@inproceedings{bhardwaj-etal-2023-knn,
title = "k{NN}-{CM}: A Non-parametric Inference-Phase Adaptation of Parametric Text Classifiers",
author = "Bhardwaj, Rishabh and
Li, Yingting and
Majumder, Navonil and
Cheng, Bo and
Poria, Soujanya",
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.903/",
doi = "10.18653/v1/2023.findings-emnlp.903",
pages = "13546--13557",
abstract = "Semi-parametric models exhibit the properties of both parametric and non-parametric modeling and have been shown to be effective in the next-word prediction language modeling task. However, there is a lack of studies on the text-discriminating properties of such models. We propose an inference-phase approach{---}\textit{k}-Nearest Neighbor Classification Model (\textit{k}NN-CM){---}that enhances the capacity of a pre-trained parametric text classifier by incorporating a simple neighborhood search through the representation space of (memorized) training samples. The final class prediction of \textit{k}NN-CM is based on the convex combination of probabilities obtained from \textit{k}NN search and prediction of the classifier. Our experiments show consistent performance improvements on eight SuperGLUE tasks, three adversarial natural language inference (ANLI) datasets, 11 question-answering (QA) datasets, and two sentiment classification datasets."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhardwaj-etal-2023-knn">
<titleInfo>
<title>kNN-CM: A Non-parametric Inference-Phase Adaptation of Parametric Text Classifiers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rishabh</namePart>
<namePart type="family">Bhardwaj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingting</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Navonil</namePart>
<namePart type="family">Majumder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soujanya</namePart>
<namePart type="family">Poria</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>Semi-parametric models exhibit the properties of both parametric and non-parametric modeling and have been shown to be effective in the next-word prediction language modeling task. However, there is a lack of studies on the text-discriminating properties of such models. We propose an inference-phase approach—k-Nearest Neighbor Classification Model (kNN-CM)—that enhances the capacity of a pre-trained parametric text classifier by incorporating a simple neighborhood search through the representation space of (memorized) training samples. The final class prediction of kNN-CM is based on the convex combination of probabilities obtained from kNN search and prediction of the classifier. Our experiments show consistent performance improvements on eight SuperGLUE tasks, three adversarial natural language inference (ANLI) datasets, 11 question-answering (QA) datasets, and two sentiment classification datasets.</abstract>
<identifier type="citekey">bhardwaj-etal-2023-knn</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.903</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.903/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>13546</start>
<end>13557</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T kNN-CM: A Non-parametric Inference-Phase Adaptation of Parametric Text Classifiers
%A Bhardwaj, Rishabh
%A Li, Yingting
%A Majumder, Navonil
%A Cheng, Bo
%A Poria, Soujanya
%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 bhardwaj-etal-2023-knn
%X Semi-parametric models exhibit the properties of both parametric and non-parametric modeling and have been shown to be effective in the next-word prediction language modeling task. However, there is a lack of studies on the text-discriminating properties of such models. We propose an inference-phase approach—k-Nearest Neighbor Classification Model (kNN-CM)—that enhances the capacity of a pre-trained parametric text classifier by incorporating a simple neighborhood search through the representation space of (memorized) training samples. The final class prediction of kNN-CM is based on the convex combination of probabilities obtained from kNN search and prediction of the classifier. Our experiments show consistent performance improvements on eight SuperGLUE tasks, three adversarial natural language inference (ANLI) datasets, 11 question-answering (QA) datasets, and two sentiment classification datasets.
%R 10.18653/v1/2023.findings-emnlp.903
%U https://aclanthology.org/2023.findings-emnlp.903/
%U https://doi.org/10.18653/v1/2023.findings-emnlp.903
%P 13546-13557
Markdown (Informal)
[kNN-CM: A Non-parametric Inference-Phase Adaptation of Parametric Text Classifiers](https://aclanthology.org/2023.findings-emnlp.903/) (Bhardwaj et al., Findings 2023)
ACL