@inproceedings{ishii-etal-2023-contrastive,
title = "Contrastive Learning for Inference in Dialogue",
author = "Ishii, Etsuko and
Xu, Yan and
Wilie, Bryan and
Ji, Ziwei and
Lovenia, Holy and
Chung, Willy and
Fung, Pascale",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.631/",
doi = "10.18653/v1/2023.emnlp-main.631",
pages = "10202--10221",
abstract = "Inference, especially those derived from inductive processes, is a crucial component in our conversation to complement the information implicitly or explicitly conveyed by a speaker. While recent large language models show remarkable advances in inference tasks, their performance in inductive reasoning, where not all information is present in the context, is far behind deductive reasoning. In this paper, we analyze the behavior of the models based on the task difficulty defined by the semantic information gap {--} which distinguishes inductive and deductive reasoning. Our analysis reveals that the information gap between dialogue contexts and desired inferences renders the inductive inference process more challenging. To mitigate this information gap, we investigate a contrastive learning approach by feeding negative samples. Our experiments suggest negative samples help models understand what is wrong and improve their inference generations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ishii-etal-2023-contrastive">
<titleInfo>
<title>Contrastive Learning for Inference in Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Etsuko</namePart>
<namePart type="family">Ishii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bryan</namePart>
<namePart type="family">Wilie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziwei</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Holy</namePart>
<namePart type="family">Lovenia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Willy</namePart>
<namePart type="family">Chung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pascale</namePart>
<namePart type="family">Fung</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>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</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>Inference, especially those derived from inductive processes, is a crucial component in our conversation to complement the information implicitly or explicitly conveyed by a speaker. While recent large language models show remarkable advances in inference tasks, their performance in inductive reasoning, where not all information is present in the context, is far behind deductive reasoning. In this paper, we analyze the behavior of the models based on the task difficulty defined by the semantic information gap – which distinguishes inductive and deductive reasoning. Our analysis reveals that the information gap between dialogue contexts and desired inferences renders the inductive inference process more challenging. To mitigate this information gap, we investigate a contrastive learning approach by feeding negative samples. Our experiments suggest negative samples help models understand what is wrong and improve their inference generations.</abstract>
<identifier type="citekey">ishii-etal-2023-contrastive</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.631</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.631/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>10202</start>
<end>10221</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Contrastive Learning for Inference in Dialogue
%A Ishii, Etsuko
%A Xu, Yan
%A Wilie, Bryan
%A Ji, Ziwei
%A Lovenia, Holy
%A Chung, Willy
%A Fung, Pascale
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F ishii-etal-2023-contrastive
%X Inference, especially those derived from inductive processes, is a crucial component in our conversation to complement the information implicitly or explicitly conveyed by a speaker. While recent large language models show remarkable advances in inference tasks, their performance in inductive reasoning, where not all information is present in the context, is far behind deductive reasoning. In this paper, we analyze the behavior of the models based on the task difficulty defined by the semantic information gap – which distinguishes inductive and deductive reasoning. Our analysis reveals that the information gap between dialogue contexts and desired inferences renders the inductive inference process more challenging. To mitigate this information gap, we investigate a contrastive learning approach by feeding negative samples. Our experiments suggest negative samples help models understand what is wrong and improve their inference generations.
%R 10.18653/v1/2023.emnlp-main.631
%U https://aclanthology.org/2023.emnlp-main.631/
%U https://doi.org/10.18653/v1/2023.emnlp-main.631
%P 10202-10221
Markdown (Informal)
[Contrastive Learning for Inference in Dialogue](https://aclanthology.org/2023.emnlp-main.631/) (Ishii et al., EMNLP 2023)
ACL
- Etsuko Ishii, Yan Xu, Bryan Wilie, Ziwei Ji, Holy Lovenia, Willy Chung, and Pascale Fung. 2023. Contrastive Learning for Inference in Dialogue. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 10202–10221, Singapore. Association for Computational Linguistics.