@inproceedings{yuan-etal-2022-mcqueen,
title = "{M}c{Q}ueen: a Benchmark for Multimodal Conversational Query Rewrite",
author = "Yuan, Yifei and
Shi, Chen and
Wang, Runze and
Chen, Liyi and
Jiang, Feijun and
You, Yuan and
Lam, Wai",
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.320",
doi = "10.18653/v1/2022.emnlp-main.320",
pages = "4834--4844",
abstract = "The task of query rewrite aims to convert an in-context query to its fully-specified version where ellipsis and coreference are completed and referred-back according to the history context. Although much progress has been made, less efforts have been paid to real scenario conversations that involve drawing information from more than one modalities. In this paper, we propose the task of multimodal conversational query rewrite (McQR), which performs query rewrite under the multimodal visual conversation setting. We collect a large-scale dataset named McQueen based on manual annotation, which contains 15k visual conversations and over 80k queries where each one is associated with a fully-specified rewrite version. In addition, for entities appearing in the rewrite, we provide the corresponding image box annotation. We then use the McQueen dataset to benchmark a state-of-the-art method for effectively tackling the McQR task, which is based on a multimodal pre-trained model with pointer generator. Extensive experiments are performed to demonstrate the effectiveness of our model on this task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yuan-etal-2022-mcqueen">
<titleInfo>
<title>McQueen: a Benchmark for Multimodal Conversational Query Rewrite</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yifei</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Runze</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liyi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feijun</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuan</namePart>
<namePart type="family">You</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wai</namePart>
<namePart type="family">Lam</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>The task of query rewrite aims to convert an in-context query to its fully-specified version where ellipsis and coreference are completed and referred-back according to the history context. Although much progress has been made, less efforts have been paid to real scenario conversations that involve drawing information from more than one modalities. In this paper, we propose the task of multimodal conversational query rewrite (McQR), which performs query rewrite under the multimodal visual conversation setting. We collect a large-scale dataset named McQueen based on manual annotation, which contains 15k visual conversations and over 80k queries where each one is associated with a fully-specified rewrite version. In addition, for entities appearing in the rewrite, we provide the corresponding image box annotation. We then use the McQueen dataset to benchmark a state-of-the-art method for effectively tackling the McQR task, which is based on a multimodal pre-trained model with pointer generator. Extensive experiments are performed to demonstrate the effectiveness of our model on this task.</abstract>
<identifier type="citekey">yuan-etal-2022-mcqueen</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.320</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.320</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>4834</start>
<end>4844</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T McQueen: a Benchmark for Multimodal Conversational Query Rewrite
%A Yuan, Yifei
%A Shi, Chen
%A Wang, Runze
%A Chen, Liyi
%A Jiang, Feijun
%A You, Yuan
%A Lam, Wai
%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 yuan-etal-2022-mcqueen
%X The task of query rewrite aims to convert an in-context query to its fully-specified version where ellipsis and coreference are completed and referred-back according to the history context. Although much progress has been made, less efforts have been paid to real scenario conversations that involve drawing information from more than one modalities. In this paper, we propose the task of multimodal conversational query rewrite (McQR), which performs query rewrite under the multimodal visual conversation setting. We collect a large-scale dataset named McQueen based on manual annotation, which contains 15k visual conversations and over 80k queries where each one is associated with a fully-specified rewrite version. In addition, for entities appearing in the rewrite, we provide the corresponding image box annotation. We then use the McQueen dataset to benchmark a state-of-the-art method for effectively tackling the McQR task, which is based on a multimodal pre-trained model with pointer generator. Extensive experiments are performed to demonstrate the effectiveness of our model on this task.
%R 10.18653/v1/2022.emnlp-main.320
%U https://aclanthology.org/2022.emnlp-main.320
%U https://doi.org/10.18653/v1/2022.emnlp-main.320
%P 4834-4844
Markdown (Informal)
[McQueen: a Benchmark for Multimodal Conversational Query Rewrite](https://aclanthology.org/2022.emnlp-main.320) (Yuan et al., EMNLP 2022)
ACL
- Yifei Yuan, Chen Shi, Runze Wang, Liyi Chen, Feijun Jiang, Yuan You, and Wai Lam. 2022. McQueen: a Benchmark for Multimodal Conversational Query Rewrite. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 4834–4844, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.