@inproceedings{chen-etal-2023-symbolization,
title = "Symbolization, Prompt, and Classification: A Framework for Implicit Speaker Identification in Novels",
author = "Chen, Yue and
He, Tianwei and
Zhou, Hongbin and
Gu, Jia-Chen and
Lu, Heng and
Ling, Zhen-Hua",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.225",
doi = "10.18653/v1/2023.findings-emnlp.225",
pages = "3455--3467",
abstract = "Speaker identification in novel dialogues can be widely applied to various downstream tasks, such as producing multi-speaker audiobooks and converting novels into scripts. However, existing state-of-the-art methods are limited to handling explicit narrative patterns like {``}Tom said, '...''', unable to thoroughly understand long-range contexts and to deal with complex cases. To this end, we propose a framework named SPC, which identifies implicit speakers in novels via symbolization, prompt, and classification. First, SPC symbolizes the mentions of candidate speakers to construct a unified label set. Then, by inserting a prompt we re-formulate speaker identification as a classification task to minimize the gap between the training objectives of speaker identification and the pre-training task. Two auxiliary tasks are also introduced in SPC to enhance long-range context understanding. Experimental results show that SPC outperforms previous methods by a large margin of 4.8{\%} accuracy on the web novel collection, which reduces 47{\%} of speaker identification errors, and also outperforms the emerging ChatGPT. In addition, SPC is more accurate in implicit speaker identification cases that require long-range context semantic understanding.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2023-symbolization">
<titleInfo>
<title>Symbolization, Prompt, and Classification: A Framework for Implicit Speaker Identification in Novels</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianwei</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongbin</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jia-Chen</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhen-Hua</namePart>
<namePart type="family">Ling</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Speaker identification in novel dialogues can be widely applied to various downstream tasks, such as producing multi-speaker audiobooks and converting novels into scripts. However, existing state-of-the-art methods are limited to handling explicit narrative patterns like “Tom said, ’...”’, unable to thoroughly understand long-range contexts and to deal with complex cases. To this end, we propose a framework named SPC, which identifies implicit speakers in novels via symbolization, prompt, and classification. First, SPC symbolizes the mentions of candidate speakers to construct a unified label set. Then, by inserting a prompt we re-formulate speaker identification as a classification task to minimize the gap between the training objectives of speaker identification and the pre-training task. Two auxiliary tasks are also introduced in SPC to enhance long-range context understanding. Experimental results show that SPC outperforms previous methods by a large margin of 4.8% accuracy on the web novel collection, which reduces 47% of speaker identification errors, and also outperforms the emerging ChatGPT. In addition, SPC is more accurate in implicit speaker identification cases that require long-range context semantic understanding.</abstract>
<identifier type="citekey">chen-etal-2023-symbolization</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.225</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.225</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>3455</start>
<end>3467</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Symbolization, Prompt, and Classification: A Framework for Implicit Speaker Identification in Novels
%A Chen, Yue
%A He, Tianwei
%A Zhou, Hongbin
%A Gu, Jia-Chen
%A Lu, Heng
%A Ling, Zhen-Hua
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F chen-etal-2023-symbolization
%X Speaker identification in novel dialogues can be widely applied to various downstream tasks, such as producing multi-speaker audiobooks and converting novels into scripts. However, existing state-of-the-art methods are limited to handling explicit narrative patterns like “Tom said, ’...”’, unable to thoroughly understand long-range contexts and to deal with complex cases. To this end, we propose a framework named SPC, which identifies implicit speakers in novels via symbolization, prompt, and classification. First, SPC symbolizes the mentions of candidate speakers to construct a unified label set. Then, by inserting a prompt we re-formulate speaker identification as a classification task to minimize the gap between the training objectives of speaker identification and the pre-training task. Two auxiliary tasks are also introduced in SPC to enhance long-range context understanding. Experimental results show that SPC outperforms previous methods by a large margin of 4.8% accuracy on the web novel collection, which reduces 47% of speaker identification errors, and also outperforms the emerging ChatGPT. In addition, SPC is more accurate in implicit speaker identification cases that require long-range context semantic understanding.
%R 10.18653/v1/2023.findings-emnlp.225
%U https://aclanthology.org/2023.findings-emnlp.225
%U https://doi.org/10.18653/v1/2023.findings-emnlp.225
%P 3455-3467
Markdown (Informal)
[Symbolization, Prompt, and Classification: A Framework for Implicit Speaker Identification in Novels](https://aclanthology.org/2023.findings-emnlp.225) (Chen et al., Findings 2023)
ACL