@inproceedings{wu-etal-2022-towards-relation,
title = "Towards relation extraction from speech",
author = "Wu, Tongtong and
Wang, Guitao and
Zhao, Jinming and
Liu, Zhaoran and
Qi, Guilin and
Li, Yuan-Fang and
Haffari, Gholamreza",
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.738",
doi = "10.18653/v1/2022.emnlp-main.738",
pages = "10751--10762",
abstract = "Relation extraction typically aims to extract semantic relationships between entities from the unstructured text. One of the most essential data sources for relation extraction is the spoken language, such as interviews and dialogues. However, the error propagation introduced in automatic speech recognition (ASR) has been ignored in relation extraction, and the end-to-end speech-based relation extraction method has been rarely explored. In this paper, we propose a new listening information extraction task, i.e., speech relation extraction. We construct the training dataset for speech relation extraction via text-to-speech systems, and we construct the testing dataset via crowd-sourcing with native English speakers. We explore speech relation extraction via two approaches: the pipeline approach conducting text-based extraction with a pretrained ASR module, and the end2end approach via a new proposed encoder-decoder model, or what we called SpeechRE.We conduct comprehensive experiments to distinguish the challenges in speech relation extraction, which may shed light on future explorations. We share the code and data on \url{https://github.com/wutong8023/SpeechRE}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2022-towards-relation">
<titleInfo>
<title>Towards relation extraction from speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tongtong</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guitao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinming</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhaoran</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guilin</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuan-Fang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</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>Relation extraction typically aims to extract semantic relationships between entities from the unstructured text. One of the most essential data sources for relation extraction is the spoken language, such as interviews and dialogues. However, the error propagation introduced in automatic speech recognition (ASR) has been ignored in relation extraction, and the end-to-end speech-based relation extraction method has been rarely explored. In this paper, we propose a new listening information extraction task, i.e., speech relation extraction. We construct the training dataset for speech relation extraction via text-to-speech systems, and we construct the testing dataset via crowd-sourcing with native English speakers. We explore speech relation extraction via two approaches: the pipeline approach conducting text-based extraction with a pretrained ASR module, and the end2end approach via a new proposed encoder-decoder model, or what we called SpeechRE.We conduct comprehensive experiments to distinguish the challenges in speech relation extraction, which may shed light on future explorations. We share the code and data on https://github.com/wutong8023/SpeechRE.</abstract>
<identifier type="citekey">wu-etal-2022-towards-relation</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.738</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.738</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>10751</start>
<end>10762</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards relation extraction from speech
%A Wu, Tongtong
%A Wang, Guitao
%A Zhao, Jinming
%A Liu, Zhaoran
%A Qi, Guilin
%A Li, Yuan-Fang
%A Haffari, Gholamreza
%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 wu-etal-2022-towards-relation
%X Relation extraction typically aims to extract semantic relationships between entities from the unstructured text. One of the most essential data sources for relation extraction is the spoken language, such as interviews and dialogues. However, the error propagation introduced in automatic speech recognition (ASR) has been ignored in relation extraction, and the end-to-end speech-based relation extraction method has been rarely explored. In this paper, we propose a new listening information extraction task, i.e., speech relation extraction. We construct the training dataset for speech relation extraction via text-to-speech systems, and we construct the testing dataset via crowd-sourcing with native English speakers. We explore speech relation extraction via two approaches: the pipeline approach conducting text-based extraction with a pretrained ASR module, and the end2end approach via a new proposed encoder-decoder model, or what we called SpeechRE.We conduct comprehensive experiments to distinguish the challenges in speech relation extraction, which may shed light on future explorations. We share the code and data on https://github.com/wutong8023/SpeechRE.
%R 10.18653/v1/2022.emnlp-main.738
%U https://aclanthology.org/2022.emnlp-main.738
%U https://doi.org/10.18653/v1/2022.emnlp-main.738
%P 10751-10762
Markdown (Informal)
[Towards relation extraction from speech](https://aclanthology.org/2022.emnlp-main.738) (Wu et al., EMNLP 2022)
ACL
- Tongtong Wu, Guitao Wang, Jinming Zhao, Zhaoran Liu, Guilin Qi, Yuan-Fang Li, and Gholamreza Haffari. 2022. Towards relation extraction from speech. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 10751–10762, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.