1 |
Survey on the Use of Typological Information in Natural Language Processing ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Automatic Selection of Context Configurations for Improved Class-Specific Word Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
On the role of seed lexicons in learning bilingual word embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
HyperLex: A Large-Scale Evaluation of Graded Lexical Entailment ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Is "universal syntax" universally useful for learning distributed word representations? ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
On the role of seed lexicons in learning bilingual word embeddings
|
|
Vulíc, I; Korhonen, Anna-Leena. - : Association for Computational Linguistics, 2016. : http://www.aclweb.org/anthology/P/P16/P16-1024.pdf, 2016. : 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers, 2016
|
|
BASE
|
|
Show details
|
|
8 |
Anchoring and agreement in syntactic annotations
|
|
Berzak, Y; Huang, Yan; Barbu, A. - : Association for Computational Linguistics, 2016. : http://dspace.mit.edu/bitstream/handle/1721.1/104453/CBMM-Memo-055.pdf?sequence=1, 2016. : EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings, 2016
|
|
BASE
|
|
Show details
|
|
9 |
Is "universal syntax" universally useful for learning distributed word representations?
|
|
Vulić, I; Korhonen, Anna-Leena. - : Association for Computational Linguistics, 2016. : https://www.aclweb.org/anthology/P/P16/P16-2084.pdf, 2016. : 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers, 2016
|
|
Abstract:
Recent comparative studies have demonstrated the usefulness of dependency-based contexts (DEPS) for learning distributed word representations for similarity tasks. In English, DEPS tend to perform better than the more common, less informed bag-of-words contexts (BOW). In this paper, we present the first cross-linguistic comparison of different context types for three different languages. DEPS are extracted from ``universal parses'' without any language-specific optimization. Our results suggest that the universal DEPS (UDEPS) are useful for detecting functional similarity (e.g., verb similarity, solving syntactic analogies) among languages, but their advantage over BOW is not as prominent as previously reported on English. We also show that simple ``post-parsing'' filtering of useful UDEPS contexts leads to consistent improvements across languages.
|
|
URL: https://doi.org/10.17863/CAM.9720 https://www.repository.cam.ac.uk/handle/1810/268508
|
|
BASE
|
|
Hide details
|
|
|
|