161 |
Post-specialisation: Retrofitting vectors of words unseen in lexical resources
|
|
|
|
BASE
|
|
Show details
|
|
162 |
Discriminating between lexico-semantic relations with the specialization tensor model
|
|
|
|
BASE
|
|
Show details
|
|
163 |
Adversarial propagation and zero-shot cross-lingual transfer of word vector specialization
|
|
|
|
BASE
|
|
Show details
|
|
167 |
Automatic Selection of Context Configurations for Improved Class-Specific Word Representations ...
|
|
|
|
BASE
|
|
Show details
|
|
168 |
Cross-lingual syntactically informed distributed word representations ...
|
|
Vulic, Ivan. - : Apollo - University of Cambridge Repository, 2017
|
|
BASE
|
|
Show details
|
|
170 |
Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints ...
|
|
|
|
BASE
|
|
Show details
|
|
171 |
Morph-fitting: Fine-Tuning Word Vector Spaces with Simple Language-Specific Rules ...
|
|
|
|
BASE
|
|
Show details
|
|
172 |
Decoding Sentiment from Distributed Representations of Sentences ...
|
|
|
|
BASE
|
|
Show details
|
|
173 |
Cross-Lingual Induction and Transfer of Verb Classes Based on Word Vector Space Specialisation ...
|
|
|
|
BASE
|
|
Show details
|
|
174 |
Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints ...
|
|
|
|
BASE
|
|
Show details
|
|
175 |
Morph-fitting: Fine-tuning word vector spaces with simple language-specific rules ...
|
|
|
|
BASE
|
|
Show details
|
|
176 |
Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints
|
|
Mrkšić, Nikola; Vulić, Ivan; Ó Séaghdha, Diarmuid. - : Association for Computational Linguistics, 2017. : https://www.transacl.org/ojs/index.php/tacl/article/view/1171, 2017. : Transactions of the Association for Computational Linguistics (TACL), 2017
|
|
BASE
|
|
Show details
|
|
177 |
Morph-fitting: Fine-tuning word vector spaces with simple language-specific rules
|
|
|
|
Abstract:
Morphologically rich languages accentuate two properties of distributional vector space models: 1) the difficulty of inducing accurate representations for low-frequency word forms; and 2) insensitivity to distinct lexical relations that have similar distributional signatures. These effects are detrimental for language understanding systems, which may infer that inexpensive is a rephrasing for expensive or may not associate acquire with acquires. In this work, we propose a novel morph-fitting procedure which moves past the use of curated semantic lexicons for improving distributional vector spaces. Instead, our method injects morphological constraints generated using simple language-specific rules, pulling inflectional forms of the same word close together and pushing derivational antonyms far apart. In intrinsic evaluation over four languages, we show that our approach: 1) improves low-frequency word estimates; and 2) boosts the semantic quality of the entire word vector collection. Finally, we show that morph-fitted vectors yield large gains in the downstream task of dialogue state tracking, highlighting the importance of morphology for tackling long-tail phenomena in language understanding tasks.
|
|
Keyword:
Dialogue state tracking; Morphologically complex languages; Semantic specialisation; Vector space models; Word embeddings
|
|
URL: https://doi.org/10.17863/CAM.10176 https://www.repository.cam.ac.uk/handle/1810/264637
|
|
BASE
|
|
Hide details
|
|
178 |
Cross-lingual syntactically informed distributed word representations
|
|
Vulic, Ivan. - : Association for Computational Linguistics, 2017. : 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference, 2017
|
|
BASE
|
|
Show details
|
|
179 |
Automatic Selection of Context Configurations for Improved Class-Specific Word Representations
|
|
Rappoport, Ari; Reichart, Roi; Korhonen, Anna-Leena. - : Association for Computational Linguistics, 2017. : https://arxiv.org/pdf/1608.05528.pdf, 2017. : Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), 2017
|
|
BASE
|
|
Show details
|
|
180 |
If sentences could see: Investigating visual information for semantic textual similarity
|
|
|
|
BASE
|
|
Show details
|
|
|
|