Many Languages, One Parser

@article{Ammar2016ManyLO,
  title={Many Languages, One Parser},
  author={Waleed Ammar and George Mulcaire and Miguel Ballesteros and Chris Dyer and Noah A. Smith},
  journal={Transactions of the Association for Computational Linguistics},
  year={2016},
  volume={4},
  pages={431-444}
}
We train one multilingual model for dependency parsing and use it to parse sentences in several languages. The parsing model uses (i) multilingual word clusters and embeddings; (ii) token-level language information; and (iii) language-specific features (fine-grained POS tags). This input representation enables the parser not only to parse effectively in multiple languages, but also to generalize across languages based on linguistic universals and typological similarities, making it more… CONTINUE READING

Results and Topics from this paper.

Key Quantitative Results

  • In the small treebank setup with 3,000 token annotations, we show that our parser consistently outperforms a strong monolingual baseline with 5.7 absolute LAS (labeled attachment score) points per language, on average.

Explore Further: Topics Discussed in This Paper

Citations

Publications citing this paper.
SHOWING 1-10 OF 100 CITATIONS

CoNLL 2018 Shared Task on Multilingual Parsing

Hui Wan Tahira Naseem Young-Suk Lee Vittorio Castelli Ballesteros
  • 2018
VIEW 14 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS
HIGHLY INFLUENCED

Surface Statistics of an Unknown Language Indicate How to Parse It

  • Transactions of the Association for Computational Linguistics
  • 2018
VIEW 9 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Natural language processing for resource-poor languages

VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Cross-Lingual Syntactic Transfer with Limited Resources

  • Transactions of the Association for Computational Linguistics
  • 2016
VIEW 15 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

A Grounded Unsupervised Universal Part-of-Speech Tagger for Low-Resource Languages

VIEW 7 EXCERPTS
CITES METHODS, RESULTS & BACKGROUND
HIGHLY INFLUENCED

Low-Resource Parsing with Crosslingual Contextualized Representations

Phoebe Mulcaire, Jungo Kasai, Noah A. Smith
  • ArXiv
  • 2019
VIEW 9 EXCERPTS
CITES BACKGROUND & METHODS

Massively Multilingual Transfer for NER

VIEW 8 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing

Edoardo Maria Ponti, Helen O’Horan, +5 authors Anna Korhonen
  • Computational Linguistics
  • 2019
VIEW 11 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Multilingual NER Transfer for Low-resource Languages

VIEW 12 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2016
2019

CITATION STATISTICS

  • 26 Highly Influenced Citations

  • Averaged 30 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 51 REFERENCES

Speech recognition with deep recurrent neural networks

  • 2013 IEEE International Conference on Acoustics, Speech and Signal Processing
  • 2013
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL