Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Improved Transition-Based Parsing by Modeling Characters instead of Words with LSTMs

About

We present extensions to a continuous-state dependency parsing method that makes it applicable to morphologically rich languages. Starting with a high-performance transition-based parser that uses long short-term memory (LSTM) recurrent neural networks to learn representations of the parser state, we replace lookup-based word representations with representations constructed from the orthographic representations of the words, also using LSTMs. This allows statistical sharing across word forms that are similar on the surface. Experiments for morphologically rich languages show that the parsing model benefits from incorporating the character-based encodings of words.

Miguel Ballesteros, Chris Dyer, Noah A. Smith• 2015

Related benchmarks

TaskDatasetResultRank
Dependency ParsingChinese Treebank (CTB) (test)
UAS85.3
99
Dependency ParsingEnglish PTB Stanford Dependencies (test)
UAS91.63
76
Dependency ParsingCoNLL 2009 (test)
UAS88.83
14
Dependency ParsingTB2 (test)
UAS80.2
13
Dependency ParsingUniversal Dependencies 1.2 (test)
UAS (de)72.4
11
Universal Dependencies ParsingTWEEBANK V2 (test)
LAS F175.7
9
Showing 6 of 6 rows

Other info

Follow for update