No Word is an Island -- A Transformation Weighting Model for Semantic Composition
원문 초록
Composition models of distributional semantics are used to construct phrase representations from the representations of their words. Composition models are typically situated on two ends of a spectrum. They either have a small number of parameters but compose all phrases in the same way, or they perform word-specific compositions at the cost of a far larger number of parameters. In this paper we propose transformation weighting (TransWeight), a composition model that consistently outperforms existing models on nominal compounds, adjective-noun phrases and adverb-adjective phrases in English, German and Dutch. TransWeight drastically reduces the number of parameters needed compared to the best model in the literature by composing similar words in the same way.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Synthetic Dataset for Evaluating Complex Compositional Knowledge for Natural Language Inference
Semantic Prediction: Which One Should Come First, Recognition or Prediction?
SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data
SentiBERT: A Transferable Transformer-Based Architecture for Compositional Sentiment Semantics
Autoencoding Pixies: Amortised Variational Inference with Graph Convolutions for Functional Distributional Semantics
Semantic Hilbert Space for Text Representation Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.