Skip to Main content Skip to Navigation
Conference papers

Neural Baselines for Word Alignments

Ahn-Khoa Ngo-Ho 1 François Yvon 1
1 TLP - Traitement du Langage Parlé
LIMSI - Laboratoire d'Informatique pour la Mécanique et les Sciences de l'Ingénieur : 247329
Abstract : Word alignments identify translational correspondences between words in a parallel sentence pair and is used, for instance, to learn bilingual dictionaries, to train statistical machine translation systems, or to perform quality estimation. In most areas of natural language processing, neural network models nowadays constitute the preferred approach, a situation that might also apply to word alignment models. In this work, we study and comprehensively evaluate neural models for unsupervised word alignment for four language pairs, contrasting several variants of neural models. We show that in most settings, neural versions of the IBM-1 and hidden Markov models vastly outperform their discrete counterparts. We also analyze typical alignment errors of the baselines that our models overcome to illustrate the benefits --- and the limitations --- of these new models for morphologically rich languages.
Complete list of metadatas

Cited literature [43 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02343217
Contributor : Limsi Publications <>
Submitted on : Saturday, November 2, 2019 - 2:53:47 PM
Last modification on : Monday, February 10, 2020 - 6:14:12 PM
Document(s) archivé(s) le : Monday, February 3, 2020 - 1:42:19 PM

File

IWSLT2019_paper_23.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02343217, version 1

Citation

Ahn-Khoa Ngo-Ho, François Yvon. Neural Baselines for Word Alignments. International Workshop on Spoken Language Translation, Nov 2019, Hong-Kong, China. ⟨hal-02343217⟩

Share

Metrics

Record views

56

Files downloads

95