Tradução automática estatística baseada em sintaxe e linguagens de árvores

Abstract

Machine Translation (MT) is one of the classic Natural Language Processing (NLP) applications. The state-of-the-art in MT is represented by statistical methods that aim to learn all necessary linguistic knowledge automatically through large collections of texts (corpora). However, while the quality of statistical MT systems had improved, nowadays these advances are not significant. For this reason, research in the area have sought to involve more explicit linguistic knowledge in these systems. One issue that purely statistical MT systems have is the lack of correct treatment of syntactic phenomena. Thus, one of the research directions when trying to incorporate linguistic knowledge in those systems is through the addition of syntactic rules. To accomplish this, many methods and formalisms with this goal in mind are studied. This text presents the investigation of methods which aim to advance the state-of-the-art in statistical MT through models that consider syntactic information. The methods and formalisms studied are those used to deal with tree languages, mainly Tree Substitution Grammars (TSGs) and Tree-to-String (TTS) Transducers. From this work, a greater understanding was obtained about the studied formalisms and their behavior when used in NLP applications.