DE eng

Search in the Catalogues and Directories

Page: 1 2 3 4 5 6
Hits 21 – 40 of 112

21
XHate-999: Analyzing and Detecting Abusive Language Across Domains and Languages ...
Glavas, Goran; Karan, Mladen; Vulic, Ivan. - : Apollo - University of Cambridge Repository, 2020
BASE
Show details
22
From Zero to Hero: On the Limitations of Zero-Shot Cross-Lingual Transfer with Multilingual Transformers ...
Lauscher, Anne; Ravishankar, Vinit; Vulic, Ivan. - : Apollo - University of Cambridge Repository, 2020
BASE
Show details
23
XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning ...
Ponti, Edoardo; Glavaš, Goran; Majewska, Olga. - : Apollo - University of Cambridge Repository, 2020
BASE
Show details
24
From Zero to Hero: On the Limitations of Zero-Shot Cross-Lingual Transfer with Multilingual Transformers ...
BASE
Show details
25
Verb Knowledge Injection for Multilingual Event Processing ...
BASE
Show details
26
Probing Pretrained Language Models for Lexical Semantics ...
BASE
Show details
27
SemEval-2020 Task 2: Predicting Multilingual and Cross-Lingual (Graded) Lexical Entailment ...
BASE
Show details
28
Specializing Unsupervised Pretraining Models for Word-Level Semantic Similarity ...
BASE
Show details
29
Specializing Unsupervised Pretraining Models for Word-Level Semantic Similarity ...
Lauscher, Anne; Vulic, Ivan; Ponti, Edoardo. - : Apollo - University of Cambridge Repository, 2020
BASE
Show details
30
SemEval-2020 Task 2: Predicting Multilingual and Cross-Lingual (Graded) Lexical Entailment ...
Glavas, Goran; Vulic, Ivan; Korhonen, Anna-Leena. - : Apollo - University of Cambridge Repository, 2020
BASE
Show details
31
Non-Linear Instance-Based Cross-Lingual Mapping for Non-Isomorphic Embedding Spaces ...
Glavas, Goran; Vulic, Ivan. - : Apollo - University of Cambridge Repository, 2020
BASE
Show details
32
Probing Pretrained Language Models for Lexical Semantics ...
Vulic, Ivan; Ponti, Edoardo; Litschko, Robert. - : Apollo - University of Cambridge Repository, 2020
BASE
Show details
33
Classification-Based Self-Learning for Weakly Supervised Bilingual Lexicon Induction ...
Karan, Mladen; Vulic, Ivan; Korhonen, Anna. - : Apollo - University of Cambridge Repository, 2020
BASE
Show details
34
Improving Bilingual Lexicon Induction with Unsupervised Post-Processing of Monolingual Word Vector Spaces ...
Vulic, Ivan; Korhonen, Anna; Glavas, Goran. - : Apollo - University of Cambridge Repository, 2020
BASE
Show details
35
Improving Bilingual Lexicon Induction with Unsupervised Post-Processing of Monolingual Word Vector Spaces
Vulic, Ivan; Korhonen, Anna; Glavas, Goran. - : 5TH WORKSHOP ON REPRESENTATION LEARNING FOR NLP (REPL4NLP-2020), 2020
BASE
Show details
36
Specializing Unsupervised Pretraining Models for Word-Level Semantic Similarity
Lauscher, Anne; Vulic, Ivan; Ponti, Edoardo; Korhonen, Anna; Glavas, Goran. - : International Committee on Computational Linguistics, 2020. : https://www.aclweb.org/anthology/2020.coling-main.118, 2020. : Proceedings of the 28th International Conference on Computational Linguistics (COLING 2020), 2020
Abstract: Unsupervised pretraining models have been shown to facilitate a wide range of downstream NLP applications. These models, however, retain some of the limitations of traditional static word embeddings. In particular, they encode only the distributional knowledge available in raw text corpora, incorporated through language modeling objectives. In this work, we complement such distributional knowledge with external lexical knowledge, that is, we integrate the discrete knowledge on word-level semantic similarity into pretraining. To this end, we generalize the standard BERT model to a multi-task learning setting where we couple BERT’s masked language modeling and next sentence prediction objectives with an auxiliary task of binary word relation classification. Our experiments suggest that our "Lexically Informed” BERT (LIBERT), specialized for the word-level semantic similarity, yields better performance than the lexically blind “vanilla” BERT on several language understanding tasks. Concretely, LIBERT outperforms BERT in 9 out of 10 tasks of the GLUE benchmark and is on a par with BERT in the remaining one. Moreover, we show consistent gains on 3 benchmarks for lexical simplification, a task where knowledge about word-level semantic similarity is paramount, as well as large gains on lexical reasoning probes.
URL: https://doi.org/10.17863/CAM.62219
https://www.repository.cam.ac.uk/handle/1810/315112
BASE
Hide details
37
Probing Pretrained Language Models for Lexical Semantics
Vulic, Ivan; Ponti, Edoardo; Litschko, Robert. - : Association for Computational Linguistics, 2020. : Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2020), 2020
BASE
Show details
38
SemEval-2020 Task 2: Predicting Multilingual and Cross-Lingual (Graded) Lexical Entailment
Glavas, Goran; Vulic, Ivan; Korhonen, Anna-Leena. - : International Committee for Computational Linguistics, 2020. : https://www.aclweb.org/anthology/2020.semeval-1.2, 2020. : Proceedings of the 14th International Workshop on Semantic Evaluation (SemEval 2020), 2020
BASE
Show details
39
Classification-Based Self-Learning for Weakly Supervised Bilingual Lexicon Induction
Karan, Mladen; Vulic, Ivan; Korhonen, Anna. - : Association for Computational Linguistics, 2020
BASE
Show details
40
Towards Instance-Level Parser Selection for Cross-Lingual Transfer of Dependency Parsers
Glavas, Goran; Agic, Zeljko; Vulic, Ivan. - : International Committee on Computational Linguistics, 2020. : https://www.aclweb.org/anthology/2020.coling-main.345, 2020. : Proceedings of the 28th International Conference on Computational Linguistics (COLING 2020), 2020
BASE
Show details

Page: 1 2 3 4 5 6

Catalogues
0
0
0
0
6
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
106
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern