1 |
Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing
|
|
|
|
In: ISSN: 0891-2017 ; EISSN: 1530-9312 ; Computational Linguistics ; https://hal.archives-ouvertes.fr/hal-02425462 ; Computational Linguistics, Massachusetts Institute of Technology Press (MIT Press), 2019, 45 (3), pp.559-601. ⟨10.1162/coli_a_00357⟩ ; https://www.mitpressjournals.org/doi/abs/10.1162/coli_a_00357 (2019)
|
|
BASE
|
|
Show details
|
|
2 |
Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Show Some Love to Your n-grams: A Bit of Progress and Stronger n-gram Language Modeling Baselines ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Specializing Unsupervised Pretraining Models for Word-Level Semantic Similarity ...
|
|
|
|
Abstract:
Unsupervised pretraining models have been shown to facilitate a wide range of downstream NLP applications. These models, however, retain some of the limitations of traditional static word embeddings. In particular, they encode only the distributional knowledge available in raw text corpora, incorporated through language modeling objectives. In this work, we complement such distributional knowledge with external lexical knowledge, that is, we integrate the discrete knowledge on word-level semantic similarity into pretraining. To this end, we generalize the standard BERT model to a multi-task learning setting where we couple BERT's masked language modeling and next sentence prediction objectives with an auxiliary task of binary word relation classification. Our experiments suggest that our "Lexically Informed" BERT (LIBERT), specialized for the word-level semantic similarity, yields better performance than the lexically blind "vanilla" BERT on several language understanding tasks. Concretely, LIBERT ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/1909.02339 https://dx.doi.org/10.48550/arxiv.1909.02339
|
|
BASE
|
|
Hide details
|
|
5 |
Do We Really Need Fully Unsupervised Cross-Lingual Embeddings? ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
How to (Properly) Evaluate Cross-Lingual Word Embeddings: On Strong Baselines, Comparative Analyses, and Some Misconceptions ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Specialising Distributional Vectors of All Words for Lexical Entailment ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Multilingual and cross-lingual graded lexical entailment ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Generalized tuning of distributional word vectors for monolingual and cross-lingual lexical entailment ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Generalized tuning of distributional word vectors for monolingual and cross-lingual lexical entailment
|
|
Glavaš, G; Vulic, Ivan. - : Association for Computational Linguistics, 2019. : ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference, 2019
|
|
BASE
|
|
Show details
|
|
11 |
Multilingual and cross-lingual graded lexical entailment
|
|
Vulic, Ivan; Ponzetto, SP; Glavaš, G. - : Association for Computational Linguistics, 2019. : ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference, 2019
|
|
BASE
|
|
Show details
|
|
12 |
How to (properly) evaluate cross-lingual word embeddings: On strong baselines, comparative analyses, and some misconceptions
|
|
Glavaš, G; Litschko, R; Ruder, S. - : Association for Computational Linguistics, 2019. : ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference, 2019
|
|
BASE
|
|
Show details
|
|
13 |
JW300: A wide-coverage parallel corpus for low-resource languages
|
|
Agic, Ž; Vulic, Ivan. - : Association for Computational Linguistics, 2019. : ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference, 2019
|
|
BASE
|
|
Show details
|
|
15 |
Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Specializing distributional vectors of all words for lexical entailment
|
|
|
|
BASE
|
|
Show details
|
|
18 |
How to (properly) evaluate cross-lingual word embeddings: On strong baselines, comparative analyses, and some misconceptions
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Cross-lingual semantic specialization via lexical relation induction
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Generalized tuning of distributional word vectors for monolingual and cross-lingual lexical entailment
|
|
|
|
BASE
|
|
Show details
|
|
|
|