Using information about multi-word expressions for the word-alignment task

Venkatapathy, Sriram; Joshi, Aravind K.

doi:10.3115/1613692.1613697

Cited by 15 publications

(9 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to improve the word alignment quality, Venkatapathy and Joshi (2006) reported a discriminative approach to use the compositionality information of verb-based multi-word expressions. Pal et al (2011) discussed the effects of incorporating prior alignment of MWE and NEs directly or indirectly into Phrase-based SMT systems.…”

Section: Bilingual Mwe In Mtmentioning

confidence: 99%

Manawi: Using Multi-Word Expressions and Named Entities to Improve Machine Translation

Tan¹,

Pal²

2014

Proceedings of the Ninth Workshop on Statistical Machine Translation

View full text Add to dashboard Cite

We describe the Manawi 1 ( ) system submitted to the 2014 WMT translation shared task. We participated in the English-Hindi (EN-HI) and Hindi-English (HI-EN) language pair and achieved 0.792 for the Translation Error Rate (TER) score 2 for EN-HI, the lowest among the competing systems. Our main innovations are (i) the usage of outputs from NLP tools, viz. billingual multi-word expression extractor and named-entity recognizer to improve SMT quality and (ii) the introduction of a novel filter method based on sentence-alignment features. The Manawi system showed the potential of improving translation quality by incorporating multiple NLP tools within the MT pipeline.

show abstract

Section: Bilingual Mwe In Mtmentioning

confidence: 99%

Manawi: Using Multi-Word Expressions and Named Entities to Improve Machine Translation

Tan¹,

Pal²

2014

Proceedings of the Ninth Workshop on Statistical Machine Translation

View full text Add to dashboard Cite

show abstract

“…A lexicon, including multiword expressions (MWEs), is a very important resource for many natural language processing (NLP) applications, such as building ontologies [1], information retrieval (IR) [2], text alignment [3], machine translation [4,5], and so on [6]. In general, extracting bilingual lexicons requires many linguistic resources, such as bilingual corpora (i.e., parallel or comparable), bilingual seed dictionaries, and some heuristics, for mapping identical word pairs between two languages.…”

Section: Introductionmentioning

confidence: 99%

Bilingual Multiword Expression Alignment by Constituent-Based Similarity Score

Seo¹,

Kwon²,

Cheon³

et al. 2016

J Inf Process Syst

View full text Add to dashboard Cite

This paper presents the constituent-based approach for aligning bilingual multiword expressions, such as noun phrases, by considering the relationship not only between source expressions and their target translation equivalents but also between the expressions and constituents of the target equivalents. We only considered the compositional preferences of multiword expressions and not their idiomatic usages because our multiword identification method focuses on their collocational or compositional preferences. In our experimental results, the constituent-based approach showed much better performances than the general method for extracting bilingual multiword expressions. For our future work, we will examine the scoring method of the constituent-based approach in regards to having the best performance. Moreover, we will extend target entries in the evaluation dictionaries by considering their synonyms.

show abstract

“…While the explicit identification of multiword expressions ("MWEs": , Baldwin and Kim (2009)) has been shown to be useful in various NLP applications , recent work has shown that automatic prediction of the degree of compositionality of MWEs also has utility, in applications including information retrieval ("IR": Acosta et al (2011)) and machine translation ("MT": Weller et al (2014), Carpuat and Diab (2010) and Venkatapathy and Joshi (2006)). For instance, Acosta et al (2011) showed that by considering non-compositional MWEs as a single unit, the effectiveness of document ranking in an IR system improves, and Carpuat and Diab (2010) showed that by adding compositionality scores to the Moses SMT system (Koehn et al, 2007), they could improve translation quality.…”

Section: Introductionmentioning

confidence: 99%

Proceedings of the 11th Workshop on Multiword Expressions

2015

View full text Add to dashboard Cite

The paper describes the results of an empirical study of integrating bigram collocations and similarities between them and unigrams into topic models. First of all, we propose a novel algorithm PLSA-SIM that is a modification of the original algorithm PLSA. It incorporates bigrams and maintains relationships between unigrams and bigrams based on their component structure. Then we analyze a variety of word association measures in order to integrate top-ranked bigrams into topic models. All experiments were conducted on four text collections of different domains and languages. The experiments distinguish a subgroup of tested measures that produce topranked bigrams, which demonstrate significant improvement of topic models quality for all collections, when integrated into PLSA-SIM algorithm.

show abstract

Using information about multi-word expressions for the word-alignment task

Cited by 15 publications

References 13 publications

Manawi: Using Multi-Word Expressions and Named Entities to Improve Machine Translation

Manawi: Using Multi-Word Expressions and Named Entities to Improve Machine Translation

Bilingual Multiword Expression Alignment by Constituent-Based Similarity Score

Proceedings of the 11th Workshop on Multiword Expressions

Contact Info

Product

Resources

About