paper-with-me

Papers

Bridging Text and Knowledge with Multi-Prototype Embedding for Few-Shot Relational Triple Extraction

2020-10-30 · COLING 2020 8 · Haiyang Yu, Ningyu Zhang, Shumin Deng, Hongbin Ye, Wei zhang, Huajun Chen

Current supervised relational triple extraction approaches require huge amounts of labeled data and thus suffer from poor performance in few-shot settings. However, people can grasp new knowledge by learning a few instances. To this end, we take the first step to study the few-shot relational triple extraction, which has not been well understood. Unlike previous single-task few-shot problems, relational triple extraction is more challenging as the entities and relations have implicit correlations. In this paper, We propose a novel multi-prototype embedding network model to jointly extract the composition of relational triples, namely, entity pairs and corresponding relations. To be specific, we design a hybrid prototypical learning mechanism that bridges text and knowledge concerning both entities and relations. Thus, implicit correlations between entities and relations are injected. Additionally, we propose a prototype-aware regularization to learn more representative prototypes. Experimental results demonstrate that the proposed method can improve the performance of the few-shot triple extraction.

📄 PDF Abstract BibTeX arXiv:2010.16059

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Bridge Text and Knowledge by Learning Multi-Prototype Entity Mention Embedding

2017-07-01 · ACL 2017 7 · Yixin Cao, Lifu Huang, Heng Ji, Xu Chen 외

Integrating text and knowledge into a unified semantic space has attracted significant research interests recently. However, the ambiguity in the common space remains a challenge, namely that the same mention phrase usua…

Entity LinkingKnowledge Graph CompletionLanguage ModelingLanguage Modelling+2

Diffusion-Link: Diffusion Probabilistic Model for Bridging the Audio-Text Modality Gap

2025-10-13 · KiHyun Nam, Jongmin Choi, Hyeongkeun Lee, Jungwoo Heo 외 arxiv

Contrastive audio-language pretraining yields powerful joint representations, yet a persistent audio-text modality gap limits the benefits of coupling multimodal encoders with large language models (LLMs). We present Dif…

Audio captioning

When is a bishop not like a rook? When it's like a rabbi! Multi-prototype BERT embeddings for estimating semantic relationships

2020-11-01 · CONLL 2020 · Gabriella Chronis, Katrin Erk

This paper investigates contextual language models, which produce token representations, as a resource for lexical semantics at the word or type level. We construct multi-prototype word embeddings from bert-base-uncased …

Semantic SimilaritySemantic Textual SimilarityVocal Bursts Type PredictionWord Embeddings

Closing the Modality Gap in Zero-Shot HAR: Contrastive Training and Separability-Optimized Prototypes on IMU Data

2026-06-09 · Anik Ghosh arxiv

Zero-shot learning (ZSL) for inertial measurement unit (IMU)-based human activity recognition (HAR) faces a central challenge: bridging the gap between sensor embeddings and semantic class representations. We systematica…

Human Activity RecognitionZero-Shot Learning

Just Shift It: Test-Time Prototype Shifting for Zero-Shot Generalization with Vision-Language Models

2024-03-19 · Elaine Sui, Xiaohan Wang, Serena Yeung-Levy

Advancements in vision-language models (VLMs) have propelled the field of computer vision, particularly in the zero-shot learning setting. Despite their promise, the effectiveness of these models often diminishes due to …

image-classificationImage ClassificationPrompt EngineeringVisual Reasoning+2