Modeling Complement Types in Phrase-Based SMT

Proceedings of the First Conference on Machine Translation, Volume 1: Research Papers, pages 43–53, Berlin, Germany, August 11-12, 2016. c⃝2016 Association for Computational Linguistics Modeling Complement Types in Phrase-Based SMT Marion Weller-Di Marco1,2, Alexander Fraser2, Sabine Schulte im Walde1 1Institut f¨ur Maschinelle Sprachverarbeitung, Universit¨at Stuttgart 2Centrum f¨ur Informations- und Sprachverarbeitung, Ludwig-Maximilians-Universit¨at M¨unchen {dimarco|schulte}@ims.uni-stuttgart.de fraser@cis.lmu.de Abstract We explore two approaches to model com- plement types (NPs and PPs) in an English- to-German SMT system: A simple abstract representation inserts pseudo-prepositions that mark the beginning of noun phrases, to improve the symmetry of source and tar- get complement types, and to provide a flat structural information on phrase bound- aries. An extension of this representation generates context-aware synthetic phrase- table entries conditioned on the source side, to model complement types in terms of grammatical case and preposition choice. Both the simple preposition-informed sys- tem and the context-aware system signifi- cantly improve over the baseline; and the context-aware system is slightly better than the system without context information. 1 Introduction SMT output is often incomprehensible because it confuses complement types (noun phrases/NPs vs. prepositional phrases/PPs) by generating a wrong grammatical case, by choosing an incorrect prepo- sition, or by arranging the complements in a mean- ingless way. However, the choice of complement types in a translation represents important infor- mation at the syntax-semantics interface: The case of an NP determines its syntactic function and its semantic role; similarly, the choice of preposition in a PP sets the semantic role of the prepositional phrase. While the lexical content of a target-language phrase is defined by the source sentence, the exact choice of preposition and case strongly depends on the target context, and most specifically on the target verb. For example, the English verb phrase to call for sth. can be translated into German by etw. erfordern (subcategorizing a direct-object NP but no preposition) or by (nach) etw. verlangen (subcat- egorizing either a direct-object NP or a PP headed by the preposition nach). Differences in grammat- ical case and syntactic functions between source and target side include phenomena like subject- object shifting: [I]SUBJ like [the book]OBJ vs. [das Buch]SUBJ gef¨allt [mir]OBJ. Here, the English ob- ject corresponds to a German subject, whereas the English subject corresponds to the indirect object in the German sentence. Selecting the wrong complement type or an in- correct preposition obviously has a major effect on the fluency of SMT output, and also has a strong im- pact on the perception of semantic roles. Consider the sentence John looks for his book. When the preposition for is translated literally by the prepo- sition f¨ur, the meaning of the translated sentence John sucht f¨ur sein Buch shifts, such that the book is no longer the object that is searched, but rather a recipient of the search. To preserve the source meaning, the prepositional phrase headed by for must be translated as a direct object of the verb suchen, or as a PP headed by the preposition nach. Since prepositions tend to be …

Content truncated to 500 words