The proceedings contain 18 papers. The topics discussed include: vector space models for phrase-based machine translation;bilingual Markov reordering labels for hierarchical SMT;better semantic frame based MT evaluati...
ISBN:
(纸本)9781937284961
The proceedings contain 18 papers. The topics discussed include: vector space models for phrase-based machine translation;bilingual Markov reordering labels for hierarchical SMT;better semantic frame based MT evaluation via inversion transduction grammars;rule-based syntactic preprocessing for syntax-based machine translation;applying HMEANT to English-Russian translations;reducing the impact of data sparsity in statistical machine translation;expanding the language model in a low-resource hybrid MT system;syntax and semantics in quality estimation of machine translation;and overcoming the curse of sentence length for neural machine translation using automatic segmentation.
The proceedings contain 12 papers. The topics discussed include: improving Chinese-English PropBank alignment;harmonizing word alignments and syntactic structures for extracting phrasal translation equivalents;non-pro...
ISBN:
(纸本)9781941643419
The proceedings contain 12 papers. The topics discussed include: improving Chinese-English PropBank alignment;harmonizing word alignments and syntactic structures for extracting phrasal translation equivalents;non-projective dependency-based pre-reordering with recurrent neural network for machine translation;translating negation: induction, search and model errors;unsupervised false friend disambiguation using contextual word clusters and parallel word alignments;analyzing English-Spanish named-entity enhanced machine translation;and translation reranking using source phrase dependency features.
The proceedings contain 15 papers. The topics discussed include: automatic projection of semantic structures: an application to pairwise translation ranking;structured vs. flat semantic role representations for machin...
ISBN:
(纸本)9781932432992
The proceedings contain 15 papers. The topics discussed include: automatic projection of semantic structures: an application to pairwise translation ranking;structured vs. flat semantic role representations for machine translation evaluation;semantic mapping using automatic word alignment and semantic role labeling;incorporating source-language paraphrases into phrase-based SMT with confusion networks;multi-word unit dependency forest-based translation rule extraction;an evaluation and possible improvement path for current SMT behavior on ambiguous nouns;and improving reordering for statistical machine translation with smoothed priors and syntactic features.
The proceedings contain 8 papers. The topics discussed include: a semantic evaluation of machine translation lexical choice;taste of two different flavors: which Manipuri script works better for English-Manipuri langu...
ISBN:
(纸本)9781937284473
The proceedings contain 8 papers. The topics discussed include: a semantic evaluation of machine translation lexical choice;taste of two different flavors: which Manipuri script works better for English-Manipuri language pair SMT systems?;hierarchical alignment decomposition labels for hiero grammar rules;a performance study of cube pruning for large-scale hierarchical machine translation;combining word reordering methods on different linguistic abstraction levels for statistical machine translation;a formal characterization of parsing word alignments by synchronous grammars with empirical evidence to the ITG hypothesis;and synchronous linear context-free rewriting systems for machine translation.
The proceedings contain 13 papers. The topics discussed include: WSD for n-best reranking and local language modeling in SMT;linguistically enriched models for Bulgarian-to-English machine translation;enriching parall...
ISBN:
(纸本)9781937284381
The proceedings contain 13 papers. The topics discussed include: WSD for n-best reranking and local language modeling in SMT;linguistically enriched models for Bulgarian-to-English machine translation;enriching parallel corpora for statistical machine translation with semantic negation rephrasing;towards a predicate-argument evaluation for MT;using parallel features in parsing of machine-translated sentences for correction of grammatical errors;unsupervised vs. supervised weight estimation for semantic MT evaluation metrics;head finalization reordering for Chinese-to-Japanese machine translation;and extracting semantic transfer rules from parallel corpora with SMT phrase aligners.
We describe a N-best reranking model based on features that combine source-side dependency syntactical information and segmentation and alignment information. Specifically, we consider segmentation-aware"phrase d...
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...
详细信息
Several preprocessing techniques using syntactic information and linguistically motivated rules have been proposed to improve the quality of phrase-based machine translation (PBMT) output. On the other hand, there has...
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.
Distributed vector representations of words are useful in various NLP tasks. We briefly review the CBOW approach and propose a bilingual application of this architecture with the aim to improve consistency and coheren...
详细信息
暂无评论