@inproceedings{pawar-etal-2024-generate,
title = "Why Generate When You Can Discriminate? A Novel Technique for Text Classification using Language Models",
author = "Pawar, Sachin and
Ramrakhiyani, Nitin and
Sinha, Anubhav and
Apte, Manoj and
Palshikar, Girish",
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2024",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-eacl.74",
pages = "1099--1114",
abstract = "In this paper, we propose a novel two-step technique for text classification using autoregressive Language Models (LM). In the first step, a set of perplexity and log-likelihood based numeric features are elicited from an LM for a text instance to be classified. Then, in the second step, a classifier based on these features is trained to predict the final label. The classifier used is usually a simple machine learning classifier like Support Vector Machine (SVM) or Logistic Regression (LR) and it is trained using a small set of training examples. We believe, our technique presents a whole new way of exploiting the available training instances, in addition to the existing ways like fine-tuning LMs or in-context learning. Our approach stands out by eliminating the need for parameter updates in LMs, as required in fine-tuning, and does not impose limitations on the number of training examples faced while building prompts for in-context learning. We evaluate our technique across 5 different datasets and compare with multiple competent baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pawar-etal-2024-generate">
<titleInfo>
<title>Why Generate When You Can Discriminate? A Novel Technique for Text Classification using Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sachin</namePart>
<namePart type="family">Pawar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitin</namePart>
<namePart type="family">Ramrakhiyani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anubhav</namePart>
<namePart type="family">Sinha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manoj</namePart>
<namePart type="family">Apte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Girish</namePart>
<namePart type="family">Palshikar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we propose a novel two-step technique for text classification using autoregressive Language Models (LM). In the first step, a set of perplexity and log-likelihood based numeric features are elicited from an LM for a text instance to be classified. Then, in the second step, a classifier based on these features is trained to predict the final label. The classifier used is usually a simple machine learning classifier like Support Vector Machine (SVM) or Logistic Regression (LR) and it is trained using a small set of training examples. We believe, our technique presents a whole new way of exploiting the available training instances, in addition to the existing ways like fine-tuning LMs or in-context learning. Our approach stands out by eliminating the need for parameter updates in LMs, as required in fine-tuning, and does not impose limitations on the number of training examples faced while building prompts for in-context learning. We evaluate our technique across 5 different datasets and compare with multiple competent baselines.</abstract>
<identifier type="citekey">pawar-etal-2024-generate</identifier>
<location>
<url>https://aclanthology.org/2024.findings-eacl.74</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>1099</start>
<end>1114</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Why Generate When You Can Discriminate? A Novel Technique for Text Classification using Language Models
%A Pawar, Sachin
%A Ramrakhiyani, Nitin
%A Sinha, Anubhav
%A Apte, Manoj
%A Palshikar, Girish
%Y Graham, Yvette
%Y Purver, Matthew
%S Findings of the Association for Computational Linguistics: EACL 2024
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F pawar-etal-2024-generate
%X In this paper, we propose a novel two-step technique for text classification using autoregressive Language Models (LM). In the first step, a set of perplexity and log-likelihood based numeric features are elicited from an LM for a text instance to be classified. Then, in the second step, a classifier based on these features is trained to predict the final label. The classifier used is usually a simple machine learning classifier like Support Vector Machine (SVM) or Logistic Regression (LR) and it is trained using a small set of training examples. We believe, our technique presents a whole new way of exploiting the available training instances, in addition to the existing ways like fine-tuning LMs or in-context learning. Our approach stands out by eliminating the need for parameter updates in LMs, as required in fine-tuning, and does not impose limitations on the number of training examples faced while building prompts for in-context learning. We evaluate our technique across 5 different datasets and compare with multiple competent baselines.
%U https://aclanthology.org/2024.findings-eacl.74
%P 1099-1114
Markdown (Informal)
[Why Generate When You Can Discriminate? A Novel Technique for Text Classification using Language Models](https://aclanthology.org/2024.findings-eacl.74) (Pawar et al., Findings 2024)
ACL