1 |
The European Language Technology Landscape in 2020: Language-Centric and Human-Centric AI for Cross-Cultural Communication in Multilingual Europe
|
|
|
|
In: Language Resources and Evaluation Conference ; https://hal.archives-ouvertes.fr/hal-02892154 ; Language Resources and Evaluation Conference, ELDA/ELRA, May 2020, Marseille, France ; https://lrec2020.lrec-conf.org/en/ (2020)
|
|
BASE
|
|
Show details
|
|
2 |
The European Language Technology Landscape in 2020: Language-Centric and Human-Centric AI for Cross-Cultural Communication in Multilingual Europe ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
The European Language Technology Landscape in 2020: Language-Centric and Human-Centric AI for Cross-Cultural Communication in Multilingual Europe ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
The European Language Technology Landscape in 2020: Language-Centric and Human-Centric AI for Cross-Cultural Communication in Multilingual Europe ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
IntKB: A Verifiable Interactive Framework for Knowledge Base Completion
|
|
|
|
In: Proceedings of the 28th International Conference on Computational Linguistics (2020)
|
|
BASE
|
|
Show details
|
|
6 |
A Geometry-Inspired Attack for Generating Natural Language Adversarial Examples
|
|
|
|
In: Proceedings of the 28th International Conference on Computational Linguistics (2020)
|
|
BASE
|
|
Show details
|
|
7 |
Morphologically Aware Word-Level Translation
|
|
|
|
In: Proceedings of the 28th International Conference on Computational Linguistics (2020)
|
|
Abstract:
We propose a novel morphologically aware probability model for bilingual lexicon induction, which jointly models lexeme translation and inflectional morphology in a structured way. Our model exploits the basic linguistic intuition that the lexeme is the key lexical unit of meaning, while inflectional morphology provides additional syntactic information. This approach leads to substantial performance improvements—19% average improvement in accuracy across 6 language pairs over the state of the art in the supervised setting and 16% in the weakly supervised setting. As another contribution, we highlight issues associated with modern BLI that stem from ignoring inflectional morphology, and propose three suggestions for improving the task.
|
|
URL: https://doi.org/10.3929/ethz-b-000462302 https://hdl.handle.net/20.500.11850/462302
|
|
BASE
|
|
Hide details
|
|
8 |
Graph Convolution over Multiple Dependency Sub-graphs for Relation Extraction.
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Specializing unsupervised pretraining models for word-level semantic similarity
|
|
|
|
BASE
|
|
Show details
|
|
11 |
XHate-999: analyzing and detecting abusive language across domains and languages
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Towards instance-level parser selection for cross-lingual transfer of dependency parsers
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Using unmarked contexts in nominal lexical semantic classification
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Les indústries de la llengua i la tecnologia per al català ; The Language Industries and Technology for Catalan ; Las industrias de la lengua y la tecnología para el catalán
|
|
|
|
In: Llengua i ús: revista tècnica de política lingüística; Núm. 58 (2016); p. 17 - 26 (2016)
|
|
BASE
|
|
Show details
|
|
19 |
Mining and Exploiting Domain-Specific Corpora in the PANACEA Platform ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Automatic Detection of Non-deverbal Event Nouns for Quick Lexicon Production ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|