@inproceedings{sekizawa-yanaka-2023-analyzing,
title = "Analyzing Syntactic Generalization Capacity of Pre-trained Language Models on {J}apanese Honorific Conversion",
author = "Sekizawa, Ryo and
Yanaka, Hitomi",
editor = "Palmer, Alexis and
Camacho-collados, Jose",
booktitle = "Proceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.starsem-1.5",
doi = "10.18653/v1/2023.starsem-1.5",
pages = "40--47",
abstract = "Using Japanese honorifics is challenging because it requires not only knowledge of the grammatical rules but also contextual information, such as social relationships. It remains unclear whether pre-trained large language models (LLMs) can flexibly handle Japanese honorifics like humans. To analyze this, we introduce an honorific conversion task that considers social relationships among people mentioned in a conversation. We construct a Japanese honorifics dataset from problem templates of various sentence structures to investigate the syntactic generalization capacity of GPT-3, one of the leading LLMs, on this task under two settings: fine-tuning and prompt learning. Our results showed that the fine-tuned GPT-3 performed better in a context-aware honorific conversion task than the prompt-based one. The fine-tuned model demonstrated overall syntactic generalizability towards compound honorific sentences, except when tested with the data involving direct speech.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sekizawa-yanaka-2023-analyzing">
<titleInfo>
<title>Analyzing Syntactic Generalization Capacity of Pre-trained Language Models on Japanese Honorific Conversion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ryo</namePart>
<namePart type="family">Sekizawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitomi</namePart>
<namePart type="family">Yanaka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jose</namePart>
<namePart type="family">Camacho-collados</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Using Japanese honorifics is challenging because it requires not only knowledge of the grammatical rules but also contextual information, such as social relationships. It remains unclear whether pre-trained large language models (LLMs) can flexibly handle Japanese honorifics like humans. To analyze this, we introduce an honorific conversion task that considers social relationships among people mentioned in a conversation. We construct a Japanese honorifics dataset from problem templates of various sentence structures to investigate the syntactic generalization capacity of GPT-3, one of the leading LLMs, on this task under two settings: fine-tuning and prompt learning. Our results showed that the fine-tuned GPT-3 performed better in a context-aware honorific conversion task than the prompt-based one. The fine-tuned model demonstrated overall syntactic generalizability towards compound honorific sentences, except when tested with the data involving direct speech.</abstract>
<identifier type="citekey">sekizawa-yanaka-2023-analyzing</identifier>
<identifier type="doi">10.18653/v1/2023.starsem-1.5</identifier>
<location>
<url>https://aclanthology.org/2023.starsem-1.5</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>40</start>
<end>47</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Analyzing Syntactic Generalization Capacity of Pre-trained Language Models on Japanese Honorific Conversion
%A Sekizawa, Ryo
%A Yanaka, Hitomi
%Y Palmer, Alexis
%Y Camacho-collados, Jose
%S Proceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F sekizawa-yanaka-2023-analyzing
%X Using Japanese honorifics is challenging because it requires not only knowledge of the grammatical rules but also contextual information, such as social relationships. It remains unclear whether pre-trained large language models (LLMs) can flexibly handle Japanese honorifics like humans. To analyze this, we introduce an honorific conversion task that considers social relationships among people mentioned in a conversation. We construct a Japanese honorifics dataset from problem templates of various sentence structures to investigate the syntactic generalization capacity of GPT-3, one of the leading LLMs, on this task under two settings: fine-tuning and prompt learning. Our results showed that the fine-tuned GPT-3 performed better in a context-aware honorific conversion task than the prompt-based one. The fine-tuned model demonstrated overall syntactic generalizability towards compound honorific sentences, except when tested with the data involving direct speech.
%R 10.18653/v1/2023.starsem-1.5
%U https://aclanthology.org/2023.starsem-1.5
%U https://doi.org/10.18653/v1/2023.starsem-1.5
%P 40-47
Markdown (Informal)
[Analyzing Syntactic Generalization Capacity of Pre-trained Language Models on Japanese Honorific Conversion](https://aclanthology.org/2023.starsem-1.5) (Sekizawa & Yanaka, *SEM 2023)
ACL