In this paper, we address the problem of mining named entity translation such as names of persons, organizations, and locations, from non parallel corpora. First, our study concentrates of different forms of named entity translation. Then, we introduce a new framework to extract all named entity translation types from a non parallel corpus. The proposed framework combines surface and linguistic-based approaches. It is language independent and do not rely on any external parallel resources such as bilingual lexicons or parallel corpora. Evaluations show that our approach for mining named entity translations from a non parallel corpus is highly effective and consistently improves the translation quality of Arabic to French machine translation system.

Google Translate provides a multilingual machine-translation service by automatically translating one written language to another. Google translate is allegedly limited in its accuracy in translation, however. This study investigated the accuracy of Google Chinese-to-English translation from the perspectives of formality and cohesion with two comparisons: Google translation with human expert translation, and Google translation with Chinese source language. The text sample was a collection of 289 spoken and written texts excerpts from the Selected Works of Mao Zedong in both Chinese and English versions. Google translate was used to translate the Chinese texts into English. These texts were analyzed by the automated text analysis tools: the Chinese and English LIWC, and the Chinese and English Coh-Metrix. Results of Pearson correlations on formality and cohesion showed Google English translation was highly correlated with both human English translation and the original Chinese texts.

Cross-language learning allows us to use training data from one language to build models for a different language. Many approaches to bilingual learning require that we have word-level alignment of sentences from parallel corpora. In this work we explore the use of autoencoder-based methods for cross-language learning of vectorial word representations that are aligned between two languages, while not relying on word-level alignments. We show that by simply learning to reconstruct the bag-of-words representations of aligned sentences, within and between languages, we can in fact learn high-quality representations and do without word alignments. Since training autoencoders on word observations presents certain computational issues, we propose and compare different variations adapted to this setting. We also propose an explicit correlation maximizing regularizer that leads to significant improvement in the performance. We empirically investigate the success of our approach on the problem of cross-language test classification, where a classifier trained on a given language (e.g., English) must learn to generalize to a different language (e.g., German). These experiments demonstrate that our approaches are competitive with the state-of-the-art, achieving up to 10-14 percentage point improvements over the best reported results on this task.

This article presents a probabilistic sub-tree alignment model and its application to tree-to-tree machine translation. Unlike previous work, we do not resort to surface heuristics or expensive annotated data, but instead derive an unsupervised model to infer the syntactic correspondence between two languages. More importantly, the developed model is syntactically-motivated and does not rely on word alignments. As a by-product, our model outputs a sub-tree alignment matrix encoding a large number of diverse alignments between syntactic structures, from which machine translation systems can efficiently extract translation rules that are often filtered out due to the errors in 1-best alignment. Experimental results show that the proposed approach outperforms three state-of-the-art baseline approaches in both alignment accuracy and grammar quality. When applied to machine translation, our approach yields a +1.0 BLEU improvement and a -0.9 TER reduction on the NIST machine translation evaluation corpora. With tree binarization and fuzzy decoding, it even outperforms a state-of-the-art hierarchical phrase-based system.

Although, Chinese and Spanish are two of the most spoken languages in the world, not much research has been done in machine translation for this language pair. This paper focuses on investigating the state-of-the-art of Chinese-to-Spanish statistical machine translation (SMT), which nowadays is one of the most popular approaches to machine translation. We conduct experimental work with the largest of these three corpora to explore alternative SMT strategies by means of using a pivot language. Three alternatives are considered for pivoting: cascading, pseudo-corpus and triangulation. As pivot language, we use either English, Arabic or French. Results show that, for a phrase-based SMT system, English is the best pivot language between Chinese and Spanish. We propose a system output combination using the pivot strategies which is capable of outperforming the direct translation strategy. The main objective of this work is motivating and involving the research community to work in this important pair of languages given their demographic impact.

With the progress in machine translation, it becomes more subtle to develop the evaluation metric capturing the systems’ differences in comparison to the human translations. In contrast to the current efforts in leveraging more linguistic information to depict translation quality, this paper takes the thread of combining language independent features for a robust solution to MT evaluation metric. To compete with finer granularity of modeling brought by linguistic features, the proposed method augments the word level metrics by a letter based calculation. An empirical study is then conducted over WMT data to train the metrics by ranking SVM. The results reveal that the integration of current language independent metrics can generate well enough performance for a variety of languages. Time-split data validation is promising as a better training setting, though the greedy strategy also works well.

Lexical cohesion arises from a chain of lexical items that establish links between sentences in a text. In this paper we propose three different models to capture lexical cohesion for document-level machine translation: (a) a direct reward model where translation hypotheses are rewarded whenever lexical cohesion devices occur in them, (b) a conditional probability model where the appropriateness of using lexical cohesion devices is measured, and (c) a mutual information trigger model where a lexical cohesion relation is considered as a trigger pair and the strength of the association between the trigger and the triggered item is estimated by mutual information. We integrate the three models into hierarchical phrase-based machine translation and evaluate their effectiveness on the NIST Chinese-English translation tasks with large-scale training data. Experiment results show that all three models can achieve substantial improvements over the baseline and that the mutual information trigger model performs better than the others.

Post-editing feedback provided by users of on-line translation services offers an excellent opportunity for automatic improvement of statistical machine translation (SMT) systems. However, feedback provided by casual users is very noisy, and must be automatically filtered in order to identify the potentially useful cases. We present a study on automatic feedback filtering in a real weblog collected from Reverso.net. We extend and re-annotate a training corpus, define an extended set of simple features and approach the problem as a binary classification task, experimenting with linear and kernelbased classifiers and feature selection. Results on the feedback filtering task show a significant improvement over the majority class, but also a precision ceiling around 70-80%. This reflects the inherent difficulty of the problemand indicates that shallow features cannot fully capture the semantic nature of the problem. Despite the modest results on the filtering task, the classifiers are proven effective in an application-based evaluation. The incorporation of a filtered set of feedback instances selected from a larger corpus significantly improves the performance of a phrase-based SMT system, according to a set of standard evaluation metrics.

Coherence that ties sentences of a text into a meaningfully connected structure is of great importance to text generation and translation. In this paper, we propose a topic-based coherence model to produce coherence for document translation, in terms of the continuity of sentence topics in a text. We automatically extract a coherence chain for each source text to be translated. Based on the extracted source coherence chain, we adopt a maximum entropy classifier to predict the target coherence chain that defines a linear topic structure for the target document. The proposed topic-based coherence model then uses the predicted target coherence chain to help decoder select coherent word/phrase translations. Our experiments show that incorporating the topic-based coherence model into machine translation achieves substantial improvement over both the baseline and previous methods that integrate document topics rather than coherence chains into machine translation.

We will see more and more applications of AI on the mobile devices. This special issue of AI Magazine is devoted to some exemplary works of AI on mobile devices. We include four works that range from mobile activity recognition and air-quality detection to machine translation and image compression. These works were chosen from a variety of sources, including the International Joint Conference on Artificial Intelligence 2011 Special Track on Integrated and Embedded AI Systems, held in Barcelona, Spain, in July 2011.