The quality of statistical machine translation performed with phrase based approaches can be increased by permuting the words in the source sentences in an order which resembles that of the target language. We propose a class of recurrent neural models which exploit sourceside dependency syntax features to reorder the words into a target-like order. We evaluate these models on the Germanto-English language pair, showing significant improvements over a phrase-based Moses baseline, obtaining a quality similar or superior to that of hand-coded syntactical reordering rules.
Morphological segmentation is an effective strategy for addressing difficulties caused by morphological complexity. In this study, we use an English-to-Arabic test bed to determine what steps and components of a phrase-based statistical machine translation pipeline benefit the most from segmenting the target language. We test several scenarios that differ primarily in when desegmentation is applied, showing that the most important criterion for success in segmentation is to allow the system to build target words from morphemes that span phrase boundaries. We also investigate the impact of segmented and unsegmented target language models (LMs) on translation quality. We show that an unsegmented LM is helpful according to BLEU score, but also leads to a drop in the overall usage of compositional morphology, bringing it to well below the amount observed in human references.
We describe 2 improvements to ChineseEnglish PropBank predicate-argument structure alignment. Taking advantage of the recently expanded PropBank English nominal and adjective predicate annotation (Bonial et al., 2014), we performed predicateargument alignments between both verb and nominal/adjective predicates in Chinese and English. Using our alignment system, this increased the number of aligned predicateargument structures by 24.5% on the parallel Xinhua News corpus. We also improved the PropBank alignment system using expectation-maximization (EM) techniques. By collecting Chinese-English predicate-topredicate and argument type-to-argument type alignment probabilities and iteratively improving the alignment output using these probabilities on a large unannotated parallel corpora, we improved the predicate alignment performance by 1 F point when using all automatic SRL and word alignment inputs.
Accurate identification of phrasal translation equivalents is critical to both phrase-based and syntax-basedmachine translation systems. We show that the extraction of many phrasal translation equivalents is made impossible by word alignments done without taking syntactic structures into consideration. To address the problem, we propose a new annotation scheme where word alignment and the alignment of non-terminal nodes (i.e., phrases) are done simultaneously to avoid conflicts between word alignments and syntactic structures. Relying on this new alignment approach, we construct a Hierarchically Aligned Chinese-English Parallel Treebank (HACEPT), and show that all phrasal translation equivalents can be automatically extracted based on the phrase alignments in HACEPT.
This paper argues in favor of a linguisticallyinformed error classification for SMT to identify system weaknesses and map them to possible syntactic, semantic and structural fixes.We propose a scheme which includes both linguistic-oriented error categories as well as SMT-oriented edit errors, and evaluate an English-Spanish system and an English Basque system developed for a Q&A scenario in the IT domain.The classification, in our use-scenario, reveals great potential for fixes from lexical semantics techniques involving entity handling for IT-related names and user interface strings, word sense disambiguation for terminology, as well as argument structure for prepositions and syntactic parsing for various levels of reordering.
