In 2007 we presented a paper that described the application of Natural Language Processing (NLP) and Machine Translation (MT) for the automated translation of process build instructions from English to other languages to support Ford’s assembly plants in non-English speaking countries. This project has continued to evolve with the addition of new languages and improvements to the translation process. However, we discovered that there was a large demand for automated language translation across all of Ford Motor Company and we decided to expand the scope of our project to address these requirements. This paper will describe our efforts to meet all of Ford’s internal translation requirements with AI and MT technology and focus on the challenges and lessons that we learned from applying advanced technology across an entire corporation.

We describe an approach for multi-engine machine translation that uses machine learning methods to train one or several classifiers for a given set of candidate translations. Contrary to existing approaches in quality estimation which only consider a single translation at a time, we explicitly model pairwise comparison with our feature vectors. We discuss several challenges our method is facing and discuss how lifelong machine learning could be applied to resolve these. We also show how the proposed architecture can be extended to allow human feedback to be included into the training process, improving the system's selection process over time.

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. For this purpose, we report details of the available parallel corpus which are Basic Traveller Expressions Corpus (Btec), Holy Bible and United Nations (Un). Additionally, 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.

The performance of a Statistical Machine Translation System (SMT) system is proportionally directed to the quality and length of the parallel corpus it uses. However for some pair of languages there is a considerable lack of them. The long term goal is to construct a Japanese-Spanish parallel corpus to be used for SMT, whereas, there are a lack of useful Japanese-Spanish parallel Corpus. To address this problem, In this study we proposed a method for extracting Japanese-Spanish Parallel Sentences from Wikipedia using POS tagging and Rule-Based approach. The main focus of this approach is the syntactic features of both languages. Human evaluation was performed over a sample and shows promising results, in comparison with the baseline.

In 2007 we presented a paper that described the application of Natural Language Processing (NLP) and Machine Translation (MT) for the automated translation of process build instructions from English to other languages to support Ford’s assembly plants in non-English speaking countries. This project has continued to evolve with the addition of new languages and improvements to the translation process. However, we discovered that there was a large demand for automated language translation across all of Ford Motor Company and we decided to expand the scope of our project to address these requirements. This paper will describe our efforts to meet all of Ford’s internal translation requirements with AI and MT technology and focus on the challenges and lessons that we learned from applying advanced technology across an entire corporation.

We believe that the Doodling game benefits from a familiar metaphor, Crowdsourcing has been shown to be an effective paradigm real-time human social interactions, the potential for both for solving problems that are computationally players to rapidly improve their language skills, and above hard and for those requiring extensive data creation and all, the possibility of being fun. Because there are many labeling (Callison-Burch and Dredze 2010, Ambati and language pairs for which there is no strong financial incentive Vogel 2010, Zaidan and Callison-Burch 2011). Such a for developing language technologies, we believe engaging model holds key advantages for language data generation the online population in volume and on a volunteer over the traditional approaches (i.e., using existing parallel basis may be the only way to gather the necessary data. We corpora or a small set of expert translators) because of the note that the Duolingo system (Duolingo 2011) is in a promise of attracting a wide online audience, with immense similar vein, as it is also designed towards collecting parallel demographic diversity in terms of languages and language data from the crowd.

Research over the past years has shown that machine translation results can be greatly enhanced with the help of mono- or bilingual human contributors, e.g. by asking hu- mans to proofread or correct outputs of machine translation systems. However, it remains difficult to determine the quality of individual revisions. This paper proposes a meth- od to determine the quality of individual contributions by analyzing task-independent data. Examples of such data are completion time, number of keystrokes, etc. An initial evaluation showed promising F-measure values larger than 0.8 for support vector machine and decision tree based classifications of a combined test set of Vietnamese and German translations.

This paper describes a statistical approach to generation of Chinese classical poetry and proposes a novel method to automatically evaluate poems. The system accepts a set of keywords representing the writing intents from a writer and generates sentences one by one to form a completed poem. A statistical machine translation (SMT) system is applied to generate new sentences, given the sentences generated previously. For each line of sentence a specific model specially trained for that line is used, as opposed to using a single model for all sentences. To enhance the coherence of sentences on every line, a coherence model using mutual information is applied to select candidates with better consistency with previous sentences. In addition, we demonstrate the effectiveness of the BLEU metric for evaluation with a novel method of generating diverse references.

This article is the first report in the best of AI in Japan series. This series will focus on the prominent accomplishments made in the AI field, not only the research and development but also the AI-related events in society. As the first in the forthcoming series, this opening article features a historical background and the contemporary AI-research activities in Japan. It then highlights some recent prominent results from the industry. Finally, a future perspective is given.

We propose a novel language-independent approach for improving machine translation for resource-poor languages by exploiting their similarity to resource-rich ones. More precisely, we improve the translation from a resource-poor source language X_1 into a resource-rich language Y given a bi-text containing a limited number of parallel sentences for X_1-Y and a larger bi-text for X_2-Y for some resource-rich language X_2 that is closely related to X_1. This is achieved by taking advantage of the opportunities that vocabulary overlap and similarities between the languages X_1 and X_2 in spelling, word order, and syntax offer: (1) we improve the word alignments for the resource-poor language, (2) we further augment it with additional translation options, and (3) we take care of potential spelling differences through appropriate transliteration. The evaluation for Indonesian- >English using Malay and for Spanish -> English using Portuguese and pretending Spanish is resource-poor shows an absolute gain of up to 1.35 and 3.37 BLEU points, respectively, which is an improvement over the best rivaling approaches, while using much less additional data. Overall, our method cuts the amount of necessary "real'' training data by a factor of 2--5.