{"title":"Syntax-Based Translation With Bilingually Lexicalized Synchronous Tree Substitution Grammars","authors":"Jiajun Zhang, Feifei Zhai, Chengqing Zong","doi":"10.1109/TASL.2013.2255283","DOIUrl":null,"url":null,"abstract":"Syntax-based models can significantly improve the translation performance due to their grammatical modeling on one or both language side(s). However, the translation rules such as the non-lexical rule “ VP→(x0x1,VP:x1PP:x0)” in string-to-tree models do not consider any lexicalized information on the source or target side. The rule is so generalized that any subtree rooted at VP can substitute for the nonterminal VP:x1. Because rules containing nonterminals are frequently used when generating the target-side tree structures, there is a risk that rules of this type will potentially be severely misused in decoding due to a lack of lexicalization guidance. In this article, inspired by lexicalized PCFG, which is widely used in monolingual parsing, we propose to upgrade the STSG (synchronous tree substitution grammars)-based syntax translation model with bilingually lexicalized STSG. Using the string-to-tree translation model as a case study, we present generative and discriminative models to integrate lexicalized STSG into the translation model. Both small- and large-scale experiments on Chinese-to-English translation demonstrate that the proposed lexicalized STSG can provide superior rule selection in decoding and substantially improve the translation quality.","PeriodicalId":55014,"journal":{"name":"IEEE Transactions on Audio Speech and Language Processing","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2013-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/TASL.2013.2255283","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Audio Speech and Language Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TASL.2013.2255283","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 6
Abstract
Syntax-based models can significantly improve the translation performance due to their grammatical modeling on one or both language side(s). However, the translation rules such as the non-lexical rule “ VP→(x0x1,VP:x1PP:x0)” in string-to-tree models do not consider any lexicalized information on the source or target side. The rule is so generalized that any subtree rooted at VP can substitute for the nonterminal VP:x1. Because rules containing nonterminals are frequently used when generating the target-side tree structures, there is a risk that rules of this type will potentially be severely misused in decoding due to a lack of lexicalization guidance. In this article, inspired by lexicalized PCFG, which is widely used in monolingual parsing, we propose to upgrade the STSG (synchronous tree substitution grammars)-based syntax translation model with bilingually lexicalized STSG. Using the string-to-tree translation model as a case study, we present generative and discriminative models to integrate lexicalized STSG into the translation model. Both small- and large-scale experiments on Chinese-to-English translation demonstrate that the proposed lexicalized STSG can provide superior rule selection in decoding and substantially improve the translation quality.
基于语法的模型由于在语言的一方或双方进行语法建模,可以显著提高翻译性能。但是,字符串到树模型中的翻译规则(如非词法规则“VP→(x0x1,VP:x1PP:x0)”)不考虑源端或目标端的任何词法化信息。这个规则是如此的一般化,以至于任何根在VP的子树都可以代替非终结的VP:x1。由于在生成目标端树结构时经常使用包含非终结符的规则,因此由于缺乏词法化指导,这种类型的规则有可能在解码中被严重滥用。在本文中,受广泛应用于单语分析的词汇化PCFG的启发,我们提出将基于同步树替换语法的STSG (synchronous tree substitution grammar)语法翻译模型升级为双语词汇化的STSG。以字符串到树的翻译模型为例,我们提出了生成模型和判别模型,将词汇化的STSG整合到翻译模型中。汉英翻译的小尺度和大尺度实验均表明,词典化STSG在译码过程中提供了优越的规则选择,显著提高了翻译质量。
期刊介绍:
The IEEE Transactions on Audio, Speech and Language Processing covers the sciences, technologies and applications relating to the analysis, coding, enhancement, recognition and synthesis of audio, music, speech and language. In particular, audio processing also covers auditory modeling, acoustic modeling and source separation. Speech processing also covers speech production and perception, adaptation, lexical modeling and speaker recognition. Language processing also covers spoken language understanding, translation, summarization, mining, general language modeling, as well as spoken dialog systems.