Abstract | In this paper, we propose a sense-based translation model to integrate word senses into statistical machine translation . |
Abstract | Our method is significantly different from preVious word sense disambiguation reformulated for machine translation in that the latter neglects word senses in nature. |
Conclusion | We have presented a sense-based translation model that integrates word senses into machine translation . |
Conclusion | 0 Word senses automatically induced by the HDP-based WSI on large-scale training data are very useful for machine translation . |
Experiments | This suggests that automatically induced word senses alone are indeed useful for machine translation . |
Introduction | In the context of machine translation , such different meanings normally produce different target translations. |
Introduction | Therefore a natural assumption is that word sense disambiguation (WSD) may contribute to statistical machine translation (SMT) by providing appropriate word senses for target translation selection with context features (Carpuat and Wu, 2005). |
Introduction | 'or Statistical Machine Translation |
Related Work | Xiong and Zhang (2013) employ a sentence-level topic model to capture coherence for document-level machine translation . |
Related Work | The difference between our work and these preVious studies on topic model for SMT lies in that we adopt topic-based WSI to obtain word senses rather than generic topics and integrate induced word senses into machine translation . |
WSI-Based Broad-Coverage Sense Tagger | We want to extend this hypothesis to machine translation by building sense-based translation model upon the HDP-based word sense induction: words with the same meanings tend to be translated in the same way. |
Abstract | We present a hybrid approach to sentence simplification which combines deep semantics and monolingual machine translation to derive simple sentences from complex ones. |
Introduction | It is useful as a preprocessing step for a variety of NLP systems such as parsers and machine translation systems (Chandrasekar et al., 1996), sum-marisation (Knight and Marcu, 2000), sentence fusion (Filippova and Strube, 2008) and semantic |
Introduction | Machine Translation systems have been adapted to translate complex sentences into $nqfleones(ZhuetaL,2010;VVubbenetaL,2012; Coster and Kauchak, 2011). |
Introduction | First, it combines a model encoding probabilities for splitting and deletion with a monolingual machine translation module which handles reordering and substitution. |
Related Work | (2010) constructed a parallel corpus (PWKP) of 108,016/114,924 comple)dsimple sentences by aligning sentences from EWKP and SWKP and used the resulting bitext to train a simplification model inspired by syntax-based machine translation (Yamada and Knight, 2001). |
Related Work | To account for deletions, reordering and substitution, Coster and Kauchak (2011) trained a phrase based machine translation system on the PWKP corpus while modifying the word alignment output by GIZA++ in Moses to allow for null phrasal alignments. |
Related Work | (2012) use Moses and the PWKP data to train a phrase based machine translation system augmented with a post-hoc reranking procedure designed to rank the output based on their dissimilarity from the source. |
Simplification Framework | We also depart from Coster and Kauchak (2011) who rely on null phrasal alignments for deletion during phrase based machine translation . |
Simplification Framework | Second, the simplified sentence(s) s’ is further simplified to s using a phrase based machine translation system (PBMT+LM). |
Simplification Framework | where the probabilities p(s’ |DC), p(s’ |s) and 19(3) are given by the DRS simplification model, the phrase based machine translation model and the language model respectively. |
Abstract | Topic models, an unsupervised technique for inferring translation domains improve machine translation quality. |
Experiments | We evaluate our new topic model, ptLDA, and existing topic models—LDA, pLDA, and tLDA—on their ability to induce domains for machine translation and the resulting performance of the translations on standard machine translation metrics. |
Introduction | In particular, we use topic models to aid statistical machine translation (Koehn, 2009, SMT). |
Introduction | Modern machine translation systems use millions of examples of translations to learn translation rules. |
Introduction | As we review in Section 2, topic models are a promising solution for automatically discovering domains in machine translation corpora. |
Polylingual Tree-based Topic Models | We compare these models’ machine translation performance in Section 5. |
Topic Models for Machine Translation | 2.1 Statistical Machine Translation |
Topic Models for Machine Translation | Statistical machine translation casts machine translation as a probabilistic process (Koehn, 2009). |
Topic Models for Machine Translation | (2012) ignore a wealth of information that could improve topic models and help machine translation . |
Introduction | As machine translation enters the workflow of professional translators, the exact nature of this human-computer interaction is currently an open challenge. |
Introduction | Instead of tasking translators to post-edit the output of machine translation systems, a more interactive approach may be more fruitful. |
Introduction | The standard approach to this problem uses the search graph of the machine translation system. |
Properties of Core Algorithm | We predict translations that were crafted by manual post-editing of machine translation output. |
Properties of Core Algorithm | We also use the search graphs of the system that produced the original machine translation output. |
Properties of Core Algorithm | In the project’s first field trialz, professional translators corrected machine translations of news stories from a competitive English—Spanish machine translation system (Koehn and Haddow, 2012). |
Refinements | Analysis of the data suggests that gains mainly come from large length mismatches between user translation and machine translation , even in the case of first pass searches. |
Refinements | For instance, if the user prefix differs only in casing from the machine translation (say, University instead of university), then we may still want to treat that as a word match in our algorithm. |
Related Work | The interactive machine translation paradigm was first explored in the TransType and TransType2 projects (Langlais et al., 2000a; Foster et al., 2002; Bender et al., 2005; Barrachina et al., 2009). |
Word Completion | When the machine translation system decides for college over university, but the user types the letter u, it should change its prediction. |
Abstract | Instead of using a parallel corpus which should have entity/relation alignment information and is thus difficult to obtain, this paper employs an off-the-shelf machine translator to translate both labeled and unlabeled instances from one language into the other language, forming pseudo parallel corpora. |
Abstract | Based on a small number of labeled instances and a large number of unlabeled instances in both languages, our method differs from theirs in that we adopt a bilingual active learning paradigm via machine translation and improve the performance for both languages simultaneously. |
Abstract | machine translation , which make use of multilingual corpora to decrease human annotation efforts by selecting highly informative sentences for a newly added language in multilingual parallel corpora. |
Abstract | We present experiments in using discourse structure for improving machine translation evaluation. |
Abstract | Then, we show that these measures can help improve a number of existing machine translation evaluation metrics both at the segment- and at the system-level. |
Experimental Results | In this section, we explore how discourse information can be used to improve machine translation evaluation metrics. |
Experimental Results | Overall, from the experimental results in this section, we can conclude that discourse structure is an important information source to be taken into account in the automatic evaluation of machine translation output. |
Introduction | From its foundations, Statistical Machine Translation (SMT) had two defining characteristics: first, translation was modeled as a generative process at the sentence-level. |
Introduction | This is demonstrated by the establishment of a recent workshop dedicated to Discourse in Machine Translation (Webber et al., 2013), collocated with the 2013 annual meeting of the Association of Computational Linguistics. |
Introduction | The area of discourse analysis for SMT is still nascent and, to the best of our knowledge, no previous research has attempted to use rhetorical structure for SMT or machine translation evaluation. |
Related Work | Addressing discourse-level phenomena in machine translation is relatively new as a research direction. |
Related Work | The field of automatic evaluation metrics for MT is very active, and new metrics are continuously being proposed, especially in the context of the evaluation campaigns that run as part of the Workshops on Statistical Machine Translation (WMT 2008-2012), and NIST Metrics for Machine Translation Challenge (MetricsMATR), among others. |
Abstract | Crowdsourcing is a viable mechanism for creating training data for machine translation . |
Conclusion | In addition to its benefits of cost and scalability, crowdsourcing provides access to languages that currently fall outside the scope of statistical machine translation research. |
Evaluation | art machine translation system (the syntax-based variant of Joshua) achieves a score of 26.91, which is reported in (Zaidan and Callison-Burch, 2011). |
Introduction | Statistical machine translation (SMT) systems are trained using bilingual sentence-aligned parallel corpora. |
Related work | These have focused on an iterative collaboration between monolingual speakers of the two languages, facilitated with a machine translation system. |
Related work | In our setup the poor translations are produced by bilingual individuals who are weak in the target language, and in their experiments the translations are the output of a machine translation system.1 Another significant difference is that the HCI studies assume cooperative participants. |
Related work | 1A variety of HC1 and NLP studies have confirmed the efficacy of monolingual or bilingual individuals post-editing of machine translation output (Callison-Burch, 2005; Koehn, 2010; Green et al., 2013). |
Abstract | Data selection has been demonstrated to be an effective approach to addressing the lack of high-quality bitext for statistical machine translation in the domain of interest. |
Conclusion | our methods into domain adaptation task of statistical machine translation in model level. |
Experiments | We use the NiuTrans 2 toolkit which adopts GIZA++ (Och and Ney, 2003) and MERT (Och, 2003) to train and tune the machine translation system. |
Experiments | This tool scores the outputs in several criterions, while the case-insensitive BLEU-4 (Papineni et al., 2002) is used as the evaluation for the machine translation system. |
Experiments | When top 600k sentence pairs are picked out from general-domain corpus to train machine translation systems, the systems perform higher than the General-domain baseline trained on 16 million parallel data. |
Introduction | Statistical machine translation depends heavily on large scale parallel corpora. |
Introduction | However, domain-specific machine translation has few parallel corpora for translation model training in the domain of interest. |
Training Data Selection Methods | Translation model is a key component in statistical machine translation . |
Abstract | However, in most current statistical machine translation (SMT) systems, the outputs of compound-complex sentences still lack proper transitional expressions. |
Conclusion | of machine translation . |
Experiments | 5 http://www.speech.sri.com/projects/srilm/ 6 The China Workshop on Machine Translation |
Introduction | During the last decade, great progress has been made on statistical machine translation (SMT) models. |
Related Work | In (Xiong et al., 2013a), three different features were designed to capture the lexical cohesion for document-level machine translation . |
Related Work | (Xiong et al., 2013b) incorporated lexical-chain-based models (Morris and Hirst, 1991) into machine translation . |
Related Work | (Meyer and Popescu-Belis, 2012) used sense-labeled discourse connectives for machine translation from English to French. |
Abstract | Neural network language models are often trained by optimizing likelihood, but we would prefer to optimize for a task specific metric, such as BLEU in machine translation . |
Abstract | Our best results improve a phrase-based statistical machine translation system trained on WMT 2012 French-English data by up to 2.0 BLEU, and the expected BLEU objective improves over a cross-entropy trained model by up to 0.6 BLEU in a single reference setup. |
Introduction | Neural network-based language and translation models have achieved impressive accuracy improvements on statistical machine translation tasks (Allauzen et al., 2011; Le et al., 2012b; Schwenk et al., 2012; Vaswani et al., 2013; Gao et al., 2014). |
Introduction | In this paper we focus on recurrent neural network architectures which have recently advanced the state of the art in language modeling (Mikolov et al., 2010; Mikolov et al., 2011; Sundermeyer et al., 2013) with several subsequent applications in machine translation (Auli et al., 2013; Kalchbrenner and Blunsom, 2013; Hu et al., 2014). |
Introduction | In practice, neural network models for machine translation are usually trained by maximizing the likelihood of the training data, either via a cross-entropy objective (Mikolov et al., 2010; Schwenk |
Corpora | While the corpus is aimed at machine translation tasks, we use the keywords associated with each talk to build a subsidiary corpus for multilingual document classification as follows.3 |
Experiments | A similar idea exists in machine translation where English is frequently used to pivot between other languages (Cohn and Lapata, 2007). |
Experiments | MT System We develop a machine translation baseline as follows. |
Experiments | We train a machine translation tool on the parallel training data, using the development data of each language pair to optimize the translation system. |
Related Work | Is was demonstrated that this approach can be applied to improve tasks related to machine translation . |
Related Work | (2013), also learned bilingual embeddings for machine translation . |
Abstract | In this paper we study the use of sentence-level dialect identification in optimizing machine translation system selection when translating mixed dialect input. |
Abstract | We test our approach on Arabic, a prototypical diglossic language; and we optimize the combination of four different machine translation systems. |
Introduction | For statistical machine translation (MT), which relies on the existence of parallel data, translating from nonstandard dialects is a challenge. |
Machine Translation Experiments | We use the open-source Moses toolkit (Koehn et al., 2007) to build four Arabic-English phrase-based statistical machine translation systems (SMT). |
Related Work | Arabic Dialect Machine Translation . |
Related Work | System Selection and Combination in Machine Translation . |
Knowledge Graph Construction | 0 Machine Translation - We script the Google translation API to get even more semantic links. |
Knowledge Graph Construction | In total, machine translation provides 53.2% of the total links and establishes connections between 3.5 million vertices. |
Related Work | The ready availability of machine translation to and from English has prompted efforts to employ translation for sentiment analysis (Bautin et al., 2008). |
Related Work | (2008) demonstrate that machine translation can perform quite well when extending the subjectivity analysis to multilingual environment, which makes it inspiring to replicate their work on lexicon-based sentiment analysis. |
Related Work | (2013) combine machine translation and word representation to generate bilingual language resources. |
Data preparation | This is done using the scripts provided by the Statistical Machine Translation system Moses (Koehn et al., 2007). |
Evaluation | In addition to these, the system’s output can be compared against the L2 reference translation(s) using established Machine Translation evaluation metrics. |
Introduction | Whereas machine translation generally concerns the translation of whole sentences or texts from one language to the other, this study focusses on the translation of native language (henceforth L1) words and phrases, i.e. |
Introduction | the role of the translation model in Statistical Machine Translation (SMT). |
System | It has also been used in machine translation studies in which local source context is used to classify source phrases into target phrases, rather than looking them up in a phrase table (Stroppa et al., 2007; Haque et al., 2011). |
Abstract | Unsupervised word segmentation (UWS) can provide domain-adaptive segmentation for statistical machine translation (SMT) without annotated data, and bilingual UWS can even optimize segmentation for alignment. |
Complexity Analysis | The first bilingual corpus: OpenMT06 was used in the NIST open machine translation 2006 Evaluation 2. |
Complexity Analysis | PatentMT9 is from the shared task of NTCIR-9 patent machine translation . |
Complexity Analysis | For the bilingual tasks, the publicly available system of Moses (Koehn et al., 2007) with default settings is employed to perform machine translation , and BLEU (Papineni et al., 2002) was used to evaluate the quality. |
Introduction | For example, in machine translation , there are various parallel corpora such as |
Abstract | Automated methods for identifying whether sentences are grammatical have various potential applications (e.g., machine translation , automated essay scoring, computer-assisted language learning). |
Introduction | Such a system could be used, for example, to check or to rank outputs from systems for text summarization, natural language generation, or machine translation . |
Introduction | While some applications (e.g., grammar checking) rely on such fine-grained predictions, others might be better addressed by sentence-level grammaticality judgments (e. g., machine translation evaluation). |
Introduction | ity of machine translation outputs (Gamon et al., 2005; Parton et al., 2011), such as the MT Quality Estimation Shared Tasks (Bojar et al., 2013, §6), but relatively little on evaluating the grammaticality of naturally occurring text. |
Introduction | Initially, these models were primarily used to create n-gram neural network language models (NNLMs) for speech recognition and machine translation (Bengio et al., 2003; Schwenk, 2010). |
Introduction | Unlike previous approaches to joint modeling (Le et al., 2012), our feature can be easily integrated into any statistical machine translation (SMT) decoder, which leads to substantially larger improvements than k-best rescoring only. |
Model Variations | We have described a novel formulation for a neural network-based machine translation joint model, along with several simple variations of this model. |
Model Variations | One of the biggest goals of this work is to quell any remaining doubts about the utility of neural networks in machine translation . |
Abstract | We propose a novel learning approach for statistical machine translation (SMT) that allows to extract supervision signals for structured learning from an extrinsic response to a translation input. |
Introduction | In this paper, we propose a novel approach for learning and evaluation in statistical machine translation (SMT) that borrows ideas from response-based learning for grounded semantic parsing. |
Introduction | We suggest that in a similar way the preservation of meaning in machine translation should be defined in the context of an interaction in an extrinsic task. |
Related Work | Interactive scenarios have been used for evaluation purposes of translation systems for nearly 50 years, especially using human reading comprehension testing (Pfafflin, 1965; Fuji, 1999; Jones et al., 2005), and more recently, using face-to-face conversation mediated via machine translation (Sakamoto et al., 2013). |
Introduction | Automatic word alignment is an important task for statistical machine translation . |
Related Work | Recently, FFNNs have been applied successfully to several tasks, such as speech recognition (Dahl et al., 2012), statistical machine translation (Le et al., 2012; Vaswani et al., 2013), and other popular natural language processing tasks (Collobert and Weston, 2008; Collobert et al., 2011). |
Training | 5.4 Machine Translation Results |
Training | Our experiments have shown that the proposed model outperforms the FFNN-based model (Yang et al., 2013) for word alignment and machine translation , and that the agreement constraint improves alignment performance. |
Abstract | This study investigates on building a better Chinese word segmentation model for statistical machine translation . |
Abstract | The experiments on a Chinese-to-English machine translation task reveal that the proposed model can bring positive segmentation effects to translation quality. |
Introduction | The empirical works show that word segmentation can be beneficial to Chinese-to-English statistical machine translation (SMT) (Xu et al., 2005; Chang et al., 2008; Zhao et al., 2013). |
Abstract | In this paper, we report our preliminary efforts in building an English-Turkish parallel treebank corpus for statistical machine translation . |
Introduction | For example, EuroParl corpus (Koehn, 2002), one of the biggest parallel corpora in statistical machine translation , contains 22 languages (but not Turkish). |
Introduction | In this study, we report our preliminary efforts in constructing an English-Turkish parallel treebank corpus for statistical machine translation . |
Abstract | We present an adaptive translation quality estimation (QE) method to predict the human-targeted translation error rate (HTER) for a document-specific machine translation model. |
Introduction | Machine translation (MT) systems suffer from an inconsistent and unstable translation quality. |
Related Work | There has been a long history of study in confidence estimation of machine translation . |
Abstract | Statistical Machine Translation (SMT) usually utilizes contextual information to disambiguate translation candidates. |
Experiments | We evaluate the performance of our neural network based topic similarity model on a Chinese-to-English machine translation task. |
Introduction | Making translation decisions is a difficult task in many Statistical Machine Translation (SMT) systems. |
Abstract | In statistical machine translation (SMT), syntax-based pre-ordering of the source language is an effective method for dealing with language pairs where there are great differences in their respective word orders. |
Introduction | This is especially important on the point of the system combination of PBSMT systems, because the diversity of outputs from machine translation systems is important for system combination (Cer et al., 2013). |
Introduction | By using both our rules and Wang et al.’s rules, one can obtain diverse machine translation results because the pre-ordering results of these two rule sets are generally different. |