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
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Dependency Parsing | Chinese Treebank (CTB) (test) | UAS85.3 | 99 | |
| Dependency Parsing | English PTB Stanford Dependencies (test) | UAS91.63 | 76 | |
| Dependency Parsing | CoNLL 2009 (test) | UAS88.83 | 14 | |
| Dependency Parsing | TB2 (test) | UAS80.2 | 13 | |
| Dependency Parsing | Universal Dependencies 1.2 (test) | UAS (de)72.4 | 11 | |
| Universal Dependencies Parsing | TWEEBANK V2 (test) | LAS F175.7 | 9 |
Showing 6 of 6 rows