Zero-shot Relation Classification as Textual Entailment
We consider the task of relation classification, and pose this task as one of textual entailment. We show that this formulation leads to several advantages, including the ability to (i) perform zero-shot relation classification by exploiting relation descriptions, (ii) utilize existing textual entailment models, and (iii) leverage readily available textual entailment datasets, to enhance the performance of relation classification systems. Our experiments show that the proposed approach achieves 20.16{\%} and 61.32{\%} in F1 zero-shot classification performance on two datasets, which further improved to 22.80{\%} and 64.78{\%} respectively with the use of conditional encoding.
Code (0)
등록된 구현이 없습니다.
Tasks
ClassificationGeneral ClassificationKnowledge Base PopulationNatural Language InferenceQuestion AnsweringRelationRelation ClassificationRelation Extractionzero-shot-classificationZero-Shot LearningZero-shot Relation ClassificationSimilar Papers 제목 키워드 기반
Improving Zero-shot Relation Classification via Automatically-acquired Entailment Templates
While fully supervised relation classification (RC) models perform well on large-scale datasets, their performance drops drastically in low-resource settings. As generating annotated examples are expensive, recent zero-s…
Natural Language InferenceRelationRelation ClassificationZero-shot Relation ClassificationLabel Verbalization and Entailment for Effective Zero and Few-Shot Relation Extraction
Relation extraction systems require large amounts of labeled examples which are costly to annotate. In this work we reformulate relation extraction as an entailment task, with simple, hand-made, verbalizations of relatio…
Natural Language InferenceRelationRelation ExtractionLabel Verbalization and Entailment for Effective Zero- and Few-Shot Relation Extraction
Relation extraction systems require large amounts of labeled examples which are costly to annotate. In this work we reformulate relation extraction as an entailment task, with simple, hand-made, verbalizations of relatio…
Natural Language InferenceRelationRelation ExtractionLogic-guided Semantic Representation Learning for Zero-Shot Relation Classification
Relation classification aims to extract semantic relations between entity pairs from the sentences. However, most existing methods can only identify seen relation classes that occurred during training. To recognize unsee…
ClassificationDescriptiveGeneral ClassificationKnowledge Graph Embeddings+6Textual Entailment for Event Argument Extraction: Zero- and Few-Shot with Multi-Source Learning
Recent work has shown that NLP tasks such as Relation Extraction (RE) can be recasted as Textual Entailment tasks using verbalizations, with strong performance in zero-shot and few-shot settings thanks to pre-trained ent…
Event Argument ExtractionNatural Language InferenceRelation ExtractionZero-shot Named Entity Recognition (NER)