Abstract
We propose a novel strategy to encode the syntax parse tree of sentence into a learnable distributed representation. The proposed syntax encoding scheme is provably information-lossless. In specific, an embedding vector is constructed for each word in the sentence, encoding the path in the syntax tree corresponding to the word. The one-to-one correspondence between these “syntax-embedding” vectors and the words (hence their embedding vectors) in the sentence makes it easy to integrate such a representation with all word-level NLP models. We empirically show the benefits of the syntax embeddings on the Authorship Attribution domain, where our approach improves upon the prior art and achieves new performance records on five benchmarking data sets.- Anthology ID:
- D18-1294
- Volume:
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Month:
- October-November
- Year:
- 2018
- Address:
- Brussels, Belgium
- Editors:
- Ellen Riloff, David Chiang, Julia Hockenmaier, Jun’ichi Tsujii
- Venue:
- EMNLP
- SIG:
- SIGDAT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2742–2753
- Language:
- URL:
- https://aclanthology.org/D18-1294
- DOI:
- 10.18653/v1/D18-1294
- Cite (ACL):
- Richong Zhang, Zhiyuan Hu, Hongyu Guo, and Yongyi Mao. 2018. Syntax Encoding with Application in Authorship Attribution. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2742–2753, Brussels, Belgium. Association for Computational Linguistics.
- Cite (Informal):
- Syntax Encoding with Application in Authorship Attribution (Zhang et al., EMNLP 2018)
- PDF:
- https://preview.aclanthology.org/bionlp-24-ingestion/D18-1294.pdf