1 |
Multilingual and Cross-Lingual Intent Detection from Spoken Data ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Multilingual and Cross-Lingual Intent Detection from Spoken Data ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Data-Driven Language Understanding for Spoken Dialogue Systems ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Adversarial Propagation and Zero-Shot Cross-Lingual Transfer of Word Vector Specialization ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Post-Specialisation: Retrofitting Vectors of Words Unseen in Lexical Resources ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Post-Specialisation: Retrofitting Vectors of Words Unseen in Lexical Resources ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Post-specialisation: Retrofitting vectors of words unseen in lexical resources
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Adversarial propagation and zero-shot cross-lingual transfer of word vector specialization
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
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 ... : ACL 2017 (Long paper) ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.1706.00377 https://arxiv.org/abs/1706.00377
|
|
BASE
|
|
Hide details
|
|
13 |
Cross-Lingual Induction and Transfer of Verb Classes Based on Word Vector Space Specialisation ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
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
|
|
17 |
Neural Belief Tracker: Data-Driven Dialogue State Tracking ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Research data supporting "On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems"
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Multi-domain Dialog State Tracking using Recurrent Neural Networks ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Stochastic Language Generation in Dialogue using Recurrent Neural Networks with Convolutional Sentence Reranking ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|