Generative Retrieval introduces a new approach to Information Retrieval by reframing it as a constrained generation task, leveraging recent advancements in Autoregressive (AR) language models. However, AR-based Generative Retrieval methods suffer from high inference latency and cost compared to traditional dense retrieval techniques, limiting their practical applicability. This paper investigates fully Non-autoregressive (NAR) language models as a more efficient alternative for generative retrieval. While standard NAR models alleviate latency and cost concerns, they exhibit a significant drop in retrieval performance (compared to AR models) due to their inability to capture dependencies between target tokens. To address this, we question the conventional choice of limiting the target token space to solely words or sub-words. We propose PIXNAR, a novel approach that expands the target vocabulary of NAR models to include multi-word entities and common phrases (up to 5 million tokens), thereby reducing token dependencies. PIXNAR employs inference optimization strategies to maintain low inference latency despite the significantly larger vocabulary. Our results demonstrate that PIXNAR achieves a relative improvement of 31.0% in MRR@10 on MS MARCO and 23.2% in Hits@5 on Natural Questions compared to standard NAR models with similar latency and cost. Furthermore, online A/B experiments on a large commercial search engine show significant increase in clicks and revenue.

Extreme Multi-label Classification (XMC) involves predicting a subset of relevant labels from an extremely large label space, given an input query and labels with textual features.Models developed for this problem have conventionally made use of dual encoder (DE) to embed the queries and label texts and one-vs-all (OvA) classifiers to rerank the shortlisted labels by the DE.While such methods have shown empirical success, a major drawback is their computational cost, often requiring upto 16 GPUs to train on the largest public dataset.Such a high cost is a consequence of calculating the loss over the entire label space.While shortlisting strategies have been proposed for classifiers, we aim to study such methods for the DE framework.In this work, we develop UniDEC, a loss-independent, end-to-end trainable framework which trains the DE and classifier together in a unified manner with a multi-class loss, while reducing the computational cost by 4 -16×.This is done via the proposed pick-some-label (PSL) reduction, which aims to compute the loss on only a subset of positive and negative labels.These labels are carefully chosen in-batch so as to maximise their supervisory signals.Not only does the proposed framework achieve state-of-the-art results on datasets with labels in the order of millions, it is also computationally and resource efficient in achieving this performance on a single GPU.Code is made available at https://github.com/the-catalyst/UniDEC.

Sponsored search is a key revenue source for search engines, where advertisers bid on keywords to target users or search queries of interest. However, finding relevant keywords for a given query is challenging due to the large and dynamic keyword space, ambiguous user/advertiser intents, and diverse possible topics and languages. In this work, we present a comprehensive comparison between two paradigms for online query rewriting: Generative (NLG) and Dense Retrieval (DR) methods. We observe that both methods offer complementary benefits that are additive. As a result, we show that around 40% of the high-quality keywords retrieved by the two approaches are unique and not retrieved by the other. To leverage the strengths of both methods, we propose CLOVER-Unity, a novel approach that unifies generative and dense retrieval methods in one single model. Through offline experiments, we show that the NLG and DR components of CLOVER-Unity consistently outperform individually trained NLG and DR models on public and internal benchmarks. Furthermore, we show that CLOVER-Unity achieves 9.8% higher good keyword density than the ensemble of two separate DR and NLG models while reducing computational costs by almost half. We conduct extensive online A/B experiments on Microsoft Bing in 140+ countries and achieve improved user engagement, with an average increase in total clicks by 0.89% and increased revenue by 1.27%. We also share our practical lessons and optimization tricks for deploying such unified models in production.

Extreme Classification (XC) seeks to tag data points with the most relevant subset of labels from an extremely large label set. Performing deep XC with dense, learnt representations for data points and labels has attracted much attention due to its superiority over earlier XC methods that used sparse, hand-crafted features. Negative mining techniques have emerged as a critical component of all deep XC methods, allowing them to scale to millions of labels. However, despite recent advances, training deep XC models with large encoder architectures such as transformers remains challenging. This paper notices that memory overheads of popular negative mining techniques often force mini-batch sizes to remain small and slow training down. In response, this paper introduces NGAME, a light-weight mini-batch creation technique that offers provably accurate in-batch negative samples. This allows training with larger mini-batches offering significantly faster convergence and higher accuracies than existing negative sampling techniques. NGAME was found to be up to 16% more accurate than state-of-the-art methods on a wide array of benchmark datasets for extreme classification, as well as 3% more accurate at retrieving search engine queries in response to a user webpage visit to show personalized ads. In live A/B tests on a popular search engine, NGAME yielded up to 23% gains in click-through-rates. Code for NGAME is available at https://github.com/Extreme-classification/ngame

As Approximate Nearest Neighbor Search (ANNS)-based dense retrieval becomes ubiquitous for search and recommendation scenarios, efficiently answering filtered ANNS queries has become a critical requirement. Filtered ANNS queries ask for the nearest neighbors of a query’s embedding from the points in the index that match the query’s labels such as date, price range, language. There has been little prior work on algorithms that use label metadata associated with vector data to build efficient indices for filtered ANNS queries. Consequently, current indices have high search latency or low recall which is not practical in interactive web-scenarios. We present two algorithms with native support for faster and more accurate filtered ANNS queries: one with streaming support, and another based on batch construction. Central to our algorithms is the construction of a graph-structured index which forms connections not only based on the geometry of the vector data, but also the associated label set. On real-world data with natural labels, both algorithms are an order of magnitude or more efficient for filtered queries than the current state of the art algorithms. The generated indices also be queried from an SSD and support thousands of queries per second at over recall@10.

Retrieving keywords (bidwords) with the same intent as query, referred to as close variant keywords, is of prime importance for effective targeted search advertising. For head and torso search queries, sponsored search engines use a huge repository of same intent queries and keywords, mined ahead of time. Online, this repository is used to rewrite the query and then lookup the rewrite in a repository of bid keywords contributing to significant revenue. Recently generative retrieval models have been shown to be effective at the task of generating such query rewrites. We observe two main limitations of such generative models. First, rewrites generated by these models exhibit low lexical diversity, and hence the rewrites fail to retrieve relevant keywords that have diverse linguistic variations. Second, there is a misalignment between the training objective - the likelihood of training data, v/s what we desire - improved quality and coverage of rewrites. In this work, we introduce CLOVER, a framework to generate both high-quality and diverse rewrites by optimizing for human assessment of rewrite quality using our diversity-driven reinforcement learning algorithm. We use an evaluation model, trained to predict human judgments, as the reward function to finetune the generation policy. We empirically show the effectiveness of our proposed approach through offline experiments on search queries across geographies spanning three major languages. We also perform online A/B experiments on Bing, a large commercial search engine, which shows (i) better user engagement with an average increase in clicks by 12.83% accompanied with an average defect reduction by 13.97%, and (ii) improved revenue by 21.29%.

This paper develops the GalaXC algorithm for Extreme Classification, where the task is to annotate a document with the most relevant subset of labels from an extremely large label set. Extreme classification has been successfully applied to several real world web-scale applications such as web search, product recommendation, query rewriting, etc. GalaXC identifies two critical deficiencies in leading extreme classification algorithms. First, existing approaches generally assume that documents and labels reside in disjoint sets, even though in several applications, labels and documents cohabit the same space. Second, several approaches, albeit scalable, do not utilize various forms of metadata offered by applications, such as label text and label correlations. To remedy these, GalaXC presents a framework that enables collaborative learning over joint document-label graphs at massive scales, in a way that naturally allows various auxiliary sources of information, including label metadata, to be incorporated. GalaXC also introduces a novel label-wise attention mechanism to meld high-capacity extreme classifiers with its framework. An efficient end-to-end implementation of GalaXC is presented that could be trained on a dataset with 50M labels and 97M training documents in less than 100 hours on 4 × V100 GPUs. This allowed GalaXC to not only scale to applications with several millions of labels, but also be up to 18% more accurate than leading deep extreme classifiers, while being upto 2-50 × faster to train and 10 × faster to predict on benchmark datasets. GalaXC is particularly well-suited to warm-start scenarios where predictions need to be made on data points with partially revealed label sets, and was found to be up to 25% more accurate than extreme classification algorithms specifically designed for warm start settings. In A/B tests conducted on the Bing search engine, GalaXC could improve the Click Yield (CY) and coverage by 1.52% and 1.11% respectively. Code for GalaXC is available at https://github.com/Extreme-classification/GalaXC

Built on top of human resources management databases within the enterprise, we present a decision support system for managing and optimizing screening activities during the hiring process in a large organization. The basic idea is to prioritize the efforts of human resource practitioners to focus on candidates that are likely of high quality, that are likely to accept a job offer if made one, and that are likely to remain with the organization for the long term. To do so, the system first individually ranks candidates along several dimensions using a keyword matching algorithm and several bipartite ranking algorithms with univariate loss trained on historical actions. Next, individual rankings are aggregated to derive a single list that is presented to the recruitment team through an interactive portal. The portal supports multiple filters that facilitate effective identification of candidates. We demonstrate the usefulness of our system on data collected from a large organization over several years with business value metrics showing greater hiring yield with less interviews. Similarly, using historical pre-hire data we demonstrate accurate identification of candidates that will have quickly left the organization. The system has been deployed as described in a large globally integrated enterprise.

Online forums have become a popular source of information due to the unique nature of information they contain. Internet users use these forums to get opinions of other people on issues and to find factual answers to specific questions. Topics discussed in online forum threads can be subjective seeking personal opinions or non-subjective seeking factual information. Hence, knowing subjectivity orientation of threads would help forum search engines to satisfy user's information needs more effectively by matching the subjectivities of user's query and topics discussed in the threads in addition to lexical match between the two. We study methods to analyze the subjectivity of online forum threads. Experimental results on a popular online forum demonstrate the effectiveness of our methods.

Online forums are becoming a popular way of finding useful information on the web. Search over forums for existing discussion threads so far is limited to keyword-based search due to the minimal effort required on part of the users. However, it is often not possible to capture all the relevant context in a complex query using a small number of keywords. Example-based search that retrieves similar discussion threads given one exemplary thread is an alternate approach that can help the user provide richer context and vastly improve forum search results. In this paper, we address the problem of finding similar threads to a given thread. Towards this, we propose a novel methodology to estimate similarity between discussion threads. Our method exploits the thread structure to decompose threads in to set of weighted overlapping components. It then estimates pairwise thread similarities by quantifying how well the information in the threads are mutually contained within each other using lexical similarities between their underlying components. We compare our proposed methods on real datasets against state-of-the-art thread retrieval mechanisms wherein we illustrate that our techniques outperform others by large margins on popular retrieval evaluation measures such as NDCG, MAP, [email protected] and MRR. In particular, consistent improvements of up to 10% are observed on all evaluation measures.

Community Question Answering portals like Yahoo! Answers have recently become a popular method for seeking information online. Users express their information need as questions for which other users generate potential answers. These questions are organized into pre-defined hierarchical categories to facilitate effective answering, hence Question Classification is an important aspect of these systems. In this paper we propose a novel system, CQC, for automatically classifying new questions into one of the hierarchical categories. Experiments conducted on large scale real data from Yahoo Answers! show that the proposed techniques are effective and outperform existing methods significantly.

Companies often receive thousands of resumes for each job posting and employ dedicated screeners to short list qualified applicants. In this paper, we present PROSPECT, a decision support tool to help these screeners shortlist resumes efficiently. Prospect mines resumes to extract salient aspects of candidate profiles like skills, experience in each skill, education details and past experience. Extracted information is presented in the form of facets to aid recruiters in the task of screening. We also employ Information Retrieval techniques to rank all applicants for a given job opening. In our experiments we show that extracted information improves our ranking by 30% there by making screening task simpler and more efficient.

To take the first step beyond keyword-based search toward entity-based search, suitable token spans ("spots") on documents must be identified as references to real-world entities from an entity catalog. Several systems have been proposed to link spots on Web pages to entities in Wikipedia. They are largely based on local compatibility between the text around the spot and textual metadata associated with the entity. Two recent systems exploit inter-label dependencies, but in limited ways. We propose a general collective disambiguation approach. Our premise is that coherent documents refer to entities from one or a few related topics or domains. We give formulations for the trade-off between local spot-to-entity compatibility and measures of global coherence between entities. Optimizing the overall entity assignment is NP-hard. We investigate practical solutions based on local hill-climbing, rounding integer linear programs, and pre-clustering entities followed by local optimization within clusters. In experiments involving over a hundred manually-annotated Web pages and tens of thousands of spots, our approaches significantly outperform recently-proposed algorithms.