Adaptive Semantic Compositionality for Sentence Modelling

Adaptive Semantic Compositionality for Sentence Modelling

Pengfei Liu, Xipeng Qiu, Xuanjing Huang

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence
Main track. Pages 4061-4067. https://doi.org/10.24963/ijcai.2017/567

Representing a sentence with a fixed vector has shown its effectiveness in various NLP tasks. Most of the existing methods are based on neural network, which recursively apply different composition functions to a sequence of word vectors thereby obtaining a sentence vector.A hypothesis behind these approaches is that the meaning of any phrase can be composed of the meanings of its constituents.However, many phrases, such as idioms, are apparently non-compositional.To address this problem, we introduce a parameterized compositional switch, which outputs a scalar to adaptively determine whether the meaning of a phrase should be composed of its two constituents.We evaluate our model on five datasets of sentiment classification and demonstrate its efficacy with qualitative and quantitative experimental analysis .
Keywords:
Natural Language Processing: Natural Language Processing
Machine Learning: Deep Learning
Natural Language Processing: Natural Language Semantics