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

arXiv: https://arxiv.org/abs/1508.00657 · HTML: https://mlsanity.com/paper/1508.00657/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Aug 2015.

## Built on by (most cited first, 10 of 10)

- [MrT5: Dynamic Token Merging for Efficient Byte-level Language Models](https://mlsanity.com/paper/2410.20771/) (2024)
- [Neural OCR Post-Hoc Correction of Historical Corpora](https://mlsanity.com/paper/2102.00583/) (2021)
- [Recent Trends in Named Entity Recognition (NER)](https://mlsanity.com/paper/2101.11420/) (2021)
- [Annotating the Tweebank Corpus on Named Entity Recognition and Building NLP Models for Social Media Analysis](https://mlsanity.com/paper/2201.07281/) (2022)
- [A Falta de Pan, Buenas Son Tortas: The Efficacy of Predicted UPOS Tags for Low Resource UD Parsing](https://mlsanity.com/paper/2106.04222/) (2021)
- [SWE2: SubWord Enriched and Significant Word Emphasized Framework for Hate Speech Detection](https://mlsanity.com/paper/2409.16673/) (2024)
- [What Taggers Fail to Learn, Parsers Need the Most](https://mlsanity.com/paper/2104.01083/) (2021)
- [UnibucKernel: Geolocating Swiss German Jodels Using Ensemble Learning](https://mlsanity.com/paper/2102.09379/) (2021)
- [Parsing linearizations appreciate PoS tags - but some are fussy about errors](https://mlsanity.com/paper/2210.15219/) (2022)
- [Another Dead End for Morphological Tags? Perturbed Inputs and Parsing](https://mlsanity.com/paper/2305.15119/) (2023)

## Abstract (arXiv)

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.