1 |
A Closer Look into the Robustness of Neural Dependency Parsers Using Better Adversarial Examples ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
A Root of a Problem: Optimizing Single-Root Dependency Parsing ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Unlexicalized Transition-based Discontinuous Constituency Parsing
|
|
|
|
In: EISSN: 2307-387X ; Transactions of the Association for Computational Linguistics ; https://hal.archives-ouvertes.fr/hal-02150073 ; Transactions of the Association for Computational Linguistics, The MIT Press, 2019, 7, pp.73--89. ⟨10.1162/tacl_a_00255⟩ (2019)
|
|
Abstract:
Lexicalized parsing models are based on the assumptions that (i) constituents are organized around a lexical head and (ii) bilexical statistics are crucial to solve ambiguities. In this paper, we introduce an unlexicalized transition-based parser for discontinuous constituency structures, based on a structure-label transition system and a bi-LSTM scoring system. We compare it with lexicalized parsing models in order to address the question of lexicalization in the context of discontinuous constituency parsing. Our experiments show that unlexicalized models systematically achieve higher results than lexicalized models, and provide additional empirical evidence that lexicalization is not necessary to achieve strong parsing results. Our best unlexicalized model sets a new state of the art on English and German discontinuous constituency treebanks. We further provide a per-phenomenon analysis of its errors on discontinuous constituents.
|
|
Keyword:
[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]
|
|
URL: https://doi.org/10.1162/tacl_a_00255 https://hal.archives-ouvertes.fr/hal-02150073
|
|
BASE
|
|
Hide details
|
|
4 |
Discontinuous Constituency Parsing with a Stack-Free Transition System and a Dynamic Oracle
|
|
|
|
In: 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT 2019) ; https://hal.archives-ouvertes.fr/hal-02150076 ; 2019 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT 2019), Jun 2019, Minneapolis, MN, United States. pp.204--217 ; https://naacl2019.org/ (2019)
|
|
BASE
|
|
Show details
|
|
5 |
Unlexicalized Transition-based Discontinuous Constituency Parsing ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Unlexicalized Transition-based Discontinuous Constituency Parsing
|
|
|
|
In: Transactions of the Association for Computational Linguistics, Vol 7, Pp 73-89 (2019) (2019)
|
|
BASE
|
|
Show details
|
|
7 |
Privacy-preserving Neural Representations of Text
|
|
|
|
In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing ; 2018 Conference on Empirical Methods in Natural Language Processing ; https://hal.archives-ouvertes.fr/hal-02135081 ; 2018 Conference on Empirical Methods in Natural Language Processing, Nov 2018, Brussels, Belgium. pp.1--10 (2018)
|
|
BASE
|
|
Show details
|
|
8 |
Empirical Risk Minimization for Probabilistic Grammars: Sample Complexity and Hardness of Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Unsupervised Bilingual POS Tagging with Markov Random Fields ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Unsupervised Bilingual POS Tagging with Markov Random Fields ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Whodunnit? Crime Drama as a Case for Natural Language Understanding ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Paraphrase Generation from Latent-Variable PCFGs for Semantic Parsing ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Paraphrase Generation From Latent-Variable Pcfgs For Semantic Parsing ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Paraphrase Generation From Latent-Variable Pcfgs For Semantic Parsing ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Paraphrase Generation from Latent-Variable PCFGs for Semantic Parsing ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Paraphrase Generation from Latent-Variable PCFGs for Semantic Parsing ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|