@inproceedings{c344aacc524046c3bd5bcd2c2a70484b,
title = "Syntax encoding with application in authorship attribution",
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.",
author = "Richong Zhang and Zhiyuan Hu and Hongyu Guo and Yongyi Mao",
note = "Publisher Copyright: {\textcopyright} 2018 Association for Computational Linguistics; 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018 ; Conference date: 31-10-2018 Through 04-11-2018",
year = "2018",
language = "英语",
series = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018",
publisher = "Association for Computational Linguistics",
pages = "2742--2753",
editor = "Ellen Riloff and David Chiang and Julia Hockenmaier and Jun'ichi Tsujii",
booktitle = "Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018",
address = "美国",
}