BM25

We approached the problem as learning how to order documents by estimated relevance with respect to a user query. Our support vector machines based classifier learns from the relevance judgments …...

AbstractRecent work on open domain question answering (QA) assumes strong supervision of the supporting evidence and/or assumes a blackbox information retrieval (IR) system to retrieve evidence candidates. We argue that …...

AbstractWe show that it is feasible to perform entity linking by training a dual encoder (two-tower) model that encodes mentions and entities in the same dense vector space, where candidate …...

AbstractCommunity Question Answering forums are popular among Internet users, and a basic problem they encounter is trying to find out if their question has already been posed before. To address …...

AbstractOpen-domain question answering relies on efficient passage retrieval to select candidate contexts, where traditional sparse vector space models, such as TF-IDF or BM25, are the de facto method. In this …...

AbstractWe present a query-based biomedical information retrieval task across two vastly different genres – newswire and research literature – where the goal is to find the research publication that supports …...

AbstractWe present our work on aligning the Unified Medical Language System (UMLS) to Wikipedia, to facilitate manual alignment of the two resources. We propose a cross-lingual neural reranking model to …...

AbstractInformation seeking is an essential step for open-domain question answering to efficiently gather evidence from a large corpus. Recently, iterative approaches have been proven to be effective for complex questions, …...

AbstractFalse claims that have been previously fact-checked can still spread on social media. To mitigate their continual spread, detecting previously fact-checked claims is indispensable. Given a claim, existing works focus …...

AbstractClassical information retrieval systems such as BM25 rely on exact lexical match and can carry out search efficiently with inverted list index. Recent neural IR models shifts towards soft matching …...

AbstractMany recent approaches towards neural information retrieval mitigate their computational costs by using a multi-stage ranking pipeline. In the first stage, a number of potentially relevant candidates are retrieved using …...

AbstractWe present a large, challenging dataset, COUGH, for COVID-19 FAQ retrieval. Similar to a standard FAQ dataset, COUGH consists of three parts: FAQ Bank, Query Bank and Relevance Set. The …...

AbstractThis study describes the development of a Portuguese Community-Question Answering benchmark in the domain of Diabetes Mellitus using a Recognizing Question Entailment (RQE) approach. Given a premise question, RQE aims …...

BERT, which has been successfully applied to many types of natural language process- ing (NLP) tasks, is also effective with vari- ous information retrieval (IR) tasks. However, it is not …...

AbstractMajor scandals in corporate history have urged the need for regulatory compliance, where organizations need to ensure that their controls (processes) comply with relevant laws, regulations, and policies. However, keeping …...

AbstractRecent work has shown that dense passage retrieval techniques achieve better ranking accuracy in open-domain question answering compared to sparse retrieval techniques such as BM25, but at the cost of …...

AbstractUnsupervised style transfer models are mainly based on an inductive learning approach, which represents the style as embeddings, decoder parameters, or discriminator parameters and directly applies these general rules to …...

Medical entity retrieval is an integral compo- nent for understanding and communicating in- formation across various health systems. Cur- rent approaches tend to work well on specific medical domains but …...

AbstractTo alleviate the data scarcity problem in training question answering systems, recent works propose additional intermediate pre-training for dense passage retrieval (DPR). However, there still remains a large discrepancy between …...

AbstractDense retrievers for open-domain question answering (ODQA) have been shown to achieve impressive performance by training on large datasets of question-passage pairs. In this work we ask whether this dependence …...

AbstractIR models using a pretrained language model significantly outperform lexical approaches like BM25. In particular, SPLADE, which encodes texts to sparse vectors, is an effective model for practical use because …...

AbstractMulti-vector retrieval methods combine the merits of sparse (e.g. BM25) and dense (e.g. DPR) retrievers and have achieved state-of-the-art performance on various retrieval tasks. These methods, however, are orders of …...

AbstractVerbatim queries submitted to search engines often do not sufficiently describe the user’s search intent. Pseudo-relevance feedback (PRF) techniques, which modify a query’srepresentation using the top-ranked documents, have been shown …...