file.pdf (188.6 kB)

Dependency Parsing for Weibo: An Efficient Probabilistic Logic Programming Approach

Download (188.6 kB)
journal contribution
posted on 01.10.2014, 00:00 by William Yang Wang, Lingpeng Kong, Kathryn Mazaitis, William W. Cohen

Dependency parsing is a core task in NLP, and it is widely used by many applications such as information extraction, question answering, and machine translation. In the era of social media, a big challenge is that parsers trained on traditional newswire corpora typically suffer from the domain mismatch issue, and thus perform poorly on social media data. We present a new GFL/FUDG-annotated Chinese treebank with more than 18K tokens from Sina Weibo (the Chinese equivalent of Twitter). We formulate the dependency parsing problem as many small and parallelizable arc prediction tasks: for each task, we use a programmable probabilistic firstorder logic to infer the dependency arc of a token in the sentence. In experiments, we show that the proposed model outperforms an off-the-shelf Stanford Chinese parser, as well as a strong MaltParser baseline that is trained on the same in-domain data.

History

Publisher Statement

© 2014 Association for Computational Linguistics

Date

01/10/2014

Exports

Exports