Abstract
The meaning of a multi-word phrase not only depends on the meaning of its constituent words, but also the rules of composing them to give the so-called compositional semantic. However, many deep learning models for learning compositional semantics target specific NLP tasks such as sentiment classification. Consequently, the word embeddings encode the lexical semantics, the weights of the networks are optimised for the classification task. Such models have no mechanisms to explicitly encode the compositional rules, and hence they are insufficient in capturing the semantics of phrases. We present a novel recurrent computational mechanism that specifically learns the compositionality by encoding the compositional rule of each word into a matrix. The network uses a recurrent architecture to capture the order of words for phrases with various lengths without requiring extra preprocessing such as part-of-speech tagging. The model is thoroughly evaluated on both supervised and unsupervised NLP tasks including phrase similarity, noun-modifier questions, sentiment distribution prediction, and domain specific term identification tasks. We demonstrate that our model consistently outperforms the LSTM and CNN deep learning models, simple algebraic compositions, and other popular baselines on different datasets.
Original language | English |
---|---|
Title of host publication | CIKM 2017 - Proceedings of the 2017 ACM Conference on Information and Knowledge Management |
Publisher | Association for Computing Machinery (ACM) |
Pages | 1499-1507 |
Number of pages | 9 |
Volume | Part F131841 |
ISBN (Electronic) | 9781450349185 |
DOIs | |
Publication status | Published - 6 Nov 2017 |
Event | 26th ACM International Conference on Information and Knowledge Management, CIKM 2017 - Singapore, Singapore Duration: 6 Nov 2017 → 10 Nov 2017 |
Conference
Conference | 26th ACM International Conference on Information and Knowledge Management, CIKM 2017 |
---|---|
Country/Territory | Singapore |
City | Singapore |
Period | 6/11/17 → 10/11/17 |