Findings of the 2017 conference on machine translation (wmt17)
This paper presents the results of the WMT17 shared tasks, which included three machine
translation (MT) tasks (news, biomedical, and multimodal), two evaluation tasks (metrics and …
translation (MT) tasks (news, biomedical, and multimodal), two evaluation tasks (metrics and …
Document-level machine translation with word vector models
E Martínez Garcia, C España Bonet… - Proceedings of the …, 2015 - upcommons.upc.edu
In this paper we apply distributional semantic information to document-level machine
translation. We train monolingual and bilingual word vector models on large corpora and we …
translation. We train monolingual and bilingual word vector models on large corpora and we …
Learning bilingual projections of embeddings for vocabulary expansion in machine translation
PS Madhyastha, C Espana-Bonet - Proceedings of the 2nd …, 2017 - aclanthology.org
We propose a simple log-bilinear softmax-based model to deal with vocabulary expansion
in machine translation. Our model uses word embeddings trained on significantly large …
in machine translation. Our model uses word embeddings trained on significantly large …
[PDF][PDF] Dependency link embeddings: Continuous representations of syntactic substructures
M Bansal - Proceedings of the 1st Workshop on Vector Space …, 2015 - aclanthology.org
We present a simple method to learn continuous representations of dependency
substructures (links), with the motivation of directly working with higher-order, structured …
substructures (links), with the motivation of directly working with higher-order, structured …
Topic-sensitive influential paper discovery in citation network
Discovering important papers in different academic topics is known as topic-sensitive
influential paper discovery. Previous works mainly find the influential papers based on the …
influential paper discovery. Previous works mainly find the influential papers based on the …
Delexicalized word embeddings for cross-lingual dependency parsing
This paper presents a new approach to the problem of cross-lingual dependency parsing,
aiming at leveraging training data from different source languages to learn a parser in a …
aiming at leveraging training data from different source languages to learn a parser in a …
The talp–upc spanish–english wmt biomedical task: Bilingual embeddings and char-based neural language model rescoring in a phrase-based system
M Ruiz Costa-Jussà, C España-i-Bonet… - ACL 2016: the 54th …, 2016 - upcommons.upc.edu
This paper describes the TALP–UPC system in the Spanish–English WMT 2016 biomedical
shared task. Our system is a standard phrase-based system enhanced with vocabulary …
shared task. Our system is a standard phrase-based system enhanced with vocabulary …
[PDF][PDF] Bilexical embeddings for quality estimation
This paper describes the SHEF submissions for the three sub-tasks of the Quality Estimation
shared task of WMT17, namely:(i) a word-level prediction system using bilexical …
shared task of WMT17, namely:(i) a word-level prediction system using bilexical …
Predicting insertion positions in word-level machine translation quality estimation
M Esplà-Gomis, F Sánchez-Martínez… - Applied Soft Computing, 2019 - Elsevier
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 …
of automatically identifying which words need to be edited (either deleted or replaced) in a …
Prepositional phrase attachment over word embedding products
PS Madhyastha, X Carreras… - Proceedings of the 15th …, 2017 - aclanthology.org
We present a low-rank multi-linear model for the task of solving prepositional phrase
attachment ambiguity (PP task). Our model exploits tensor products of word embeddings …
attachment ambiguity (PP task). Our model exploits tensor products of word embeddings …