Zero-Shot Multi-Label Topic Inference with Sentence Encoders
Sentence encoders have indeed been shown to achieve superior performances for many downstream text-mining tasks and, thus, claimed to be fairly general. Inspired by this, we performed a detailed study on how to leverage these sentence encoders for the "zero-shot topic inference" task, where the topics are defined/provided by the users in real-time. Extensive experiments on seven different datasets demonstrate that Sentence-BERT demonstrates superior generality compared to other encoders, while Universal Sentence Encoder can be preferred when efficiency is a top priority.
Code (0)
등록된 구현이 없습니다.
Tasks
SentenceSimilar Papers 제목 키워드 기반
Text2Topic: Multi-Label Text Classification System for Efficient Topic Detection in User Generated Content with Zero-Shot Capabilities
Multi-label text classification is a critical task in the industry. It helps to extract structured information from large amount of textual data. We propose Text to Topic (Text2Topic), which achieves high multi-label cla…
Decision MakingMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATIONMulti Label Text Classification+3Realistic Zero-Shot Cross-Lingual Transfer in Legal Topic Classification
We consider zero-shot cross-lingual transfer in legal topic classification using the recent MultiEURLEX dataset. Since the original dataset contains parallel documents, which is unrealistic for zero-shot cross-lingual tr…
Cross-Lingual TransferTopic ClassificationTranslationZero-Shot Cross-Lingual TransferRealistic Zero-Shot Cross-Lingual Transfer in Legal Topic Classification
We consider zero-shot cross-lingual transfer in legal topic classification using the recent Multi-EURLEX dataset. Since the original dataset contains parallel documents, which is unrealistic for zero-shot cross-lingual t…
ClassificationCross-Lingual TransferTopic ClassificationTranslation+1Conformal Predictor for Improving Zero-shot Text Classification Efficiency
Pre-trained language models (PLMs) have been shown effective for zero-shot (0shot) text classification. 0shot models based on natural language inference (NLI) and next sentence prediction (NSP) employ cross-encoder archi…
ClassificationNatural Language InferenceSentencetext-classification+3Forget NLI, Use a Dictionary: Zero-Shot Topic Classification for Low-Resource Languages with Application to Luxembourgish
In NLP, zero-shot classification (ZSC) is the task of assigning labels to textual data without any labeled examples for the target classes. A common method for ZSC is to fine-tune a language model on a Natural Language I…
Language ModellingNatural Language InferenceTopic Classificationzero-shot-classification+1