A Cross-Sentence Latent Variable Model for Semi-Supervised Text Sequence Matching
원문 초록
We present a latent variable model for predicting the relationship between a pair of text sequences. Unlike previous auto-encoding--based approaches that consider each sequence separately, our proposed framework utilizes both sequences within a single model by generating a sequence that has a given relationship with a source sequence. We further extend the cross-sentence generating framework to facilitate semi-supervised training. We also define novel semantic constraints that lead the decoder network to generate semantically plausible and diverse sequences. We demonstrate the effectiveness of the proposed model from quantitative and qualitative experiments, while achieving state-of-the-art results on semi-supervised natural language inference and paraphrase identification.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Sentinel: Decoding Context Utilization via Attention Probing for Efficient LLM Context Compression
A MISMATCHED Benchmark for Scientific Natural Language Inference
Thunder-NUBench: A Benchmark for LLMs' Sentence-Level Negation Understanding
EEG2TEXT-CN: An Exploratory Study of Open-Vocabulary Chinese Text-EEG Alignment via Large Language Model and Contrastive Learning on ChineseEEG
Representation Learning through Multimodal Attention and Time-Sync Comments for Affective Video Content Analysis
DIBERT: Dependency Injected Bidirectional Encoder Representations from Transformers
토론
이 논문과 연결된 포럼 글이 아직 없습니다.