arXiv:1808.07383
Dynamic Self-Attention : Computing Attention over Words Dynamically for Sentence Embedding
원문 초록
In this paper, we propose Dynamic Self-Attention (DSA), a new self-attention mechanism for sentence embedding. We design DSA by modifying dynamic routing in capsule network (Sabouretal.,2017) for natural language processing. DSA attends to informative words with a dynamic weight vector. We achieve new state-of-the-art results among sentence encoding methods in Stanford Natural Language Inference (SNLI) dataset with the least number of parameters, while showing comparative results in Stanford Sentiment Treebank (SST) dataset.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering
Parameter-Efficient Transformer Embeddings
Information Leakage of Sentence Embeddings via Generative Embedding Inversion Attacks
IPCGRL: Language-Instructed Reinforcement Learning for Procedural Level Generation
FanChuan: A Multilingual and Graph-Structured Benchmark For Parody Detection and Analysis
Exploring RWKV for Sentence Embeddings: Layer-wise Analysis and Baseline Comparison for Semantic Similarity
토론
이 논문과 연결된 포럼 글이 아직 없습니다.