@inproceedings{sui-etal-2021-large,
title = "A Large-Scale {C}hinese Multimodal {NER} Dataset with Speech Clues",
author = "Sui, Dianbo and
Tian, Zhengkun and
Chen, Yubo and
Liu, Kang and
Zhao, Jun",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.218",
doi = "10.18653/v1/2021.acl-long.218",
pages = "2807--2818",
abstract = "In this paper, we aim to explore an uncharted territory, which is Chinese multimodal named entity recognition (NER) with both textual and acoustic contents. To achieve this, we construct a large-scale human-annotated Chinese multimodal NER dataset, named CNERTA. Our corpus totally contains 42,987 annotated sentences accompanying by 71 hours of speech data. Based on this dataset, we propose a family of strong and representative baseline models, which can leverage textual features or multimodal features. Upon these baselines, to capture the natural monotonic alignment between the textual modality and the acoustic modality, we further propose a simple multimodal multitask model by introducing a speech-to-text alignment auxiliary task. Through extensive experiments, we observe that: (1) Progressive performance boosts as we move from unimodal to multimodal, verifying the necessity of integrating speech clues into Chinese NER. (2) Our proposed model yields state-of-the-art (SoTA) results on CNERTA, demonstrating its effectiveness. For further research, the annotated dataset is publicly available at \url{http://github.com/DianboWork/CNERTA}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sui-etal-2021-large">
<titleInfo>
<title>A Large-Scale Chinese Multimodal NER Dataset with Speech Clues</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dianbo</namePart>
<namePart type="family">Sui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengkun</namePart>
<namePart type="family">Tian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yubo</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we aim to explore an uncharted territory, which is Chinese multimodal named entity recognition (NER) with both textual and acoustic contents. To achieve this, we construct a large-scale human-annotated Chinese multimodal NER dataset, named CNERTA. Our corpus totally contains 42,987 annotated sentences accompanying by 71 hours of speech data. Based on this dataset, we propose a family of strong and representative baseline models, which can leverage textual features or multimodal features. Upon these baselines, to capture the natural monotonic alignment between the textual modality and the acoustic modality, we further propose a simple multimodal multitask model by introducing a speech-to-text alignment auxiliary task. Through extensive experiments, we observe that: (1) Progressive performance boosts as we move from unimodal to multimodal, verifying the necessity of integrating speech clues into Chinese NER. (2) Our proposed model yields state-of-the-art (SoTA) results on CNERTA, demonstrating its effectiveness. For further research, the annotated dataset is publicly available at http://github.com/DianboWork/CNERTA.</abstract>
<identifier type="citekey">sui-etal-2021-large</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.218</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.218</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>2807</start>
<end>2818</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Large-Scale Chinese Multimodal NER Dataset with Speech Clues
%A Sui, Dianbo
%A Tian, Zhengkun
%A Chen, Yubo
%A Liu, Kang
%A Zhao, Jun
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F sui-etal-2021-large
%X In this paper, we aim to explore an uncharted territory, which is Chinese multimodal named entity recognition (NER) with both textual and acoustic contents. To achieve this, we construct a large-scale human-annotated Chinese multimodal NER dataset, named CNERTA. Our corpus totally contains 42,987 annotated sentences accompanying by 71 hours of speech data. Based on this dataset, we propose a family of strong and representative baseline models, which can leverage textual features or multimodal features. Upon these baselines, to capture the natural monotonic alignment between the textual modality and the acoustic modality, we further propose a simple multimodal multitask model by introducing a speech-to-text alignment auxiliary task. Through extensive experiments, we observe that: (1) Progressive performance boosts as we move from unimodal to multimodal, verifying the necessity of integrating speech clues into Chinese NER. (2) Our proposed model yields state-of-the-art (SoTA) results on CNERTA, demonstrating its effectiveness. For further research, the annotated dataset is publicly available at http://github.com/DianboWork/CNERTA.
%R 10.18653/v1/2021.acl-long.218
%U https://aclanthology.org/2021.acl-long.218
%U https://doi.org/10.18653/v1/2021.acl-long.218
%P 2807-2818
Markdown (Informal)
[A Large-Scale Chinese Multimodal NER Dataset with Speech Clues](https://aclanthology.org/2021.acl-long.218) (Sui et al., ACL-IJCNLP 2021)
ACL
- Dianbo Sui, Zhengkun Tian, Yubo Chen, Kang Liu, and Jun Zhao. 2021. A Large-Scale Chinese Multimodal NER Dataset with Speech Clues. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 2807–2818, Online. Association for Computational Linguistics.