Related papers: DREQ: Document Re-Ranking Using Entity-based Query…

Contrastive learning has been the dominant approach to training dense retrieval models. In this work, we investigate the impact of ranking context - an often overlooked aspect of learning dense retrieval models. In particular, we examine…

CODEC is a document and entity ranking benchmark that focuses on complex research topics. We target essay-style information needs of social science researchers, i.e. "How has the UK's Open Banking Regulation benefited Challenger Banks?".…

Entity Linking has two main open areas of research: 1) generate candidate entities without using alias tables and 2) generate more contextual representations for both mentions and entities. Recently, a solution has been proposed for the…

Table retrieval is essential for accessing information stored in structured tabular formats; however, it remains less explored than text retrieval. The content of the table primarily consists of phrases and words, which include a large…

Despite considerable progress in neural relevance ranking techniques, search engines still struggle to process complex queries effectively - both in terms of precision and recall. Sparse and dense Pseudo-Relevance Feedback (PRF) approaches…

State-of-the-art neural models typically encode document-query pairs using cross-attention for re-ranking. To this end, models generally utilize an encoder-only (like BERT) paradigm or an encoder-decoder (like T5) approach. These paradigms,…

Pairing a lexical retriever with a neural re-ranking model has set state-of-the-art performance on large-scale information retrieval datasets. This pipeline covers scenarios like question answering or navigational queries, however, for…

Retrieval-Augmented Generation (RAG) over Knowledge Graphs (KGs) suffers from the fact that indexing approaches may lose important contextual nuance when text is reduced to triples, thereby degrading performance in downstream…

The hypergraph-of-entity was conceptually proposed as a general model for entity-oriented search. However, only the performance for ad hoc document retrieval had been assessed. We continue this line of research by also evaluating ad hoc…

We present two novel models of document coherence and their application to information retrieval (IR). Both models approximate document coherence using discourse entities, e.g. the subject or object of a sentence. Our first model views text…

Dense retrieval models, which aim at retrieving the most relevant document for an input query on a dense representation space, have gained considerable attention for their remarkable success. Yet, dense models require a vast amount of…

A fundamental goal of search engines is to identify, given a query, documents that have relevant text. This is intrinsically difficult because the query and the document may use different vocabulary, or the document may contain query words…

Document-level relation extraction aims to extract relations among entities within a document. Compared with its sentence-level counterpart, Document-level relation extraction requires inference over multiple sentences to extract complex…

Deep neural networks have achieved significant improvements in information retrieval (IR). However, most existing models are computational costly and can not efficiently scale to long documents. This paper proposes a novel End-to-End neural…

Retrieval-Augmented Generation (RAG) has recently demonstrated the performance of Large Language Models (LLMs) in the knowledge-intensive tasks such as Question-Answering (QA). RAG expands the query context by incorporating external…

Entities are at the center of how we represent and aggregate knowledge. For instance, Encyclopedias such as Wikipedia are structured by entities (e.g., one per Wikipedia article). The ability to retrieve such entities given a query is…

Reading comprehension models are based on recurrent neural networks that sequentially process the document tokens. As interest turns to answering more complex questions over longer documents, sequential reading of large portions of text…

Dense Retrieval (DR) reaches state-of-the-art results in first-stage retrieval, but little is known about the mechanisms that contribute to its success. Therefore, in this work, we conduct an interpretation study of recently proposed DR…

BERT based ranking models have achieved superior performance on various information retrieval tasks. However, the large number of parameters and complex self-attention operation come at a significant latency overhead. To remedy this, recent…

Despite the advantages of their low-resource settings, traditional sparse retrievers depend on exact matching approaches between high-dimensional bag-of-words (BoW) representations of both the queries and the collection. As a result,…