Extending CCG-based Syntactic Constraints in Hierarchical Phrase-Based SMT
نویسندگان
چکیده
In this paper, we describe two approaches to extending syntactic constraints in the Hierarchical Phrase-Based (HPB) Statistical Machine Translation (SMT) model using Combinatory Categorial Grammar (CCG). These extensions target the limitations of previous syntax-augmented HPB SMT systems which limit the coverage of the syntactic constraints applied. We present experiments on Arabic–English and Chinese–English translation. Our experiments show that using extended CCG labels helps to increase nonterminal label coverage and achieve significant improvements over the baseline for Arabic– English translation. In addition, combining extended CCG labels with CCGaugmented glue grammar helps to improve the performance of the Chinese–English translation over the baseline systems.
منابع مشابه
CCG Contextual Labels in Hierarchical Phrase-Based SMT
In this paper, we present a method to employ target-side syntactic contextual information in a Hierarchical Phrase-Based system. Our method uses Combinatory Categorial Grammar (CCG) to annotate training data with labels that represent the left and right syntactic context of target-side phrases. These labels are then used to assign labels to nonterminals in hierarchical rules. CCG-based contextu...
متن کاملSupertags as Source Language Context in Hierarchical Phrase-Based SMT
Statistical machine translation (SMT) models have recently begun to include source context modeling, under the assumption that the proper lexical choice of the translation for an ambiguous word can be determined from the context in which it appears. Various types of lexical and syntactic features have been explored as effective source context to improve phrase selection in SMT. In the present w...
متن کاملLexical Syntax for Statistical Machine Translation
Statistical Machine Translation (SMT) is by far the most dominant paradigm of Machine Translation. This can be justified by many reasons, such as accuracy, scalability, computational efficiency and fast adaptation to new languages and domains. However, current approaches of Phrase-based SMT lacks the capabilities of producing more grammatical translations and handling long-range reordering whil...
متن کاملA CCG-based Quality Estimation Metric for Statistical Machine Translation
We describe a metric for estimating the quality of Statistical Machine Translation (SMT) output based on syntactic features extracted using Combinatory Categorial Grammar (CCG). CCG has been demonstrated to be better suited to deal with SMT texts than context free phrase structure grammar formalisms. We use CCG features to estimate the grammaticality of the translations by dividing them into ma...
متن کاملPractical Approach to Syntax-based Statistical Machine Translation
This paper presents a practical approach to statistical machine translation (SMT) based on syntactic transfer. Conventionally, phrase-based SMT generates an output sentence by combining phrase (multiword sequence) translation and phrase reordering without syntax. On the other hand, SMT based on tree-to-tree mapping, which involves syntactic information, is theoretical, so its features remain un...
متن کامل