Bilingual terminology extraction using multi‐level termhood

Abstract

Purpose -Terminology is the set of technical words or expressions used in specific contexts, which denotes the core concept in a formal discipline and is usually applied in the fields of machine translation, information retrieval, information extraction and text categorization, etc. Bilingual terminology extraction plays an important role in the application of bilingual dictionary compilation, bilingual ontology construction, machine translation and cross-language information retrieval etc. This paper aims to address the issues of monolingual terminology extraction and bilingual term alignment based on multi-level termhood. Design/methodology/approach -A method based on multi-level termhood is proposed. The new method computes the termhood of the terminology candidate as well as the sentence that includes the terminology by the comparison of the corpus. Since terminologies and general words usually have different distribution in the corpus, termhood can also be used to constrain and enhance the performance of term alignment when aligning bilingual terms on the parallel corpus. In this paper, bilingual term alignment based on termhood constraints is presented. Findings -Experimental results show multi-level termhood can get better performance than the existing method for terminology extraction. If termhood is used as a constraining factor, the performance of bilingual term alignment can be improved. Originality/value -The termhood of the candidate terminology and the sentence that includes the terminology is used for terminology extraction, which is called multi-level termhood. Multi-level termhood is computed by the comparison of the corpus. Bilingual term alignment method based on termhood constraint is put forward and termhood is used in the task of bilingual terminology extraction. Experimental results show that termhood constraints can improve the performance of terminology alignment to some extent.

Bilingual lexical extraction based on word alignment for improving corpus search

“…Some of these approaches rely on the existence of a seed lexicon (Semmar, 2018; Tsvetkov and Wintner, 2010; Xu et al , 2015) or existing translation memories and phrase tables (Oliver, 2017), while in some cases the existence of additional resources, in addition to the input corpus, is not required (Arcan et al , 2017; Bouamor et al , 2012; Garabík and Dimitrova, 2015; Naguib, 2016). Some approaches require parallel sentence-aligned data (Arcan et al , 2017; Bouamor et al , 2012; Garabík and Dimitrova, 2015; Semmar, 2018; Zhang and Wu, 2012), while others perform the extraction on comparable corpora (Hazem and Morin, 2016; Pinnis et al , 2012; Xu et al , 2015). The technique employed in Naguib (2016), used groups of aligned sentences (verses).…”

“…In Irvine and Callison-Burch (2016), the authors performed two experiments, the first one relying on the existence of a bilingual dictionary with no parallel texts and the second one requiring only the existence of a small amount of parallel data. Bilingual lexica were compiled for different language pairs: English/French (Bouamor et al , 2012; Hakami and Bollegala, 2017; Semmar, 2018), English/Spanish (Oliver, 2017), English/Arabic (Naguib, 2016), English/Italian and English/German (Arcan et al , 2017), English/Slovene (Vintar and Fišer, 2008), English/Croatian, Latvian, Lithuanian and Romanian (Pinnis et al , 2012), English/Chinese (Xu et al , 2015; Zhang and Wu, 2012), English/Hebrew (Tsvetkov and Wintner, 2010), English/Italian (Arcan et al , 2017), Slovak/Bulgarian (Garabík and Dimitrova, 2015), Serbian/English (Krstev et al , 2018) and so on.…”

Semi-automatic extraction of multiword terms from domain-specific corpora

“…It is used for lexicon creation, acquisition of novel terms, text classification, text indexing, machine-assisted translation and other NLP tasks. Different approaches to MWT extraction, linguistics- or statistics-based (or both), have already been published recently (Cram and Daille, 2016; Sclano and Velardi, 2007; Verberne et al , 2016; Vivaldi and Rodríguez, 2007; Yin et al , 2016; Zhang and Wu, 2012). Most of the methods used for MWT extraction today are hybrid; that is, they usually integrate statistical information, such as frequencies of n-grams and collocations, with linguistic information, such as syntactic patterns of expressions.…”