@inproceedings{cairang-yuan-2024-ticomr,
title = "{T}i{C}om{R}:基于提示的藏文对话型阅读理解模型({T}i{C}om{R}: A Prompt-based {T}ibetan Conversational Reading Comprehension Model)",
author = "Cairang, Pengmao and
Yuan, Sun",
editor = "Sun, Maosong and
Liang, Jiye and
Han, Xianpei and
Liu, Zhiyuan and
He, Yulan",
booktitle = "Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)",
month = jul,
year = "2024",
address = "Taiyuan, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2024.ccl-1.18/",
pages = "242--253",
language = "zho",
abstract = "{\textquotedblleft}现有的对话型阅读模型在中英文对话型阅读理解任务中表现出色,但由于藏文在语法结构、表达方式等方面同中英文有显著差异,导致这些模型在对藏文对话型阅读理解的对话历史进行建模时存在困难。鉴于此,本文利用当前大模型的优越能力,提出了一种基于提示的对话历史建模方法-TicomR,以解决藏文对话型阅读理解任务中模型性能受限的问题。该方法通过引入基于提示的学习机制,直接在段落文本中添加提示来突显对话历史,而非修改段落标记嵌入,从而在微调过程中实现对对话历史的精确建模,以增强模型对问题的理解能力。实验结果表明,TiComR模型在藏文对话型阅读理解任务上取得了显著的性能提升,并在英文数据集CoQA上也有较好的表现。本文将TicomR开放供研究使用,http://github.com/Tshor/TicomR。{\textquotedblright}"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cairang-yuan-2024-ticomr">
<titleInfo>
<title>TiComR:基于提示的藏文对话型阅读理解模型(TiComR: A Prompt-based Tibetan Conversational Reading Comprehension Model)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pengmao</namePart>
<namePart type="family">Cairang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sun</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">zho</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiye</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianpei</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Taiyuan, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>“现有的对话型阅读模型在中英文对话型阅读理解任务中表现出色,但由于藏文在语法结构、表达方式等方面同中英文有显著差异,导致这些模型在对藏文对话型阅读理解的对话历史进行建模时存在困难。鉴于此,本文利用当前大模型的优越能力,提出了一种基于提示的对话历史建模方法-TicomR,以解决藏文对话型阅读理解任务中模型性能受限的问题。该方法通过引入基于提示的学习机制,直接在段落文本中添加提示来突显对话历史,而非修改段落标记嵌入,从而在微调过程中实现对对话历史的精确建模,以增强模型对问题的理解能力。实验结果表明,TiComR模型在藏文对话型阅读理解任务上取得了显著的性能提升,并在英文数据集CoQA上也有较好的表现。本文将TicomR开放供研究使用,http://github.com/Tshor/TicomR。”</abstract>
<identifier type="citekey">cairang-yuan-2024-ticomr</identifier>
<location>
<url>https://aclanthology.org/2024.ccl-1.18/</url>
</location>
<part>
<date>2024-07</date>
<extent unit="page">
<start>242</start>
<end>253</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TiComR:基于提示的藏文对话型阅读理解模型(TiComR: A Prompt-based Tibetan Conversational Reading Comprehension Model)
%A Cairang, Pengmao
%A Yuan, Sun
%Y Sun, Maosong
%Y Liang, Jiye
%Y Han, Xianpei
%Y Liu, Zhiyuan
%Y He, Yulan
%S Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)
%D 2024
%8 July
%I Chinese Information Processing Society of China
%C Taiyuan, China
%G zho
%F cairang-yuan-2024-ticomr
%X “现有的对话型阅读模型在中英文对话型阅读理解任务中表现出色,但由于藏文在语法结构、表达方式等方面同中英文有显著差异,导致这些模型在对藏文对话型阅读理解的对话历史进行建模时存在困难。鉴于此,本文利用当前大模型的优越能力,提出了一种基于提示的对话历史建模方法-TicomR,以解决藏文对话型阅读理解任务中模型性能受限的问题。该方法通过引入基于提示的学习机制,直接在段落文本中添加提示来突显对话历史,而非修改段落标记嵌入,从而在微调过程中实现对对话历史的精确建模,以增强模型对问题的理解能力。实验结果表明,TiComR模型在藏文对话型阅读理解任务上取得了显著的性能提升,并在英文数据集CoQA上也有较好的表现。本文将TicomR开放供研究使用,http://github.com/Tshor/TicomR。”
%U https://aclanthology.org/2024.ccl-1.18/
%P 242-253
Markdown (Informal)
[TiComR:基于提示的藏文对话型阅读理解模型(TiComR: A Prompt-based Tibetan Conversational Reading Comprehension Model)](https://aclanthology.org/2024.ccl-1.18/) (Cairang & Yuan, CCL 2024)
ACL