Papers Zero-Shot Text Classification
“Zero-Shot Text Classification” 태그가 달린 논문 48편 · 필터 해제
Beyond the Next Token: Towards Prompt-Robust Zero-Shot Classification via Efficient Multi-Token Prediction
Zero-shot text classification typically relies on prompt engineering, but the inherent prompt brittleness of large language models undermines its reliability. Minor changes in prompt can cause significant discrepancies i…
AttributeLanguage ModelingLanguage ModellingPrompt Engineering+5Analysis of Socially Unacceptable Discourse with Zero-shot Learning
Socially Unacceptable Discourse (SUD) analysis is crucial for maintaining online positive environments. We investigate the effectiveness of Entailment-based zero-shot text classification (unsupervised method) for SUD det…
text-classificationText ClassificationZero-Shot LearningZero-Shot Text ClassificationRetrieval Augmented Zero-Shot Text Classification
Zero-shot text learning enables text classifiers to handle unseen classes efficiently, alleviating the need for task-specific training data. A simple approach often relies on comparing embeddings of query (text) to those…
ClassificationRetrievaltext-classificationText Classification+2Liberating Seen Classes: Boosting Few-Shot and Zero-Shot Text Classification via Anchor Generation and Classification Reframing
Few-shot and zero-shot text classification aim to recognize samples from novel classes with limited labeled samples or no labeled samples at all. While prevailing methods have shown promising performance via transferring…
Binary ClassificationClassificationLanguage ModellingMulti-class Classification+3Small Language Models are Good Too: An Empirical Study of Zero-Shot Classification
This study is part of the debate on the efficiency of large versus small language models for text classification by prompting.We assess the performance of small language models in zero-shot text classification, challengi…
Classificationtext-classificationText Classificationzero-shot-classification+2Breaking Free Transformer Models: Task-specific Context Attribution Promises Improved Generalizability Without Fine-tuning Pre-trained LLMs
Fine-tuning large pre-trained language models (LLMs) on particular datasets is a commonly employed strategy in Natural Language Processing (NLP) classification tasks. However, this approach usually results in a loss of m…
Sentiment AnalysisSentiment ClassificationText ClassificationWord Embeddings+1A Novel Prompt-tuning Method: Incorporating Scenario-specific Concepts into a Verbalizer
The verbalizer, which serves to map label words to class labels, is an essential component of prompt-tuning. In this paper, we present a novel approach to constructing verbalizers. While existing methods for verbalizer c…
text-classificationText ClassificationZero-Shot Text ClassificationAn Evaluation Framework for Mapping News Headlines to Event Classes in a Knowledge Graph
Mapping ongoing news headlines to event-related classes in a rich knowledge base can be an important component in a knowledge-based event analysis and forecasting solution. In this paper, we present a methodology for cre…
Entity LinkingNatural Language Inferencetext-classificationText Classification+1Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label Descriptions
Language model (LM) prompting--a popular paradigm for solving NLP tasks--has been shown to be susceptible to miscalibration and brittleness to slight prompt variations, caused by its discriminative prompting approach, i.…
ClassificationLanguage ModelingLanguage Modellingtext-classification+4This is not a Dataset: A Large Negation Benchmark to Challenge Large Language Models
Although large language models (LLMs) have apparently acquired a certain level of grammatical knowledge and the ability to make generalizations, they fail to interpret negation, a crucial step in Natural Language Process…
DescriptiveNegationText ClassificationZero-Shot Text ClassificationWC-SBERT: Zero-Shot Text Classification via SBERT with Self-Training for Wikipedia Categories
Our research focuses on solving the zero-shot text classification problem in NLP, with a particular emphasis on innovative self-training strategies. To achieve this objective, we propose a novel self-training strategy th…
text-classificationText ClassificationZero-Shot Text ClassificationWisdom of Instruction-Tuned Language Model Crowds. Exploring Model Label Variation
Large Language Models (LLMs) exhibit remarkable text classification capabilities, excelling in zero- and few-shot learning (ZSL and FSL) scenarios. However, since they are trained on different datasets, performance varie…
Few-Shot LearningHate Speech DetectionLanguage ModelingLanguage Modelling+5Analysis of the Fed's communication by using textual entailment model of Zero-Shot classification
In this study, we analyze documents published by central banks using text mining techniques and propose a method to evaluate the policy tone of central banks. Since the monetary policies of major central banks have a bro…
Natural Language InferenceSentiment Analysistext-classificationText Classification+3Label Agnostic Pre-training for Zero-shot Text Classification
Conventional approaches to text classification typically assume the existence of a fixed set of predefined labels to which a given text can be classified. However, in real-world applications, there exists an infinite lab…
Classificationtext-classificationText ClassificationZero-shot Generalization+1PESCO: Prompt-enhanced Self Contrastive Learning for Zero-shot Text Classification
We present PESCO, a novel contrastive learning framework that substantially improves the performance of zero-shot text classification. We formulate text classification as a neural text matching problem where each documen…
ClassificationContrastive Learningtext-classificationText Classification+2Zero-Shot Text Classification via Self-Supervised Tuning
Existing solutions to zero-shot text classification either conduct prompting with pre-trained language models, which is sensitive to the choices of templates, or rely on large-scale annotated data of relevant tasks for m…
ClassificationSelf-Supervised LearningSentenceSentiment Analysis+4ReGen: Zero-Shot Text Classification via Training Data Generation with Progressive Dense Retrieval
With the development of large language models (LLMs), zero-shot learning has attracted much attention for various NLP tasks. Different from prior works that generate training data with billion-scale natural language gene…
DescriptiveRetrievaltext-classificationText Classification+4The Benefits of Label-Description Training for Zero-Shot Text Classification
Pretrained language models have improved zero-shot text classification by allowing the transfer of semantic knowledge from the training data in order to classify among specific label sets in downstream tasks. We propose …
Classificationdomain classificationtext-classificationText Classification+3Generation-driven Contrastive Self-training for Zero-shot Text Classification with Instruction-following LLM
The remarkable performance of large language models (LLMs) in zero-shot language understanding has garnered significant attention. However, employing LLMs for large-scale inference or domain-specific fine-tuning requires…
Instruction FollowingLanguage ModellingSentencetext-classification+3ChatGPT: Beginning of an End of Manual Linguistic Data Annotation? Use Case of Automatic Genre Identification
ChatGPT has shown strong capabilities in natural language generation tasks, which naturally leads researchers to explore where its abilities end. In this paper, we examine whether ChatGPT can be used for zero-shot text c…
Language ModelingLanguage Modellingtext-classificationText Classification+2