Diffusion large language models (dLLMs) offer an efficient alternative to autoregressive models through parallel decoding, yet existing post-training methods largely rely on random masking strategies that overlook intrinsic token dependencies.In this work, we present an empirical analysis of attention in dLLMs and show that tokens attending more strongly to unmasked context exhibit greater generation stability and play a critical role in reasoning.Motivated by these findings, we propose AGDO, an attention-guided denoising and optimization framework that aligns both training and optimization with attention-derived dependencies.AGDO determines the denoising order based on attention structure and emphasizes attentioncritical tokens during supervised fine-tuning and reinforcement learning.Experiments on mathematical and coding benchmarks demonstrate that AGDO consistently improves reasoning performance, outperforming state-of-theart post-training methods for dLLMs.

Deep Learning Recommendation Models (DLRMs) often rely on extensive manual feature engineering to improve accuracy and user experience, which increases system complexity and limits scalability of model performance with respect to computational resources. Recently, Meta introduced a generative ranking paradigm based on HSTU block that enables end-to-end learning from raw user behavior sequences and demonstrates scaling law on large datasets that can be regarded as the state-of-the-art (SOTA). However, splitting user behaviors into interleaved item and action information significantly increases the input sequence length, which adversely affects both training and inference efficiency. To address this issue, we propose the Twin-Flow Generative Ranking Network (TFGR), that employs a Twin-flow mechanism to optimize interaction modeling, ensuring efficient training and inference through end-to-end token processing. TFGR duplicates the original user behavior sequence into a real flow and a fake flow based on the authenticity of the action information, and then defines a novel interaction method between the real flow and the fake flow within the QKV module of the self-attention mechanism. This design reduces computational overhead and improves both training efficiency and inference performance compared to Meta's HSTU-based model. Experiments on both open-source and real industrial datasets show that TFGR outperforms DLRM, which serves as the industrial online baseline with extensive feature engineering, as well as Meta's HSTU and other common recommendation models such as DIN, DCN, DIEN, and DeepFM. Furthermore, we investigate optimal parameter allocation strategies under computational constraints, establishing TFGR as an efficient and effective next-generation generative ranking paradigm.

Visual instruction tuning is crucial for enhancing the zero-shot generalization capability of Multi-modal Large Language Models (MLLMs). In this paper, we aim to investigate a fundamental question: “what makes for good visual instructions”. Through a comprehensive empirical study, we find that instructions focusing on complex visual reasoning tasks are particularly effective in improving the performance of MLLMs, with results correlating to instruction complexity. Based on this insight, we develop a systematic approach to automatically create high-quality complex visual reasoning instructions. Our approach employs a synthesize-complicate-reformulate paradigm, leveraging multiple stages to gradually increase the complexity of the instructions while guaranteeing quality. Based on this approach, we create the ComVint dataset with 32K examples, and fine-tune four MLLMs on it. Experimental results consistently demonstrate the enhanced performance of all compared MLLMs, such as a 27.86% and 27.60% improvement for LLaVA on MME-Perception and MME-Cognition, respectively. Our code and data are publicly available at the link: https://github.com/RUCAIBox/ComVint.

Conversational recommendation systems (CRSs) use multi-turn interaction to capture user preferences and provide personalized recommendations. A fundamental challenge in CRSs lies in effectively understanding user preferences from conversations. Previous research primarily focuses on the issue of insufficient contextual information in conversations. They address this by introducing external knowledge sources, such as knowledge graphs, large language models (LLMs), and conversational recommendation corpora. Based on this, they design specific alignment strategies (e.g., prompt learning and instruction tuning) to integrate such knowledge for user preference understanding and item recommendation. However, user preferences can be multifaceted and complex, posing significant challenges for accurate recommendations even with access to abundant external knowledge. While interaction with users can clarify their true preferences, frequent user involvement may lead to a degraded user experience.

Recently, Large Language Models (LLMs) such as ChatGPT have showcased remarkable abilities in solving general tasks, demonstrating the potential for applications in recommender systems. To assess how effectively LLMs can be used in recommendation tasks, our study primarily focuses on employing LLMs as recommender systems through prompt engineering. We propose a general framework for leveraging LLMs in recommendation tasks, focusing on the capabilities of LLMs as recommenders. To conduct our analysis, we formalize the input of LLMs for recommendation into natural language prompts with two key aspects and explain how our framework can be generalized to various recommendation scenarios. As for the use of LLMs as recommenders, we analyze the impact of public availability, tuning strategies, model architecture, parameter scale, and context length on recommendation results based on the classification of LLMs. As for prompt engineering, we further analyze the impact of four important components of prompts, i.e., task descriptions, user interest modeling, candidate items construction, and prompting strategies. In each section, we first define and categorize concepts in line with the existing literature. Then, we propose inspiring research questions followed by detailed experiments on two public datasets, in order to systematically analyze the impact of different factors on recommendation performance. Based on our empirical analysis, we finally summarize promising directions to shed lights on future research.

As an effective tool for eliciting the power of Large Language Models (LLMs), prompting has recently demonstrated unprecedented abilities across a variety of complex tasks. To further improve the performance, prompt ensemble has attracted substantial interest for tackling the hallucination and instability of LLMs. However, existing methods usually adopt a two-stage paradigm, which requires a pre-prepared set of prompts with substantial manual effort, and is unable to perform directed optimization for different weak learners. In this paper, we propose a simple, universal, and automatic method named PREFER (Prompt Ensemble learning via Feedback-Reflect-Refine) to address the stated limitations. Specifically, given the fact that weak learners are supposed to focus on hard examples during boosting, PREFER builds a feedback mechanism for reflecting on the inadequacies of existing weak learners. Based on this, the LLM is required to automatically synthesize new prompts for iterative refinement. Moreover, to enhance stability of the prompt effect evaluation, we propose a novel prompt bagging method involving forward and backward thinking, which is superior to majority voting and is beneficial for both feedback and weight calculation in boosting. Extensive experiments demonstrate that our PREFER achieves state-of-the-art performance in multiple types of tasks by a significant margin. We have made our code publicly available.

Cross-domain recommendation has attracted substantial interest in industrial apps such as Meituan, which serves multiple business domains via knowledge transfer and meets the diverse interests of users. However, existing methods typically follow an implicit modeling paradigm that blends the knowledge from both the source and target domains, and design intricate network structures to share learned embeddings or patterns between domains to improve recommendation accuracy. Since the transfer of interest signals is unsupervised, these implicit paradigms often struggle with the negative transfer resulting from differences in service functions and presentation forms across different domains. In this paper, we propose a simple and effective EXplicit Interest Transfer framework named EXIT to address the stated challenge. Specifically, we propose a novel label combination approach that enables the model to directly learn beneficial source domain interests through supervised learning, while excluding inappropriate interest signals. Moreover, we introduce a scene selector network to model the interest transfer intensity under fine-grained scenes. Offline experiments conducted on the industrial production dataset and online A/B tests validate the superiority and effectiveness of our proposed framework. Without complex network structures or training processes, EXIT can be easily deployed in the industrial recommendation system. EXIT has been successfully deployed in the online homepage recommendation system of Meituan App, serving the main traffic.

At present, most recommender systems involve two stakeholders, providers and customers. Apart from maximizing the recommendation accuracy, the fairness issue for both sides should also be considered. Most of previous studies try to improve two-sided fairness with post-processing algorithms or fairness-aware loss constraints, which are highly dependent on the heuristic adjustments without respect to the optimization goal of accuracy. In contrast, we propose a novel training framework, adaptive weighting towards two-sided fairness-aware recommendation (named Ada2Fair), which lies in the extension of the accuracy-focused objective to a controllable preference learning loss over the interaction data. Specifically, we adjust the optimization scale of an interaction sample with an adaptive weight generator, and estimate the two-sided fairness-aware weights within model training. During the training process, the recommender is trained with two-sided fairness-aware weights to boost the utility of niche providers and inactive customers in a unified way. Extensive experiments on three public datasets verify the effectiveness of Ada2Fair, which can achieve Pareto efficiency in two-sided fairness-aware recommendation.

Video-Text pre-training aims at learning transferable representations from large-scale video-text pairs via aligning the semantics between visual and textual information. State-of-the-art approaches extract visual features from raw pixels in an end-to-end fashion. However, these methods operate at frame-level directly and thus overlook the spatio-temporal structure of objects in video, which yet has a strong synergy with nouns in textual descriptions. In this work, we propose a simple yet effective module for video-text representation learning, namely RegionLearner, which can take into account the structure of objects during pre-training on large-scale video-text pairs. Given a video, our module (1) first quantizes continuous visual features via clustering patch-features into the same cluster according to content similarity, then (2) generates learnable masks to aggregate fragmentary features into regions with complete semantics, and finally (3) models the spatio-temporal dependencies between different semantic regions. In contrast to using off-the-shelf object detectors, our proposed module does not require explicit supervision and is much more computationally efficient. We pre-train the proposed approach on the public WebVid2M and CC3M datasets. Extensive evaluations on four downstream video-text retrieval benchmarks clearly demonstrate the effectiveness of our RegionLearner.

Within online platforms, it is critical to capture the dynamic user preference from the sequential interaction behaviors for making accurate recommendation over time. Recently, significant progress has been made in sequential recommendation with deep learning. However, existing neural sequential recommender often suffer from the data sparsity issue in real-world applications.

Mainstream Video-Language Pre-training (VLP) models [10, 26, 64] consist of three parts, a video encoder, a text encoder, and a video-text fusion Transformer. They pursue better performance via utilizing heavier unimodal encoders or multimodal fusion Transformers, resulting in increased parameters with lower efficiency in downstream tasks. In this work, we for the first time introduce an end-to-end VLP model, namely all-in-one Transformer, that embeds raw video and textual signals into joint representations using a unified backbone architecture. We argue that the unique temporal information of video data turns out to be a key barrier hindering the design of a modality-agnostic Transformer. To overcome the challenge, we introduce a novel and effective token rolling operation to encode temporal representations from video clips in a non-parametric manner. The careful design enables the representation learning of both video-text multimodal inputs and unimodal inputs using a unified model. Our pretrained ali-in-one Transformer is transferred to various downstream video-text tasks after fine-tuning, including text-video retrieval, video-question answering, multiple choice and video captioning. State-of-the-art performances with the minimal model FLOPs on ten datasets demonstrate the superiority of our method compared to the competitive counterparts. The code and pretrained models are available at https://github.com/showlab/all-in-one.

Vision-Language Pre-Training (VLP) has shown promising capabilities to align image and text pairs, facilitating a broad variety of cross-modal learning tasks. However, we observe that VLP models often lack the visual grounding/localization capability which is critical for many downstream tasks such as visual reasoning. In this work, we propose a novel Position-guided Text Prompt (PTP) paradigm to enhance the visual grounding ability of cross-modal models trained with VLP. Specifically, in the VLP phase, PTP divides the image into N x N blocks, and identifies the objects in each block through the widely used object detector in VLP. It then reformulates the visual grounding task into a fill-in-the-blank problem given a PTP by encouraging the model to predict the objects in the given blocks or regress the blocks of a given object, e.g. filling “[P]” or “[O]” in a PTP “The block [P] has a [O]”. This mechanism improves the visual grounding capability of VLP models and thus helps them better handle various downstream tasks. By introducing PTP into several state-of-the-art VLP frameworks, we observe consistently significant improvements across representative cross-modal learning model architectures and several benchmarks, e.g. zero-shot Flickr30K Retrieval (+4.8 in average recall@1) for ViLT [16] baseline, and COCO Captioning (+5.3 in CIDEr) for SOTA BLIP [19] baseline. Moreover, PTP achieves comparable results with object-detector based methods [8, 23, 45], and much faster inference speed since PTP discards its object detector for inference while the later cannot.

Inspired by the superior language abilities of large language models (LLM), large visionlanguage models (LVLM) have been recently proposed by integrating powerful LLMs for improving the performance on complex multimodal tasks.Despite the promising progress on LVLMs, we find that they suffer from object hallucinations, i.e., they tend to generate objects inconsistent with the target images in the descriptions.To investigate it, this work presents the first systematic study on object hallucination of LVLMs.We conduct the evaluation experiments on several representative LVLMs, and show that they mostly suffer from severe object hallucination issues.We further discuss that the visual instructions may influence the hallucination, and find that: objects that frequently appear in the visual instructions or co-occur with the image objects are obviously prone to be hallucinated by LVLMs.Besides, we further design a polling-based query method called POPE for better evaluation of object hallucination.Experiment results show that our POPE can evaluate object hallucination in a more stable and flexible way.

Panoramic activity recognition is required to jointly identify multi-granularity human behaviors including individual actions, group activities, and global activities in multi-person videos. Previous methods encode these behaviors hierarchically through multiple stages, which disturb the inherent co-occurrence across multi-granularity behaviors in the same scene. To this end, we propose a novel Multi-granularity Unified Perception (MUP) framework that perceives different granularity behaviors universally to explore the co-occurrence motion pattern via the same parameters in an end-to-end fashion. To be specific, the proposed framework stacks three Unified Motion Encoding (UME) blocks for modeling multiple granularity behaviors with shared parameters. UME block mines intra-relevant and cross-relevant semantics synchronously from input feature sequences via Intra-granularity Motion Embedding (IME) and Cross-granularity Motion Prototyping (CMP). In particular, IME aims to model the interactions among visual features within each granularity based on the attention mechanism. CMP aims to aggregate features across different granularities (i.e., person to group) via several learnable prototypes. Extensive experiments demonstrate that MUP outperforms the state-of-the-art methods on JRDB-PAR and has satisfactory interpretability.

Within online platforms, it is critical to capture the semantics of sequential user behaviors for accurately predicting user interests. Recently, significant progress has been made in sequential recommendation with deep learning. However, existing neural sequential recommendation models may not perform well in practice due to the sparsity of the real-world data especially in cold-start scenarios. To tackle this problem, we propose the model ReDA, which stands for Retrieval-enhanced Data Augmentation for modeling sequential user behaviors. The main idea of our approach is to leverage the related information from similar users for generating both relevant and diverse augmentation. First, we train a neural retriever to retrieve the augmentation users according to the se- mantic similarity between user representations, and then conduct two types of data augmentation to generate augmented user representations. Furthermore, these augmented data are incorporated in a contrastive learning framework for learning more capable representations. Extensive experiments conducted on both public and industry datasets demonstrate the superiority of our proposed method over existing state-of-the-art methods, especially when only limited training data is available.

In this paper, we study the task of cold-start sequential recommendation, where new users with very short interaction sequences come with time. We cast this problem as a few-shot learning problem and adopt a meta-learning approach to developing our solution. For our task, a major obstacle of effective knowledge transfer that is there exists significant characteristic divergence between old and new interaction sequences for meta-learning. To address the above issues, we purpose a Multimodal MetaLearning (denoted as MML) approach that incorporates multimodal side information of items (e.g., text and image) into the meta-learning process, to stabilize and improve the meta-learning process for cold-start sequential recommendation. In specific, we design a group of multimodal meta-learners corresponding to each kind of modality, where ID features are used to develop the main meta-learner and the rest text and image features are used to develop auxiliary meta-learners. Instead of simply combing the predictions from different meta-learners, we design an adaptive, learnable fusion layer to integrate the predictions based on different modalities. Meanwhile, we design a cold-start item embedding generator, which utilize multimodal side information to warm up the ID embeddings of new items. Extensive offline and online experiments demonstrate that MML can significantly improve the recommendation performance for cold-start users compared with baseline models. Our code is released at https://github.com/RUCAIBox/MML.

Recently, pre-training based approaches are proposed to leverage self-supervised signals for improving the performance of sequential recommendation. However, most of existing pre-training recommender systems simply model the historical behavior of a user as a sequence, while lack of sufficient consideration on temporal interaction patterns that are useful for modeling user behavior.

Video-Language Pretraining (VLP), which aims to learn transferable representation to advance a wide range of video-text downstream tasks, has recently received increasing attention. Best performing works rely on large-scale, 3rd-person video-text datasets, such as HowTo100M. In this work, we exploit the recently released Ego4D dataset to pioneer Egocentric VLP along three directions. (i) We create EgoClip, a 1st-person video-text pretraining dataset comprising 3.8M clip-text pairs well-chosen from Ego4D, covering a large variety of human daily activities. (ii) We propose a novel pretraining objective, dubbed EgoNCE, which adapts video-text contrastive learning to the egocentric domain by mining egocentric-aware positive and negative samples. (iii) We introduce EgoMCQ, a development benchmark that is close to EgoClip and hence can support effective validation and fast exploration of our design decisions in EgoClip and EgoNCE. Furthermore, we demonstrate strong performance on five egocentric downstream tasks across three datasets: video-text retrieval on EPIC-KITCHENS-100; action recognition on Charades-Ego; natural language query, moment query, and object state change classification on Ego4D challenge benchmarks. The dataset and code are available at https://github.com/showlab/EgoVLP.

Infographic bar charts have been widely adopted for communicating numerical information because of their attractiveness and memorability. However, these infographics are often created manually with general tools, such as PowerPoint and Adobe Illustrator, and merely composed of primitive visual elements, such as text blocks and shapes. With the absence of chart models, updating or reusing these infographics requires tedious and error-prone manual edits. In this paper, we propose a mixed-initiative approach to mitigate this pain point. On one hand, machines are adopted to perform precise and trivial operations, such as mapping numerical values to shape attributes and aligning shapes. On the other hand, we rely on humans to perform subjective and creative tasks, such as changing embellishments or approving the edits made by machines. We encapsulate our technique in a PowerPoint add-in prototype and demonstrate the effectiveness by applying our technique on a diverse set of infographic bar chart examples.

Point-of-Interest (POI) recommendation is an important task in location-based social networks. It facilitates the relation modeling between users and locations. Recently, researchers recommend POIs by long- and short-term interests and achieve success. However, they fail to well capture the periodic interest. People tend to visit similar places at similar times or in similar areas. Existing models try to acquire such kind of periodicity by user's mobility status or time slot, which limits the performance of periodic interest. To this end, we propose to learn spatial-temporal periodic interest. Specifically, in the long-term module, we learn the temporal periodic interest of daily granularity, then utilize intra-level attention to form long-term interest. In the short-term module, we construct various short-term sequences to acquire the spatial-temporal periodic interest of hourly, areal, and hourly-areal granularities, respectively. Finally, we apply inter-level attention to automatically integrate multiple interests. Experiments on two real-world datasets demonstrate the state-of-the-art performance of our method.

Layout representation, which models visual elements and their inter-relations in a canvas, plays a crucial role in graphic design intelligence. With a large variety of layout designs and the unique characteristic of layouts that visual elements are defined as a list of categorical (e.g., type) and numerical (e.g., position and size) properties, it is challenging to learn general and compact representations with limited data. Inspired by the recent success of self-supervised pre-training techniques in various natural language processing tasks, in this paper, we propose CanvasEmb (Canvas Embedding), which pre-trains deep representations from unlabeled graphic designs by jointly conditioning on all the context elements in a canvas, with a multi-dimensional feature encoder and a multi-task learning objective. The pre-trained CanvasEmb model can be fine-tuned with just one additional output layer and with a small size of training data to create models for a wide range of downstream tasks. We verify our approach with presentation slides data. We construct a large-scale dataset with more than one million slides and propose two layout understanding tasks with human-labeled sets, namely element role labeling and image captioning. Evaluation results on these two tasks show that our model with fine-tuning achieves state-of-the-art performance. Furthermore, we conduct a deep analysis aiming to understand the modeling mechanism of CanvasEmb and demonstrate its great potential with two extended applications: layout auto completion and layout retrieval.

Chart images are commonly used for data visualization. Automatically reading the chart values is a key step for chart content understanding. Charts have a lot of variations in style (e.g. bar chart, line chart, pie chart and etc.), which makes pure rule-based data extraction methods difficult to handle. However, it is also improper to directly apply end- to-end deep learning solutions since these methods usually deal with specific types of charts. In this paper, we propose an unified method ChartOCR to extract data from various types of charts. We show that by combing deep framework and rule-based methods, we can achieve a satisfying generalization ability and obtain accurate and semantic-rich intermediate results. Our method extracts the key points that define the chart components. By adjusting the prior rules, the framework can be applied to different chart types. Experiments show that our method achieves state-of-the- art performance with fast processing speed on two public datasets. Besides, we also introduce and evaluate on a large dataset ExcelChart400K for training deep models on chart images. The code and the dataset are publicly available at https://github.com/soap117/DeepRule.

Existing state of the art neural entity linking models employ attention-based bag-of-words context model and pre-trained entity embeddings bootstrapped from word embeddings to assess topic level context compatibility. However, the latent entity type information in the immediate context of the mention is neglected, which causes the models often link mentions to incorrect entities with incorrect type. To tackle this problem, we propose to inject latent entity type information into the entity embeddings based on pre-trained BERT. In addition, we integrate a BERT-based entity similarity score into the local context model of a state-of-the-art model to better capture latent entity type information. Our model significantly outperforms the state-of-the-art entity linking models on standard benchmark (AIDA-CoNLL). Detailed experiment analysis demonstrates that our model corrects most of the type errors produced by the direct baseline.

Learning semantic correspondences between structured input data (e.g., slot-value pairs) and associated texts is a core problem for many downstream NLP applications, e.g., data-to-text generation.Large-scale datasets recently proposed for generation contain loosely corresponding data text pairs, where part of spans in text cannot be aligned to its incomplete paired input.To learn semantic correspondences from such datasets, we propose a two-stage local-to-global alignment (L2GA) framework.First, a local model based on multi-instance learning is applied to build alignments for texts spans that can be directly grounded to its paired structured input.Then, a novel global model built upon a memory-guided conditional random field (CRF) layer aims to infer missing alignments for text spans not supported by paired incomplete inputs, where the memory is designed to leverage alignment clues provided by the local model to strengthen the global model.In this way, the local model and global model can work jointly to learn semantic correspondences in the same framework.Experimental results show that our proposed method can be generalized to both restaurant and computer domains and improve the alignment accuracy.

Creating a good looking chart for better visualization is time consuming. There are plenty of well-designed charts on the Web, which are ideal references for imitation of chart style. However, stored as bitmap images, reference charts have hinder machine interpretation of style settings and thus difficult to be directly applied. In this paper, we extract visual properties from reference chart images as style templates to restyle charts. We first construct a large-scale dataset of 187,059 chart images from real world data, labeled with predefined visual property values. Then we introduce an end-to-end learning network to extract the properties based on two image-encoding approaches. Furthermore, in order to capture spatial relationships of chart objects, which are crucial in solving the task, we propose a novel positional encoding method to integrate clues of relative positions between objects. Experimental results show that our model significantly outperforms baseline models. By adding positional features, our model achieves better performance. Finally, we present the application for chart restyling based on our model.

Bar charts are commonly used for data visualization. One common form of chart distribution is in its image form. To enable machine comprehension of chart images, precise detection of chart components in chart images is a critical step. Existing image object detection methods do not perform well in chart component detection which requires high boundary detection precision. And traditional rule-based approaches lack enough generalization ability. In order to address this problem, we design a novel two-stage component detection framework for bar charts that combines point-based and region-based ideas, by simulating the process that human creating bounding boxes for objects. The experiment on our labeled ChartDet dataset shows our method greatly improves the performance of chart object detection. We further extend our method to a general object detection task and get comparable performance.

Recent neural language generation systems often hallucinate contents (i.e., producing irrelevant or contradicted facts), especially when trained on loosely corresponding pairs of the input structure and text.To mitigate this issue, we propose to integrate a language understanding module for data refinement with selftraining iterations to effectively induce strong equivalence between the input data and the paired text.Experiments on the E2E challenge dataset show that our proposed framework can reduce more than 50% relative unaligned noise from the original data-text pairs.A vanilla sequence-to-sequence neural NLG model trained on the refined data has improved on content correctness compared with the current state-of-the-art ensemble generator.

Shuang Chen, Jinpeng Wang, Xiaocheng Feng, Feng Jiang, Bing Qin, Chin-Yew Lin. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Data-to-text generation aims to generate descriptions given a structured input data (i.e., a table with multiple records).Existing neural methods for encoding input data can be divided into two categories: a) pooling based encoders which ignore dependencies between input records or b) recurrent encoders which model only sequential dependencies between input records.In our investigation, although the recurrent encoder generally outperforms the pooling based encoder by learning the sequential dependencies, it is sensitive to the order of the input records (i.e., performance decreases when injecting the random shuffling noise over input data).To overcome this problem, we propose to adopt the self-attention mechanism to learn dependencies between arbitrary input records.Experimental results show the proposed method achieves comparable results and remains stable under random shuffling over input data.

For the task of entity disambiguation, mention contexts and entity descriptions both contain various kinds of information content while only a subset of them are helpful for disambiguation. In this paper, we propose a type-aware co-attention model for entity disambiguation, which tries to identify the most discriminative words from mention contexts and most relevant sentences from corresponding entity descriptions simultaneously. To bridge the semantic gap between mention contexts and entity descriptions, we further incorporate entity type information to enhance the co-attention mechanism. Our evaluation shows that the proposed model outperforms the state-of-the-arts on three public datasets. Further analysis also confirms that both the co-attention mechanism and the type-aware mechanism are effective.

The task of entity linking aims to identify concepts mentioned in a text fragments and link them to a reference knowledge base.Entity linking in long text has been well studied in previous work.However, short text entity linking is more challenging since the texts are noisy and less coherent.To better utilize the local information provided in short texts, we propose a novel neural network framework, Aggregated Semantic Matching (ASM), in which two different aspects of semantic information between the local context and the candidate entity are captured via representationbased and interaction-based neural semantic matching models, and then two matching signals work jointly for disambiguation with a rank aggregation mechanism.Our evaluation shows that the proposed model outperforms the state-of-the-arts on public tweet datasets.

Recent neural models for data-to-text generation are mostly based on data-driven end-toend training over encoder-decoder networks.Even though the generated texts are mostly fluent and informative, they often generate descriptions that are not consistent with the input structured data.This is a critical issue especially in domains that require inference or calculations over raw data.In this paper, we attempt to improve the fidelity of neural data-to-text generation by utilizing pre-executed symbolic operations.We propose a framework called Operationguided Attention-based sequence-to-sequence network (OpAtt), with a specifically designed gating mechanism as well as a quantization module for operation results to utilize information from pre-executed operations.Experiments on two sports datasets show our proposed method clearly improves the fidelity of the generated texts to the input structured data.

Previous work on grounded language learning did not fully capture the semantics underlying the correspondences between structured world state representations and texts, especially those between numerical values and lexical terms.In this paper, we attempt at learning explicit latent semantic annotations from paired structured tables and texts, establishing correspondences between various types of values and texts.We model the joint probability of data fields, texts, phrasal spans, and latent annotations with an adapted semi-hidden Markov model, and impose a soft statistical constraint to further improve the performance.As a by-product, we leverage the induced annotations to extract templates for language generation.Experimental results suggest the feasibility of the setting in this study, as well as the effectiveness of our proposed framework.1

Network embedding is a classical task which aims to map the nodes of a network to low-dimensional vectors. Most of the previous network embedding methods are trained in an unsupervised scheme. Then the learned node embeddings can be used as inputs of many machine learning tasks such as node classification, attribute inference. However, the discrimination validity of the node embeddings maybe improved by considering the node label information and the node attribute information. Inspired by traditional semi-supervised learning techniques, we explore to train the node embeddings and the node classifiers simultaneously with the text attributes information in a flexible framework. We present NLSTNE (Non-Linear Smoothed Transductive Network Embedding), a transductive network embedding method, whose embeddings are enhanced by modeling the non-linear pairwise similarity between the nodes and the non-linear relationship between the nodes and the text attributes. We use the node classification task to evaluate the quality of node embeddings learned by different models on four real-world network datasets . The experimental results demonstrate that our model outperforms several state-of-the-art network embedding methods.

We present in this article an automated framework that extracts product adopter information from online reviews and incorporates the extracted information into feature-based matrix factorization for more effective product recommendation. In specific, we propose a bootstrapping approach for the extraction of product adopters from review text and categorize them into a number of different demographic categories. The aggregated demographic information of many product adopters can be used to characterize both products and users in the form of distributions over different demographic categories. We further propose a graph-based method to iteratively update user- and product-related distributions more reliably in a heterogeneous user--product graph and incorporate them as features into the matrix factorization approach for product recommendation. Our experimental results on a large dataset crawled from J ing D ong , the largest B2C e-commerce website in China, show that our proposed framework outperforms a number of competitive baselines for product recommendation.

In this paper, we propose to study the problem of identifying and classifying tweets into intent categories. For example, a tweet “I wanna buy a new car” indicates the user’s intent for buying a car. Identifying such intent tweets will have great commercial value among others. In particular, it is important that we can distinguish different types of intent tweets. We propose to classify intent tweets into six categories, namely Food & Drink, Travel, Career & Education, Goods & Services, Event and Activities and Trifle. We propose a semisupervised learning approach to categorizing intent tweets into the six categories.We construct a test collection by using a bootstrap method. Our experimental results show that our approach is effective in inferring intent categories for tweets.

In this paper, we explore the idea of social role theory (SRT) and propose a novel regularized topic model which incorporates SRT into the generative process of social media content. We assume that a user can play multiple social roles, and each social role serves to fulfil different duties and is associated with a role-driven distribution over latent topics. In particular, we focus on social roles corresponding to the most common social activities on social networks. Our model is instantiated on microblogs, i.e., Twitter and community question-answering (cQA), i.e., Yahoo!Answers, where social roles on Twitter include “originators” and “propagators”, and roles on cQA are “askers” and “answerers”. Both explicit and implicit interactions between users are taken into account and modeled as regularization factors. To evaluate the performance of our proposed method, we have conducted extensive experiments on two Twitter datasets and two cQA datasets. Furthermore, we also consider multi-role modeling for scientific papers where an author's research expertise area is considered as a social role. A novel application of detecting users' research interests through topical keyword labeling based on the results of our multi-role model has been presented. The evaluation results have shown the feasibility and effectiveness of our model.

Learning user interests from online social networks helps to better understand user behaviors and provides useful guidance to design user-centric applications. Apart from analyzing users' online content, it is also important to consider users' social connections in the social Web. Graph regularization methods have been widely used in various text mining tasks, which can leverage the graph structure information extracted from data. Previously, graph regularization methods operate under the cluster assumption that nearby nodes are more similar and nodes on the same structure (typically referred to as a cluster or a manifold) are likely to be similar. We argue that learning user interests from complex, sparse, and dynamic social networks should be based on the link structure assumption under which node similarities are evaluated based on the local link structures instead of explicit links between two nodes. We propose a regularization framework based on the relation bipartite graph, which can be constructed from any type of relations. Using Twitter as our case study, we evaluate our proposed framework from social networks built from retweet relations. Both quantitative and qualitative experiments show that our proposed method outperforms a few competitive baselines in learning user interests over a set of predefined topics. It also gives superior results compared to the baselines on retweet prediction and topical authority identification.

A large number of studies have been devoted to modeling the contents and interactions between users on Twitter. In this paper, we propose a method inspired from Social Role Theory (SRT), which assumes that a user behaves differently with different roles in the generation process of Twitter content. We consider the two most distinctive social roles on Twitter: originator and propagator, who respectively posts original messages and retweets or forwards the messages from others. In addition, we also consider role-specific social interactions, especially implicit interactions between users who share some common interests. All the above elements are integrated into a novel regularized topic model. We evaluate the proposed method on real Twitter data. The results show that our method is more effective than the existing ones which do not distinguish social roles.

Hot trends are likely to bring new business opportunities.For example, "Air Pollution" might lead to a significant increase of the sales of related products, e.g., mouth mask.For ecommerce companies, it is very important to make rapid and correct response to these hot trends in order to improve product sales.In this paper, we take the initiative to study the task of how to identify trend related products.The major novelty of our work is that we automatically learn commercial intents revealed from microblogs.We carefully construct a data collection for this task and present quite a few insightful findings.In order to solve this problem, we further propose a graph based method, which jointly models relevance and associativity.We perform extensive experiments and the results showed that our methods are very effective.