A Discriminative Model for Semantics-to-String Translation
نویسندگان
چکیده
We present a feature-rich discriminative model for machine translation which uses an abstract semantic representation on the source side. We include our model as an additional feature in a phrase-based decoder and we show modest gains in BLEU score in an n-best re-ranking experiment.
منابع مشابه
Translation and Hybridity in Scenes and Frames Semantics
The present study is a theoretical attempt to illustrate how Fillmore's Scenes and Frames Semantics (SFS) could be employed as a framework to portray the process of understanding and translating hybrid texts. It first reviews the origin of SFS; then it maps SFS onto Nida’s linguistic model of translation process and the Interpretive Theory of Translation; it examines in the next section, withi...
متن کاملA Discriminative Syntactic Model for Source Permutation via Tree Transduction
A major challenge in statistical machine translation is mitigating the word order differences between source and target strings. While reordering and lexical translation choices are often conducted in tandem, source string permutation prior to translation is attractive for studying reordering using hierarchical and syntactic structure. This work contributes an approach for learning source strin...
متن کاملNon-Projective Parsing for Statistical Machine Translation
We describe a novel approach for syntaxbased statistical MT, which builds on a variant of tree adjoining grammar (TAG). Inspired by work in discriminative dependency parsing, the key idea in our approach is to allow highly flexible reordering operations during parsing, in combination with a discriminative model that can condition on rich features of the sourcelanguage string. Experiments on tra...
متن کاملRule Selection with Soft Syntactic Features for String-to-Tree Statistical Machine Translation
In syntax-based machine translation, rule selection is the task of choosing the correct target side of a translation rule among rules with the same source side. We define a discriminative rule selection model for systems that have syntactic annotation on the target language side (stringto-tree). This is a new and clean way to integrate soft source syntactic constraints into string-to-tree syste...
متن کاملDiscriminative Training and Variational Decoding in Machine Translation via Novel Algorithms for Weighted Hypergraphs
A hypergraph or “packed forest” is a compact data structure that uses structure-sharing to represent exponentially many trees in polynomial space. A probabilistic/weighted hypergraph also defines a probability (or other weight) for each tree, and can be used to represent the hypothesis space considered (for a given input) by a monolingual parser or a tree-based translation system (e.g., tree to...
متن کامل