1 |
EVI: Multilingual Spoken Dialogue Tasks and Dataset for Knowledge-Based Enrolment, Verification, and Identification ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Improving Word Translation via Two-Stage Contrastive Learning ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Learning Domain-Specialised Representations for Cross-Lingual Biomedical Entity Linking ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Emergent Communication Pretraining for Few-Shot Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
On the Limitations of Unsupervised Bilingual Dictionary Induction ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Scoring Lexical Entailment with a Supervised Directional Similarity Network ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Semantic Specialisation of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints ...
|
|
|
|
Abstract:
We present Attract-Repel, an algorithm for improving the semantic quality of word vectors by injecting constraints extracted from lexical resources. Attract-Repel facilitates the use of constraints from mono- and cross-lingual resources, yielding semantically specialised cross-lingual vector spaces. Our evaluation shows that the method can make use of existing cross-lingual lexicons to construct high-quality vector spaces for a plethora of different languages, facilitating semantic transfer from high- to lower-resource ones. The effectiveness of our approach is demonstrated with state-of-the-art results on semantic similarity datasets in six languages. We next show that Attract-Repel-specialised vectors boost performance in the downstream task of dialogue state tracking (DST) across multiple languages. Finally, we show that cross-lingual vector spaces produced by our algorithm facilitate the training of multilingual DST models, which brings further performance improvements. ... : Accepted for publication at TACL (to be presented at EMNLP 2017) ...
|
|
Keyword:
Artificial Intelligence cs.AI; Computation and Language cs.CL; FOS Computer and information sciences; Machine Learning cs.LG
|
|
URL: https://dx.doi.org/10.48550/arxiv.1706.00374 https://arxiv.org/abs/1706.00374
|
|
BASE
|
|
Hide details
|
|
|
|