41 |
From Zero to Hero: On the Limitations of Zero-Shot Cross-Lingual Transfer with Multilingual Transformers
|
|
|
|
BASE
|
|
Show details
|
|
42 |
XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning
|
|
|
|
BASE
|
|
Show details
|
|
43 |
XHate-999: Analyzing and Detecting Abusive Language Across Domains and Languages
|
|
Glavas, Goran; Karan, Mladen; Vulic, Ivan. - : International Committee on Computational Linguistics, 2020. : https://www.aclweb.org/anthology/2020.coling-main.559, 2020. : Proceedings of the 28th International Conference on Computational Linguistics (COLING 2020), 2020
|
|
BASE
|
|
Show details
|
|
44 |
Specializing unsupervised pretraining models for word-level semantic similarity
|
|
|
|
BASE
|
|
Show details
|
|
45 |
Non-linear instance-based cross-lingual mapping for non-isomorphic embedding spaces
|
|
|
|
BASE
|
|
Show details
|
|
46 |
Classification-based self-learning for weakly supervised bilingual lexicon induction
|
|
|
|
BASE
|
|
Show details
|
|
47 |
AraWEAT: Multidimensional analysis of biases in Arabic word embeddings
|
|
|
|
BASE
|
|
Show details
|
|
49 |
Common sense or world knowledge? Investigating adapter-based knowledge injection into pretrained transformers
|
|
|
|
BASE
|
|
Show details
|
|
50 |
XHate-999: analyzing and detecting abusive language across domains and languages
|
|
|
|
BASE
|
|
Show details
|
|
51 |
On the limitations of cross-lingual encoders as exposed by reference-free machine translation evaluation
|
|
|
|
BASE
|
|
Show details
|
|
52 |
XCOPA: A multilingual dataset for causal commonsense reasoning
|
|
|
|
BASE
|
|
Show details
|
|
53 |
Improving bilingual lexicon induction with unsupervised post-processing of monolingual word vector spaces
|
|
|
|
BASE
|
|
Show details
|
|
54 |
From zero to hero: On the limitations of zero-shot language transfer with multilingual transformers
|
|
|
|
BASE
|
|
Show details
|
|
55 |
SemEval-2020 Task 2: Predicting multilingual and cross-lingual (graded) lexical entailment
|
|
|
|
BASE
|
|
Show details
|
|
56 |
Towards instance-level parser selection for cross-lingual transfer of dependency parsers
|
|
|
|
BASE
|
|
Show details
|
|
57 |
Specializing Unsupervised Pretraining Models for Word-Level Semantic Similarity ...
|
|
|
|
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 ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/1909.02339 https://dx.doi.org/10.48550/arxiv.1909.02339
|
|
BASE
|
|
Hide details
|
|
58 |
Do We Really Need Fully Unsupervised Cross-Lingual Embeddings? ...
|
|
|
|
BASE
|
|
Show details
|
|
59 |
How to (Properly) Evaluate Cross-Lingual Word Embeddings: On Strong Baselines, Comparative Analyses, and Some Misconceptions ...
|
|
|
|
BASE
|
|
Show details
|
|
60 |
Specialising Distributional Vectors of All Words for Lexical Entailment ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|