@inproceedings{kongyoung-etal-2022-monoqa,
title = "mono{QA}: Multi-Task Learning of Reranking and Answer Extraction for Open-Retrieval Conversational Question Answering",
author = "Kongyoung, Sarawoot and
Macdonald, Craig and
Ounis, Iadh",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.485",
doi = "10.18653/v1/2022.emnlp-main.485",
pages = "7207--7218",
abstract = "To address the Conversational Question Answering (ORConvQA) task, previous work has considered an effective three-stage architecture, consisting of a retriever, a reranker, and a reader to extract the answers. In order to effectively answer the users{'} questions, a number of existing approaches have applied multi-task learning, such that the same model is shared between the reranker and the reader. Such approaches also typically tackle reranking and reading as classification tasks. On the other hand, recent text generation models, such as monoT5 and UnifiedQA, have been shown to respectively yield impressive performances in passage reranking and reading. However, no prior work has combined monoT5 and UnifiedQA to share a single text generation model that directly extracts the answers for the users instead of predicting the start/end positions in a retrieved passage. In this paper, we investigate the use of Multi-Task Learning (MTL) to improve performance on the ORConvQA task by sharing the reranker and reader{'}s learned structure in a generative model. In particular, we propose monoQA, which uses a text generation model with multi-task learning for both the reranker and reader. Our model, which is based on the T5 text generation model, is fine-tuned simultaneously for both reranking (in order to improve the precision of the top retrieved passages) and extracting the answer. Our results on the OR-QuAC and OR-CoQA datasets demonstrate the effectiveness of our proposed model, which significantly outperforms existing strong baselines with improvements ranging from +12.31{\%} to +19.51{\%} in MAP and from +5.70{\%} to +23.34{\%} in F1 on all used test sets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kongyoung-etal-2022-monoqa">
<titleInfo>
<title>monoQA: Multi-Task Learning of Reranking and Answer Extraction for Open-Retrieval Conversational Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sarawoot</namePart>
<namePart type="family">Kongyoung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Craig</namePart>
<namePart type="family">Macdonald</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iadh</namePart>
<namePart type="family">Ounis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To address the Conversational Question Answering (ORConvQA) task, previous work has considered an effective three-stage architecture, consisting of a retriever, a reranker, and a reader to extract the answers. In order to effectively answer the users’ questions, a number of existing approaches have applied multi-task learning, such that the same model is shared between the reranker and the reader. Such approaches also typically tackle reranking and reading as classification tasks. On the other hand, recent text generation models, such as monoT5 and UnifiedQA, have been shown to respectively yield impressive performances in passage reranking and reading. However, no prior work has combined monoT5 and UnifiedQA to share a single text generation model that directly extracts the answers for the users instead of predicting the start/end positions in a retrieved passage. In this paper, we investigate the use of Multi-Task Learning (MTL) to improve performance on the ORConvQA task by sharing the reranker and reader’s learned structure in a generative model. In particular, we propose monoQA, which uses a text generation model with multi-task learning for both the reranker and reader. Our model, which is based on the T5 text generation model, is fine-tuned simultaneously for both reranking (in order to improve the precision of the top retrieved passages) and extracting the answer. Our results on the OR-QuAC and OR-CoQA datasets demonstrate the effectiveness of our proposed model, which significantly outperforms existing strong baselines with improvements ranging from +12.31% to +19.51% in MAP and from +5.70% to +23.34% in F1 on all used test sets.</abstract>
<identifier type="citekey">kongyoung-etal-2022-monoqa</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.485</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.485</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>7207</start>
<end>7218</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T monoQA: Multi-Task Learning of Reranking and Answer Extraction for Open-Retrieval Conversational Question Answering
%A Kongyoung, Sarawoot
%A Macdonald, Craig
%A Ounis, Iadh
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F kongyoung-etal-2022-monoqa
%X To address the Conversational Question Answering (ORConvQA) task, previous work has considered an effective three-stage architecture, consisting of a retriever, a reranker, and a reader to extract the answers. In order to effectively answer the users’ questions, a number of existing approaches have applied multi-task learning, such that the same model is shared between the reranker and the reader. Such approaches also typically tackle reranking and reading as classification tasks. On the other hand, recent text generation models, such as monoT5 and UnifiedQA, have been shown to respectively yield impressive performances in passage reranking and reading. However, no prior work has combined monoT5 and UnifiedQA to share a single text generation model that directly extracts the answers for the users instead of predicting the start/end positions in a retrieved passage. In this paper, we investigate the use of Multi-Task Learning (MTL) to improve performance on the ORConvQA task by sharing the reranker and reader’s learned structure in a generative model. In particular, we propose monoQA, which uses a text generation model with multi-task learning for both the reranker and reader. Our model, which is based on the T5 text generation model, is fine-tuned simultaneously for both reranking (in order to improve the precision of the top retrieved passages) and extracting the answer. Our results on the OR-QuAC and OR-CoQA datasets demonstrate the effectiveness of our proposed model, which significantly outperforms existing strong baselines with improvements ranging from +12.31% to +19.51% in MAP and from +5.70% to +23.34% in F1 on all used test sets.
%R 10.18653/v1/2022.emnlp-main.485
%U https://aclanthology.org/2022.emnlp-main.485
%U https://doi.org/10.18653/v1/2022.emnlp-main.485
%P 7207-7218
Markdown (Informal)
[monoQA: Multi-Task Learning of Reranking and Answer Extraction for Open-Retrieval Conversational Question Answering](https://aclanthology.org/2022.emnlp-main.485) (Kongyoung et al., EMNLP 2022)
ACL