@inproceedings{bansal-etal-2022-r3,
title = "R3 : Refined Retriever-Reader pipeline for Multidoc2dial",
author = "Bansal, Srijan and
Tripathi, Suraj and
Agarwal, Sumit and
Gururaja, Sireesh and
Veerubhotla, Aditya Srikanth and
Dutt, Ritam and
Mitamura, Teruko and
Nyberg, Eric",
editor = "Feng, Song and
Wan, Hui and
Yuan, Caixia and
Yu, Han",
booktitle = "Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.dialdoc-1.17",
doi = "10.18653/v1/2022.dialdoc-1.17",
pages = "148--154",
abstract = "In this paper, we present our submission to the DialDoc shared task based on the MultiDoc2Dial dataset. MultiDoc2Dial is a conversational question answering dataset that grounds dialogues in multiple documents. The task involves grounding a user{'}s query in a document followed by generating an appropriate response. We propose several improvements over the baseline{'}s retriever-reader architecture to aid in modeling goal-oriented dialogues grounded in multiple documents. Our proposed approach employs sparse representations for passage retrieval, a passage re-ranker, the fusion-in-decoder architecture for generation, and a curriculum learning training paradigm. Our approach shows a 12 point improvement in BLEU score compared to the baseline RAG model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bansal-etal-2022-r3">
<titleInfo>
<title>R3 : Refined Retriever-Reader pipeline for Multidoc2dial</title>
</titleInfo>
<name type="personal">
<namePart type="given">Srijan</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suraj</namePart>
<namePart type="family">Tripathi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sumit</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sireesh</namePart>
<namePart type="family">Gururaja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aditya</namePart>
<namePart type="given">Srikanth</namePart>
<namePart type="family">Veerubhotla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritam</namePart>
<namePart type="family">Dutt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Teruko</namePart>
<namePart type="family">Mitamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Nyberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Song</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caixia</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Han</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present our submission to the DialDoc shared task based on the MultiDoc2Dial dataset. MultiDoc2Dial is a conversational question answering dataset that grounds dialogues in multiple documents. The task involves grounding a user’s query in a document followed by generating an appropriate response. We propose several improvements over the baseline’s retriever-reader architecture to aid in modeling goal-oriented dialogues grounded in multiple documents. Our proposed approach employs sparse representations for passage retrieval, a passage re-ranker, the fusion-in-decoder architecture for generation, and a curriculum learning training paradigm. Our approach shows a 12 point improvement in BLEU score compared to the baseline RAG model.</abstract>
<identifier type="citekey">bansal-etal-2022-r3</identifier>
<identifier type="doi">10.18653/v1/2022.dialdoc-1.17</identifier>
<location>
<url>https://aclanthology.org/2022.dialdoc-1.17</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>148</start>
<end>154</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T R3 : Refined Retriever-Reader pipeline for Multidoc2dial
%A Bansal, Srijan
%A Tripathi, Suraj
%A Agarwal, Sumit
%A Gururaja, Sireesh
%A Veerubhotla, Aditya Srikanth
%A Dutt, Ritam
%A Mitamura, Teruko
%A Nyberg, Eric
%Y Feng, Song
%Y Wan, Hui
%Y Yuan, Caixia
%Y Yu, Han
%S Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F bansal-etal-2022-r3
%X In this paper, we present our submission to the DialDoc shared task based on the MultiDoc2Dial dataset. MultiDoc2Dial is a conversational question answering dataset that grounds dialogues in multiple documents. The task involves grounding a user’s query in a document followed by generating an appropriate response. We propose several improvements over the baseline’s retriever-reader architecture to aid in modeling goal-oriented dialogues grounded in multiple documents. Our proposed approach employs sparse representations for passage retrieval, a passage re-ranker, the fusion-in-decoder architecture for generation, and a curriculum learning training paradigm. Our approach shows a 12 point improvement in BLEU score compared to the baseline RAG model.
%R 10.18653/v1/2022.dialdoc-1.17
%U https://aclanthology.org/2022.dialdoc-1.17
%U https://doi.org/10.18653/v1/2022.dialdoc-1.17
%P 148-154
Markdown (Informal)
[R3 : Refined Retriever-Reader pipeline for Multidoc2dial](https://aclanthology.org/2022.dialdoc-1.17) (Bansal et al., dialdoc 2022)
ACL
- Srijan Bansal, Suraj Tripathi, Sumit Agarwal, Sireesh Gururaja, Aditya Srikanth Veerubhotla, Ritam Dutt, Teruko Mitamura, and Eric Nyberg. 2022. R3 : Refined Retriever-Reader pipeline for Multidoc2dial. In Proceedings of the Second DialDoc Workshop on Document-grounded Dialogue and Conversational Question Answering, pages 148–154, Dublin, Ireland. Association for Computational Linguistics.