1 |
Universals of Linguistic Idiosyncrasy in Multilingual Computational Linguistics (Dagstuhl Seminar 21351)
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Universals of Linguistic Idiosyncrasy in Multilingual Computational Linguistics (Dagstuhl Seminar 21351) ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Attention Can Reflect Syntactic Structure (If You Let It) ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
What Should/Do/Can LSTMs Learn When Parsing Auxiliary Verb Constructions? ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Understanding Pure Character-Based Neural Machine Translation: The Case of Translating Finnish into English ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Understanding Pure Character-Based Neural Machine Translation: The Case of Translating Finnish into English
|
|
|
|
In: Tang, Gongbo; Sennrich, Rico; Nivre, Joakim (2020). Understanding Pure Character-Based Neural Machine Translation: The Case of Translating Finnish into English. In: Proceedings of the 28th International Conference on Computational Linguistics, Barcelona, Spain, 8 December 2020 - 13 December 2020, 4251-4262. (2020)
|
|
BASE
|
|
Show details
|
|
16 |
Encoders Help You Disambiguate Word Senses in Neural Machine Translation ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Encoders Help You Disambiguate Word Senses in Neural Machine Translation ...
|
|
|
|
Abstract:
Neural machine translation (NMT) has achieved new state-of-the-art performance in translating ambiguous words. However, it is still unclear which component dominates the process of disambiguation. In this paper, we explore the ability of NMT encoders and decoders to disambiguate word senses by evaluating hidden states and investigating the distributions of self-attention. We train a classifier to predict whether a translation is correct given the representation of an ambiguous noun. We find that encoder hidden states outperform word embeddings significantly which indicates that encoders adequately encode relevant information for disambiguation into hidden states. Decoders could provide further relevant information for disambiguation. Moreover, the attention weights and attention entropy show that self-attention can detect ambiguous nouns and distribute more attention to the context. Note that this is a revised version. The content related to decoder hidden states has been updated. ... : Update with corrections. Here is the link to the erratum: https://www.aclweb.org/anthology/D19-1149e1.pdf ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.1908.11771 https://arxiv.org/abs/1908.11771
|
|
BASE
|
|
Hide details
|
|
|
|