2 |
Graph Algorithms for Multiparallel Word Alignment
|
|
|
|
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing ; The 2021 Conference on Empirical Methods in Natural Language Processing ; https://hal.archives-ouvertes.fr/hal-03424044 ; The 2021 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Nov 2021, Punta Cana, Dominica ; https://2021.emnlp.org/ (2021)
|
|
BASE
|
|
Show details
|
|
3 |
Distributed representations for multilingual language processing
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Distributed representations for multilingual language processing ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
ParCourE: A Parallel Corpus Explorer for a Massively Multilingual Corpus ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Multilingual LAMA: Investigating Knowledge in Multilingual Pretrained Language Models ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Wine is Not v i n. -- On the Compatibility of Tokenizations Across Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Locating Language-Specific Information in Contextualized Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Static Embeddings as Efficient Knowledge Bases? ...
|
|
|
|
Abstract:
Read the paper on the folowing link: https://www.aclweb.org/anthology/2021.naacl-main.186/ Abstract: Recent research investigates factual knowledge stored in large pretrained language models (PLMs). Instead of structural knowledge base (KB) queries, masked sentences such as “Paris is the capital of [MASK]” are used as probes. The good performance on this analysis task has been interpreted as PLMs becoming potential repositories of factual knowledge. In experiments across ten linguistically diverse languages, we study knowledge contained in static embeddings. We show that, when restricting the output space to a candidate set, simple nearest neighbor matching using static embeddings performs better than PLMs. E.g., static embeddings perform 1.6% points better than BERT while just using 0.3% of energy for training. One important factor in their good comparative performance is that static embed- dings are standardly learned for a large vocabulary. In contrast, BERT exploits its more sophisticated, but expensive ...
|
|
URL: https://underline.io/lecture/20004-static-embeddings-as-efficient-knowledge-basesquestion https://dx.doi.org/10.48448/cf3z-dn34
|
|
BASE
|
|
Hide details
|
|
13 |
ParCourE: A Parallel Corpus Explorer for a Massively Multilingual Corpus ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Wine is not v i n. On the Compatibility of Tokenizations across Languages ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
SimAlign: High Quality Word Alignments Without Parallel Training Data Using Static and Contextualized Embeddings
|
|
|
|
In: EMNLP 2020 ; https://hal.archives-ouvertes.fr/hal-03013194 ; EMNLP 2020, Association for Computational Linguistics, Nov 2020, Online, United States. pp.1627 - 1643 (2020)
|
|
BASE
|
|
Show details
|
|
18 |
SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings
|
|
|
|
In: Findings of ACL: EMNLP 2020 (2020)
|
|
BASE
|
|
Show details
|
|
19 |
Monolingual and Multilingual Reduction of Gender Bias in Contextualized Representations
|
|
|
|
BASE
|
|
Show details
|
|
20 |
Increasing Learning Efficiency of Self-Attention Networks through Direct Position Interactions, Learnable Temperature, and Convoluted Attention
|
|
|
|
BASE
|
|
Show details
|
|
|
|