The learning of probabilistic models with many hidden variables and nondecomposable dependencies is an important and challenging problem. In contrast to traditional approaches based on approximate inference in a single intractable model, our approach is to train a set of tractable submodels by encouraging them to agree on the hidden variables. This allows us to capture non-decomposable aspects of the data while still maintaining tractability. We propose an objective function for our approach, derive EMstyle algorithms for parameter estimation, and demonstrate their effectiveness on three challenging real-world learning tasks.

The learning of probabilistic models with many hidden variables and nondecomposable dependenciesis an important and challenging problem. In contrast to traditional approaches based on approximate inference in a single intractable model, our approach is to train a set of tractable submodels by encouraging them to agree on the hidden variables. This allows us to capture non-decomposable aspects of the data while still maintaining tractability. We propose an objective function for our approach, derive EMstyle algorithms for parameter estimation, and demonstrate their effectiveness on three challenging real-world learning tasks.

We present a novel paradigm for statistical machine translation (SMT), based on joint modeling of word alignment and the topical aspects underlying bilingual document pairs via a hidden Markov Bilingual Topic AdMixture (HM-BiTAM). In this new paradigm, parallel sentence-pairs from a parallel document-pair are coupled via a certain semantic-flow, to ensure coherence of topical context in the alignment of matching words between languages, during likelihood-based training of topic-dependent translational lexicons, as well as topic representations in each language. The resulting trained HM-BiTAM can not only display topic patterns like other methods such as LDA, but now for bilingual corpora; it also offers a principled way of inferring optimal translation in a context-dependent way. Our method integrates the conventional IBM Models based on HMM --- a key component for most of the state-of-the-art SMT systems, with the recently proposed BiTAM model, and we report an extensive empirical analysis (in many way complementary to the description-oriented of our method in three aspects: word alignment, bilingual topic representation, and translation.

The expectation maximization (EM) algorithm is a widely used maximum likelihood estimationprocedure for statistical models when the values of some of the variables in the model are not observed. Very often, however, our aim is primarily tofind a model that assigns values to the latent variables that have intended meaning for our data and maximizing expected likelihood only sometimes accomplishes this.Unfortunately, it is typically difficult to add even simple a-priori information about latent variables in graphical models without making the models overly complex or intractable. In this paper, we present an efficient, principled way to inject rich constraints on the posteriors of latent variables into the EM algorithm. Our method can be used to learn tractable graphical models that satisfy additional,otherwise intractable constraints. Focusing on clustering and the alignment problem for statistical machine translation, we show that simple, intuitive posteriorconstraints can greatly improve the performance over standard baselines and be competitive with more complex, intractable models.

This article focuses on Word Sense Disambiguation (WSD), which is a Natural Language Processing task that is thought to be important for many Language Technology applications, such as Information Retrieval, Information Extraction, or Machine Translation. One of the main issues preventing the deployment of WSD technology is the lack of training examples for Machine Learning systems, also known as the Knowledge Acquisition Bottleneck. A method which has been shown to work for small samples of words is the automatic acquisition of examples. We have previously shown that one of the most promising example acquisition methods scales up and produces a freely available database of 150 million examples from Web snippets for all polysemous nouns in WordNet. This paper focuses on the issues that arise when using those examples, all alone or in addition to manually tagged examples, to train a supervised WSD system for all nouns. The extensive evaluation on both lexical-sample and all-words Senseval benchmarks shows that we are able to improve over commonly used baselines and to achieve top-rank performance. The good use of the prior distributions from the senses proved to be a crucial factor.

Machine translation (MT) was one of the first applications of artificial intelligence technology that was deployed to solve real-world problems. In the late 1990s, Ford Vehicle Operations began working with Systran Software Inc. to adapt and customize its machine-translation technology in order to translate Ford's vehicle assembly build instructions from English to German, Spanish, Dutch, and Portuguese. The assembly build instructions at Ford contain text written in a controlled language as well as unstructured remarks and comments. The MT system has already translated more than 7 million instructions into these languages and is an integral part of the overall manufacturing process-planning system used to support Ford's assembly plants in Europe, Mexico and South America.

We are very pleased to republish here extended versions of a sample of the papers drawn from the Innovative Applications of Artificial Intelligence Conference (IAAI-06), which was held July 17-20, 2006, in Boston, Massachusetts. Three of these articles describe deployed applications and two describe emerging applications.

Machine translation (MT) was one of the first applications of artificial intelligence technology that was deployed to solve real-world problems. Since the early 1960s, researchers have been building and utilizing computer systems that can translate from one language to another without requiring extensive human intervention. In the late 1990s, Ford Vehicle Operations began working with Systran Software Inc. to adapt and customize its machine-translation technology in order to translate Ford's vehicle assembly build instructions from English to German, Spanish, Dutch, and Portuguese. The use of machine translation was made necessary by the vast amount of dynamic information that needed to be translated in a timely fashion. The assembly build instructions at Ford contain text written in a controlled language as well as unstructured remarks and comments. The MT system has already translated more than 7 million instructions into these languages and is an integral part of the overall manufacturing process-planning system used to support Ford's assembly plants in Europe, Mexico and South America. In this paper, we focus on how AI techniques, such as knowledge representation and natural language processing can improve the accuracy of machine translation in a dynamic environment such as auto manufacturing.

This paper evaluates the different tasks carried out in the translation of pronominal anaphora in a machine translation (MT) system. The MT interlingua approach named AGIR (Anaphora Generation with an Interlingua Representation) improves upon other proposals presented to date because it is able to translate intersentential anaphors, detect co-reference chains, and translate Spanish zero pronouns into English---issues hardly considered by other systems. The paper presents the resolution and evaluation of these anaphora problems in AGIR with the use of different kinds of knowledge (lexical, morphological, syntactic, and semantic). The translation of English and Spanish anaphoric third-person personal pronouns (including Spanish zero pronouns) into the target language has been evaluated on unrestricted corpora. We have obtained a precision of 80.4% and 84.8% in the translation of Spanish and English pronouns, respectively. Although we have only studied the Spanish and English languages, our approach can be easily extended to other languages such as Portuguese, Italian, or Japanese.

MITAP (MITRE text and audio processing) is a prototype system available for monitoring infectious disease outbreaks and other global events. MITAP focuses on providing timely, multilingual, global information access to medical experts and individuals involved in humanitarian assistance and relief work. Multiple information sources in multiple languages are automatically captured, filtered, translated, summarized, and categorized by disease, region, information source, person, and organization. Critical information is automatically extracted and tagged to facilitate browsing, searching, and sorting. The system supports shared situational awareness through collaboration, allowing users to submit other articles for processing, annotate existing documents, post directly to the system, and flag messages for others to see. MITAP currently stores over 1 million articles and processes an additional 2,000 to 10,000 daily, delivering up-to-date information to dozens of regular users.