Bitextor's participation in WMT'16: shared task on document alignment

Esplà-Gomis, Miquel; Forcada, Mikel L.; Rojas, Sergio Ortiz; Ferrández-Tordera, Jorge

doi:10.18653/v1/w16-2367

Cited by 15 publications

(15 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper proposes a collection of features that builds on those defined by Esplà-Gomis et al [13] and can be obtained from any source of bilingual information: in our experiments, online MT systems and an online bilingual concordancer were used. The results obtained on the datasets published for the word-level MT QE shared tasks at WMT15 and WMT16 confirm the good performance of the approach proposed, which is able to reproduce or even improve on the results obtained by Esplà-Gomis et al [13] and Esplà-Gomis et al [51].…”

Section: Discussionsupporting

confidence: 77%

Predicting insertion positions in word-level machine translation quality estimation

Esplà-Gomis

Sánchez-Martínez

Forcada

2019

Applied Soft Computing

Self Cite

View full text Add to dashboard Cite

Word-level machine translation (MT) quality estimation (QE) is usually formulated as the task of automatically identifying which words need to be edited (either deleted or replaced) in a translation T produced by an MT system. The advantage of estimating MT quality at the word level is that this information can be used to guide post-editors since it enables the identification of the specific words in T that need to be edited in order to ease their work. However, wordlevel MT QE, as defined in the current literature, has an obvious limitation: it does not identify the positions in T in which missing words need to be inserted.To deal with this limitation, we propose a method which identifies both word deletions and insertion positions in T . This is, to the best of our knowledge, the first approach allowing the identification of insertion positions in word-level MT QE. The method proposed can use any source of bilingual information -such as MT, dictionaries, or phrase-level translation memories-to extract features that are then used by a neural network to produce a prediction for both words and insertion positions (gaps between words) in the translation T . In this paper, several feature sets and neural network architectures are explored and evaluated on publicly-available datasets used in previous evaluation campaigns for wordlevel MT QE. The results confirm the feasibility of the proposed approach, as

show abstract

Section: Discussionsupporting

confidence: 77%

Predicting insertion positions in word-level machine translation quality estimation

Esplà-Gomis

Sánchez-Martínez

Forcada

2019

Applied Soft Computing

Self Cite

View full text Add to dashboard Cite

show abstract

“…The vectors are then typically matched with cosine similarity (Buck and Koehn, 2016a). The raw vectors may be recentered around the mean vector for a web domain (Germann, 2016) Document alignment quality can be improved with additional features such ratio of shared links, similarity of link URLs, ratio of shared images, binary feature indicating if the documents are linked, DOM structure similarity (Esplà-Gomis et al, 2016), same numbers (Papavassiliou et al, 2016), or same named entities (Lohar et al, 2016). Guo et al (2019) introduce the use of document embeddings, constructed from sentence embeddings, to the document alignment task.…”

Section: Document Alignmentmentioning

confidence: 99%

ParaCrawl: Web-Scale Acquisition of Parallel Corpora

Bañón¹,

Chen²,

Haddow³

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Previous methods depended on engineering features. (Shi et al, 2006;Esplà-Gomis et al, 2016) used metadata information from web crawls to mine parallel data. Recent methods used crosslingual word embeddings to obtain parallel corpora (Guo et al, 2018;Schwenk, 2018;Bouamor and Sajjad, 2018;Schwenk et al, 2019b,a).…”

Section: Related Workmentioning

confidence: 99%

Parallel sentences mining with transfer learning in an unsupervised setting

Sun¹,

Zhu²,

Feng³

et al. 2021

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Rese

View full text Add to dashboard Cite

The quality and quantity of parallel sentences are known as very important training data for constructing neural machine translation (N-MT) systems. However, these resources are not available for many low-resource language pairs. Many existing methods need strong supervision and hence are not suitable. Although there have been several attempts at developing unsupervised models, they ignore the language-invariant between languages. In this paper, we propose an approach based on transfer learning to mine parallel sentences in an unsupervised setting. With the help of bilingual corpora of rich-resource language pairs, we can mine parallel sentences without bilingual supervision of low-resource language pairs. Experiments show that our approach improves the performance of mined parallel sentences compared with previous methods. In particular, we achieve good results at two real-world low-resource language pairs.

show abstract

Bitextor's participation in WMT'16: shared task on document alignment

Cited by 15 publications

References 8 publications

Predicting insertion positions in word-level machine translation quality estimation

Predicting insertion positions in word-level machine translation quality estimation

ParaCrawl: Web-Scale Acquisition of Parallel Corpora

Parallel sentences mining with transfer learning in an unsupervised setting

Contact Info

Product

Resources

About