More Like this

1. Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer

   https://doi.org/10.18653/v1/2022.emnlp-main.149  

   Jiang, Zhengbao ; Gao, Luyu ; Wang, Zhiruo ; Araki, Jun ; Ding, Haibo ; Callan, Jamie ; Neubig, Graham ( January 2022 , Association for Computational Linguistics)

   Systems for knowledge-intensive tasks such as open-domain question answering (QA) usually consist of two stages: efficient retrieval of relevant documents from a large corpus and detailed reading of the selected documents. This is usually done through two separate models, a retriever that encodes the query and finds nearest neighbors, and a reader based on Transformers. These two components are usually modeled separately, which necessitates a cumbersome implementation and is awkward to optimize in an end-to-end fashion. In this paper, we revisit this design and eschew the separate architecture and training in favor of a single Transformer that performs retrieval as attention (RAA), and end-to-end training solely based on supervision from the end QA task. We demonstrate for the first time that an end-to-end trained single Transformer can achieve both competitive retrieval and QA performance on in-domain datasets, matching or even slightly outperforming state-of-the-art dense retrievers and readers. Moreover, end-to-end adaptation of our model significantly boosts its performance on out-of-domain datasets in both supervised and unsupervised settings, making our model a simple and adaptable end-to-end solution for knowledge-intensive tasks. 

   more » « less
2. Noisy Private Information Retrieval: On Separability of Channel Coding and Information Retrieval

   https://doi.org/10.1109/TIT.2019.2935440  

   Banawan, Karim ; Ulukus, Sennur ( December 2019 , IEEE Transactions on Information Theory)

   null (Ed.)
3. Information Retrieval and Interaction System (IRIS): A Toolkit for Investigating Information Retrieval and Interaction Activities

   https://doi.org/10.1145/3176349.3176895  

   Pulliza, Jonathan ; Shah, Chirag ( January 2018 , ACM Conference on Human Information Interaction and Retrieval (CHIIR))

   In this demo we present IRIS, an open-source framework that provides a set of simple and modular document operators that can be combined in various ways to create more interesting and advanced functionality otherwise unavailable during most information search sessions. Those functionalities include summarization, ranking, filtering and query. The goal is to support users looking for, collecting, and synthesizing information. The system is also easily extendable, allowing for customized functionality for users during information sessions and researchers studying higher levels of abstraction for information retrieval. The demo shows the front end interactions using a browser plug-in that offers new interactions with documents during search sessions, as well as the back-end components driving the system. 

   more » « less
4. DPRL Systems in the CLEF 2021 ARQMath Lab: Sentence-BERT for Answer Retrieval, Learning-to-Rank for Formula Retrieval

   Mansouri, Behrooz ; Oard, Douglas W. ; Zanibbi, Richard ( July 2021 , Proc. CLEF 2021 (CEUR Working Notes))
5. CSurF: Sparse Lexical Retrieval through Contextualized Surface Forms

   https://doi.org/10.1145/3578337.3605126  

   Fan, Zhen ; Gao, Luyu ; Callan, Jamie ( August 2023 , ACM)

   Lexical exact-match systems perform text retrieval efficiently with sparse matching signals and fast retrieval through inverted lists, but naturally suffer from the mismatch between lexical surface form and implicit term semantics. This paper proposes to directly bridge the surface form space and the term semantics space in lexical exact-match retrieval via contextualized surface forms (CSF). Each CSF pairs a lexical surface form with a context source, and is represented by a lexical form weight and a contextualized semantic vector representation. This framework is able to perform sparse lexicon-based retrieval by learning to represent each query and document as a "bag-of-CSFs", simultaneously addressing two key factors in sparse retrieval: vocabulary expansion of surface form and semantic representation of term meaning. At retrieval time, it efficiently matches CSFs through exact-match of learned surface forms, and effectively scores each CSF pair via contextual semantic representations, leading to joint improvement in both term match and term scoring. Multiple experiments show that this approach successfully resolves the main mismatch issues in lexical exact-match retrieval and outperforms state-of-the-art lexical exact-match systems, reaching comparable accuracy as lexical all-to-all soft match systems as an efficient exact-match-based system. 

   more » « less