Andraz Repar, V. Podpečan, Anze Vavpetic, N. Lavrač, Senja Pollak
{"title":"术语集成器:一种用于双语术语提取和对齐的集成学习方法","authors":"Andraz Repar, V. Podpečan, Anze Vavpetic, N. Lavrač, Senja Pollak","doi":"10.1075/TERM.00029.REP","DOIUrl":null,"url":null,"abstract":"Abstract This paper describes TermEnsembler, a bilingual term extraction and alignment system utilizing a novel ensemble learning approach to bilingual term alignment. In the proposed system, the processing starts with monolingual term extraction from a language industry standard file type containing aligned English and Slovenian texts. The two separate term lists are then automatically aligned using an ensemble of seven bilingual alignment methods, which are first executed separately and then merged using the weights learned with an evolutionary algorithm. In the experiments, the weights were learned on one domain and tested on two other domains. When evaluated on the top 400 aligned term pairs, the precision of term alignment is over 96%, while the number of correctly aligned multi-word unit terms exceeds 30% when evaluated on the top 400 term pairs.","PeriodicalId":44429,"journal":{"name":"Terminology","volume":null,"pages":null},"PeriodicalIF":0.9000,"publicationDate":"2019-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"10","resultStr":"{\"title\":\"TermEnsembler: An ensemble learning approach to bilingual term extraction and alignment\",\"authors\":\"Andraz Repar, V. Podpečan, Anze Vavpetic, N. Lavrač, Senja Pollak\",\"doi\":\"10.1075/TERM.00029.REP\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Abstract This paper describes TermEnsembler, a bilingual term extraction and alignment system utilizing a novel ensemble learning approach to bilingual term alignment. In the proposed system, the processing starts with monolingual term extraction from a language industry standard file type containing aligned English and Slovenian texts. The two separate term lists are then automatically aligned using an ensemble of seven bilingual alignment methods, which are first executed separately and then merged using the weights learned with an evolutionary algorithm. In the experiments, the weights were learned on one domain and tested on two other domains. When evaluated on the top 400 aligned term pairs, the precision of term alignment is over 96%, while the number of correctly aligned multi-word unit terms exceeds 30% when evaluated on the top 400 term pairs.\",\"PeriodicalId\":44429,\"journal\":{\"name\":\"Terminology\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.9000,\"publicationDate\":\"2019-07-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"10\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Terminology\",\"FirstCategoryId\":\"98\",\"ListUrlMain\":\"https://doi.org/10.1075/TERM.00029.REP\",\"RegionNum\":4,\"RegionCategory\":\"文学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"0\",\"JCRName\":\"LANGUAGE & LINGUISTICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Terminology","FirstCategoryId":"98","ListUrlMain":"https://doi.org/10.1075/TERM.00029.REP","RegionNum":4,"RegionCategory":"文学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"0","JCRName":"LANGUAGE & LINGUISTICS","Score":null,"Total":0}
TermEnsembler: An ensemble learning approach to bilingual term extraction and alignment
Abstract This paper describes TermEnsembler, a bilingual term extraction and alignment system utilizing a novel ensemble learning approach to bilingual term alignment. In the proposed system, the processing starts with monolingual term extraction from a language industry standard file type containing aligned English and Slovenian texts. The two separate term lists are then automatically aligned using an ensemble of seven bilingual alignment methods, which are first executed separately and then merged using the weights learned with an evolutionary algorithm. In the experiments, the weights were learned on one domain and tested on two other domains. When evaluated on the top 400 aligned term pairs, the precision of term alignment is over 96%, while the number of correctly aligned multi-word unit terms exceeds 30% when evaluated on the top 400 term pairs.
期刊介绍:
Terminology is an independent journal with a cross-cultural and cross-disciplinary scope. It focusses on the discussion of (systematic) solutions not only of language problems encountered in translation, but also, for example, of (monolingual) problems of ambiguity, reference and developments in multidisciplinary communication. Particular attention will be given to new and developing subject areas such as knowledge representation and transfer, information technology tools, expert systems and terminological databases. Terminology encompasses terminology both in general (theory and practice) and in specialized fields (LSP), such as physics.