In this paper we present a novel approach of utilizing Semantic Role Labeling (SRL) information to improve Hierarchical Phrase-based Machine translation. We propose an algorithm to extract SRL-aware Synchronous Contex...
ISBN:
(纸本)9781932432992
In this paper we present a novel approach of utilizing Semantic Role Labeling (SRL) information to improve Hierarchical Phrase-based Machine translation. We propose an algorithm to extract SRL-aware Synchronous Context-Free Grammar (SCFG) rules. Conventional Hiero-style SCFG rules will also be extracted in the same framework. Special conversion rules are applied to ensure that when SRL-aware SCFG rules are used in derivation, the decoder only generates hypotheses with complete semantic structures. We perform machine translation experiments using 9 different Chinese-English test-sets. Our approach achieved an average BLEU score improvement of 0.49 as well as 1.21 point reduction in TER.
We argue that failing to capture the degree of contribution of each semantic frame in a sentence explains puzzling results in recent work on the MEANT family of semantic MT evaluation metrics, which have disturbingly ...
ISBN:
(纸本)9781932432992
We argue that failing to capture the degree of contribution of each semantic frame in a sentence explains puzzling results in recent work on the MEANT family of semantic MT evaluation metrics, which have disturbingly indicated that dissociating semantic roles and fillers from their predicates actually improves correlation with human adequacy judgments even though, intuitively, properly segregating event frames should more accurately reflect the preservation of meaning. Our analysis finds that both properly structured and flattened representations fail to adequately account for the contribution of each semantic frame to the overall sentence. We then show that the correlation of HMEANT, the human variant of MEANT, can be greatly improved by introducing a simple length-based weighting scheme that approximates the degree of contribution of each semantic frame to the overall sentence. The new results also show that, without flattening the structure of semantic frames, weighting the degree of each frame's contribution gives HMEANT higher correlations than the previously best-performing flattened model, as well as HTER.
A key concern in building syntax-based machine translation systems is how to improve coverage by incorporating more traditional phrase-based SMT phrase pairs that do not correspond to syntactic constituents. At the sa...
详细信息
The empirical adequacy of synchronous context-free grammars of rank two (2-SCFGs) (Satta and Peserico, 2005), used in syntax-based machine translation systems such as Wu (1997), Zhang et al. (2006) and Chiang (2007), ...
详细信息
The proceedings contain 14 papers. The topics discussed include: chunk-level reordering of source language sentences with automatically learned rules for statistical machine translation;extraction phenomena in synchro...
The proceedings contain 14 papers. The topics discussed include: chunk-level reordering of source language sentences with automatically learned rules for statistical machine translation;extraction phenomena in synchronous TAG syntax and semantics;inversion transduction grammar for joint phrasal translation modeling;factorization of synchronous context-free grammars in linear time;binarization, synchronous binarization, and target-side binarization;machine translation as tree labeling;discriminative word alignment by learning the alignment structure and syntactic divergence between a language pair;generation in machine translation from deep syntactic trees;and combining morphosyntactic enriched representation with n-best reranking in statisticaltranslation.
作者：
Padó, SebastianBoleda, GemmaSALSA
Dept. of Computational Linguistics Saarland University Saarbrücken Germany GLiCom
Dept. of Translation and Interpreting Pompeu Fabra University Barcelona Spain
We present a data and error analysis for semantic role labelling. In a first experiment, we build a generic statistical model for semantic role assignment in the FrameNet paradigm and show that there is a high varianc...
详细信息
暂无评论