become a crucial component of large-scale information retrieval systems. A popular strategy is to represent original data samples by compact binary codes through hashing. A spectrum of machine learning methods have been utilized, but they often lack expressiveness and flexibility in modeling to learn effective representations. The recent advances of deep learning in a wide range of applications has demonstrated its capability to learn robust and powerful feature representations for complex data. Especially, deep generative models naturally combine the expressiveness of probabilistic generative models with the high capacity of deep neural networks, which is very suitable for text modeling. However, little work has leveraged the recent progress in deep learning for text hashing.

The accelerating rate of scientific publications makes it difficult to find relevant citations or related work. Context-aware citation recommendation aims to solve this problem by providing a curated list of high-quality candidates given a short passage of text. Existing literature adopts bag-of-word representations leading to the loss of valuable semantics and lacks the ability to integrate metadata or generalize to unseen manuscripts in the training set. We propose a flexible encoder-decoder architecture called Neural Citation Network (NCN), embodying a robust representation of the citation context with a max time delay neural network, further augmented with an attention mechanism and author networks. The recurrent neural network decoder consults this representation when determining the optimal paper to recommend based solely on its title. Quantitative results on the large-scale CiteSeer dataset reveal NCN cultivates a significant improvement over competitive baselines. Qualitative evidence highlights the effectiveness of the proposed end-to-end neural network revealing a promising research direction for citation recommendation.

Identifying topic trends on microblogging services such as Twitter and estimating those topics’ future popularity have great academic and business value, especially when the operations can be done in real time. For any third party, however, capturing and processing such huge volumes of real-time data in microblogs are almost infeasible tasks, as there always exist API (Application Program Interface) request limits, monitoring and computing budgets, as well as timeliness requirements. To deal with these challenges, we propose a cost-effective system framework with algorithms that can automatically select a subset of representative users in microblogging networks in offline, under given cost constraints. Then the proposed system can online monitor and utilize only these selected users’ real-time microposts to detect the overall trending topics and predict their future popularity among the whole microblogging network. Therefore, our proposed system framework is practical for real-time usage as it avoids the high cost in capturing and processing full real-time data, while not compromising detection and prediction performance under given cost constraints. Experiments with real microblogs dataset show that by tracking only 500 users out of 0.6 million users and processing no more than 30,000 microposts daily, about 92% trending topics could be detected and predicted by the proposed system and, on average, more than 10 hours earlier than they appear in official trends lists.

Expertise search is a well-established field in information retrieval. In recent years, the increasing availability of data enables accumulation of evidence of talent and expertise from a wide range of domains. The availability of big data significantly benefits employers and recruiters. By analyzing the massive amounts of structured and unstructured data, organizations may be able to find the exact skill sets and talent they need to grow their business. The aim of this workshop is to provide a forum for industry and academia to discuss the recent progress in talent search and management, and how the use of big data and data-driven decision making can advance talent acquisition and human resource management.

People often implicitly or explicitly express their needs in social media in the form of "user status text". Such text can be very useful for service providers and product manufacturers to proactively provide relevant services or products that satisfy people's immediate needs. In this paper, we study how to infer a user's intent based on the user's "status text" and retrieve relevant mobile apps that may satisfy the user's needs. We address this problem by framing it as a new entity retrieval task where the query is a user's status text and the entities to be retrieved are mobile apps. We first propose a novel approach that generates a new representation for each query. Our key idea is to leverage social media to build parallel corpora that contain implicit intention text and the corresponding explicit intention text. Specifically, we model various user intentions in social media text using topic models, and we predict user intention in a query that contains implicit intention. Then, we retrieve relevant mobile apps with the predicted user intention. We evaluate the mobile app retrieval task using a new data set we create. Experiment results indicate that the proposed model is effective and outperforms the state-of-the-art retrieval models.

Product reviews have become an important resource for customers before they make purchase decisions. However, the abundance of reviews makes it difficult for customers to digest them and make informed choices. In our study, we aim to help customers who want to quickly capture the main idea of a lengthy product review before they read the details. In contrast with existing work on review analysis and document summarization, we aim to retrieve a set of real-world user questions to summarize a review. In this way, users would know what questions a given review can address and they may further read the review only if they have similar questions about the product. Specifically, we design a two-stage approach which consists of question retrieval and question diversification. We first propose probabilistic retrieval models to locate candidate questions that are relevant to a review. We then design a set function to re-rank the questions with the goal of rewarding diversity in the final question set. The set function satisfies submodularity and monotonicity, which results in an efficient greedy algorithm of submodular optimization. Evaluation on product reviews from two categories shows that the proposed approach is effective for discovering meaningful questions that are representative for individual reviews.

As one of the most important state-of-the-art classification techniques, Support Vector Machine (SVM) has been widely adopted in many real-world applications, such as object detection, face recognition, text categorization, etc., due to its competitive practical performance and elegant theoretical interpretation. However, it treats all samples independently, and ignores the fact that, in many real situations especially when data are in high dimensional space, samples typically lie on low dimensional manifolds of the feature space and thus a sample can be related to its neighbors by being represented as a linear combination of other samples on the same manifold. This linear representation, which is usually sparse, reflects the structure of underlying manifolds. It has been extensively explored in the recent literature and proven to be critical for the performance of classification. To benefit from both the underlying low dimensional manifold structure and the large margin classifier, this paper proposes a novel method called Sparsity Preserving Support Vector Machine(SP-SVM), which explicitly considers the sparse representation of samples while maximizing the margin between different classes. Consequently, SP-SVM inherits both the discriminative power of support vector machine and the merits of sparsity. A set of experiments on real-world benchmark data sets show that SP-SVM achieves significantly higher precision on recognition task than various competitive baselines including the traditional SVM, the sparse representation based method and the classical nearest neighbor classifier.

Personal expertise or interests often evolve over time. Despite much work on expertise retrieval in the recent years, very little work has studied the dynamics of personal expertise. In this paper, we propose a probabilistic model to characterize how people change or stick with their expertise. Specifically, three factors are taken into consideration in whether an expert will choose a new expertise area: 1) the personality of the expert in exploring new areas; 2) the similarity between the new area and the expert's current areas; 3) the popularity of the new area. These three factors are integrated into a unified generative process. A predictive language model is derived to estimate the distribution of the expert's words in her future publications. In addition, KL divergence is defined on the predictive language model to quantify and forecast the change of expertise. We conduct the experiments on a testbed of academic publications and the initial results demonstrate the effectiveness of the proposed approach.

Conventional approaches to road hazard detection involve manual inspections of roads by government transportation agencies. These approaches are usually expensive to execute, and sometimes are not able to capture the most recent hazards. Moreover, they often only focus on major highways due to a lack of sufficient manpower. Consequently, many hazards on minor roads get ignored, which may pose serious dangers to drivers. In this paper, we demonstrate an application of Twitter to atomically determining road hazards. By building language models based on Twitter users' online communication, our system aims at pinpointing potential road hazards that pose driving risks. The likelihood of poor driving conditions can then be exposed via map overlays to warn drivers about potentially dangerous driving conditions in their locale or on current routes, thereby significantly reducing the chances of an accident occurring. To the best of our knowledge, this is the first work demonstrating the utility of social media to automatically detect road hazards. We conduct experiments on a testbed of tweets discussing road conditions and the initial results demonstrate the effectiveness of our approach.

Localized query prediction (LQP) is the task of estimating web query trends for a specific location. This problem subsumes many interesting personalized web applications such as personalization for buzz query detection, for query expansion, and for query recommendation. These personalized applications can greatly enhance user interaction with web search engines by providing more customized information discovered from user input (i.e., queries), but the LQP task has rarely been investigated in the literature. Although exist abundant work on estimating global web search trends does exist, it often encounters the big challenge of data sparsity when personalization comes into play. In this article, we tackle the LQP task by proposing a series of collaborative language models (CLMs). CLMs alleviate the data sparsity issue by collaboratively collecting queries and trend information from the other locations. The traditional statistical language models assume a fixed background language model, which loses the taste of personalization. In contrast, CLMs are personalized language models with flexible background language models customized to various locations. The most sophisticated CLM enables the collaboration to adapt to specific query topics, which further advances the personalization level. An extensive set of experiments have been conducted on a large-scale web query log to demonstrate the effectiveness of the proposed models.

With a huge number of active users on microblogs, it becomes increasingly important to identify authoritative users on specific topics. This paper tackles the task of finding authorities on Twitter given any query topic. Although there exists much work on identifying influential users on Twitter, most of them focus on global authority regardless of the topic. We propose a novel Topical Authority Propagation (TAP) model by utilizing the fact that topical authority can be propagated through retweeting, i.e., if a user's tweet on a given topic is retweeted by a topical authority, that user is likely to be an authority on the topic as well. Topical relevance of candidate authorities can be seamlessly integrated into the model. Link analysis algorithms such as PageRank can then be utilized to characterize how topical authority is propagated through retweeting. We conduct a set of experiments on Twitter and demonstrate the effectiveness of the proposed approach.

Most of the current recommender systems heavily rely on explicit user feedback such as ratings on items to model users' interests. However, in many applications, it is very hard to collect the explicit feedback, while implicit feedback such as user clicks may be more available. Furthermore, it is often more suitable for many recommender systems to address a ranking problem than a rating predicting problem. This paper proposes a latent pairwise preference learning (LPPL) approach for recommendation with implicit feedback. LPPL directly models user preferences with respect to a set of items rather than the rating scores on individual items, which are modeled with a set of features by analyzing clickthrough data available in many real-world recommender systems. The LPPL approach models both the latent variables of group structure of users and the pairwise preferences simultaneously. We conduct experiments on the testbed from a real-world recommender system and demonstrate that the proposed approach can effectively improve the recommendation performance against several baseline algorithms.

With the rapid growth of online news services, users can actively respond to online news by making comments. Users often express subjective emotions in comments such as sadness, surprise and anger. Such emotions can help understand the preferences and perspectives of individual users, and therefore may facilitate online publishers to provide users with more relevant services. This paper tackles the task of predicting emotions for the comments of online news. To the best of our knowledge, this is the first research work for addressing the task. In particular, this paper proposes a novel Meta classification approach that exploits heterogeneous information sources such as the content of the comments and the emotion tags of news articles generated by users. The experiments on two datasets from online news services demonstrate the effectiveness of the proposed approach.

This paper presents a novel opinion mining research problem, which is called Contrastive Opinion Modeling (COM). Given any query topic and a set of text collections from multiple perspectives, the task of COM is to present the opinions of the individual perspectives on the topic, and furthermore to quantify their difference. This general problem subsumes many interesting applications, including opinion summarization and forecasting, government intelligence and cross-cultural studies. We propose a novel unsupervised topic model for contrastive opinion modeling. It simulates the generative process of how opinion words occur in the documents of different collections. The ad hoc opinion search process can be efficiently accomplished based on the learned parameters in the model. The difference of perspectives can be quantified in a principled way by the Jensen-Shannon divergence among the individual topic-opinion distributions. An extensive set of experiments have been conducted to evaluate the proposed model on two datasets in the political domain: 1) statement records of U.S. senators; 2) world news reports from three representative media in U.S., China and India, respectively. The experimental results with both qualitative and quantitative analysis have shown the effectiveness of the proposed model.

Identifying similar professionals is an important task for many core services in professional social networks. Information about users can be obtained from heterogeneous information sources, and different sources provide different insights on user similarity.

Expert search has made rapid progress in modeling, algorithms and evaluations in the recent years. However, there is very few work on analyzing how users interact with expert search systems. In this paper, we conduct analysis of an expert search query log. The aim is to understand the special characteristics of expert search usage. To the best of our knowledge, this is one of the earliest work on expert search query log analysis. We find that expert search users generally issue shorter queries, more common queries, and use more advanced search features, with fewer queries in a session, than general Web search users do. This study explores a new research direction in expert search by analyzing and exploiting query logs.

Generative models such as statistical language modeling have been widely studied in the task of expert search to model the relationship between experts and their expertise indi-cated in supporting documents. On the other hand, dis-criminative models have received little attention in expert search research, although they have been shown to outper-form generative models in many other information retrieval and machine learning applications. In this paper, we propose a principled relevance-based discriminative learning frame-work for expert search and derive specific discriminative models from the framework. Compared with the state-of-the-art language models for expert search, the proposed re-search can naturally integrate various document evidence and document-candidate associations into a single model without extra modeling assumptions or effort. An extensive set of experiments have been conducted on two TREC En-terprise track corpora (i.e., W3C and CERC) to demonstrate the effectiveness and robustness of the proposed framework.

Prediction of motor shaft misalignment is essential for the development of effective coupling and rotating equipment maintenance information systems. It can be stated as a multivariate regression problem with ill-posed data. In this paper, hybrid models of principal components regression (PCR) and partial least squares regression (PLS) have been proposed for this problem. The basic idea of hybrid models is to combine the merits of PCR and PLS to develop more accurate prediction techniques. Both the principal components defined in PCR and the latent variables in PLS are involved in a hybrid model. The experimental results show that an optimal hybrid model can outperform PCR and PLS, especially when the number of predictor variables increases. It suggests that the proposed approach may be particularly useful for complex prediction tasks that need more predictor variables. Discussions for future research are also presented.