Articles

We define noun phrase translation as a subtask of machine translation. This en- ables us to build a dedicated noun phrase translation subsystem that improves over the currently best general statistical ma- chine translation methods by incorporat- ing special modeling and special features. We achieved 65.5% translation accuracy in a …...

This paper describes an alternative trans- lation model based on a text chunk un- der the framework of statistical machine translation. The translation model sug- gested here first performs chunking. Then, each word in a chunk is translated. Fi- nally, translated chunks are reordered. Under this scenario of translation model- …...

It is well known that occurrence counts of words in documents are often mod- eled poorly by standard distributions like the binomial or Poisson. Observed counts vary more than simple models predict, prompting the use of overdispersed mod- els like Gamma-Poisson or Beta-binomial mixtures as robust alternatives. Another deficiency of …...

This paper presents a method for unsu- pervised discovery of semantic patterns. Semantic patterns are useful for a vari- ety of text understanding tasks, in par- ticular for locating events in text for in- formation extraction. The method builds upon previously described approaches to iterative unsupervised pattern acquisition. One common …...

This paper presents a Chinese word segmen- tation system that uses improved source- channel models of Chinese sentence genera- tion. Chinese words are defined as one of the following four types: lexicon words, mor- phologically derived words, factoids, and named entities. Our system provides a unified approach to the four …...

We present a language-independent and unsupervised algorithm for the segmenta- tion of words into morphs. The algorithm is based on a new generative probabilis- tic model, which makes use of relevant prior information on the length and fre- quency distributions of morphs in a lan- guage. Our algorithm is shown …...

Pipelined Natural Language Generation (NLG) systems have grown increasingly complex as architectural modules were added to support language functionali- ties such as referring expressions, lexical choice, and revision. This has given rise to discussions about the relative placement of these new modules in the overall archi- tecture. Recent work on …...

We address appropriate user modeling in order to generate cooperative responses to each user in spoken dialogue systems. Un- like previous studies that focus on user’s knowledge or typical kinds of users, the user model we propose is more compre- hensive. Specifically, we set up three di- mensions of user …...

� This� paper� discusses� the� challenges� and� pro- poses� a� solution� to� performing� information� re- trieval�on�the�Web�using�Chinese�natural�language� speech� query.� The� main� contribution� of� this� re- search�is�in�devising�a�divide-and-conquer�strategy� to� alleviate� the� speech� recognition� errors.� It� uses� the�query�model�to�facilitate�the�extraction�of�main� core�semantic�string�(CSS)�from�the�Chinese�natu- ral�language�speech�query.�It�then�breaks�the�CSS� into� basic� components� corresponding� to� phrases,� and� uses� a� multi-tier� strategy� to� map� the� …...

This paper presents a method to de- velop a class of variable memory Markov models that have higher memory capac- ity than traditional (uniform memory) Markov models. The structure of the vari- able memory models is induced from a manually annotated corpus through a de- cision tree learning algorithm. A …...

This paper concerns the discourse under- standing process in spoken dialogue sys- tems. This process enables the system to understand user utterances based on the context of a dialogue. Since multiple can- didates for the understanding result can be obtained for a user utterance due to the ambiguity of speech …...

Several approaches have been described for the automatic unsupervised acquisi- tion of patterns for information extraction. Each approach is based on a particular model for the patterns to be acquired, such as a predicate-argument structure or a de- pendency chain. The effect of these al- ternative models has not been …...

In this paper, we present a learning ap- proach to the scenario template task of information extraction, where information filling one template could come from mul- tiple sentences. When tested on the MUC- 4 task, our learning approach achieves accuracy competitive to the best of the MUC-4 systems, which were …...

This paper presents a new bottom-up chart parsing algorithm for Prolog along with a compilation procedure that reduces the amount of copying at run-time to a con- stant number (2) per edge. It has ap- plications to unification-based grammars with very large partially ordered cate- gories, in which copying is …...

Link detection has been regarded as a core technology for the Topic Detection and Tracking tasks of new event detection. In this paper we formulate story link detec- tion and new event detection as informa- tion retrieval task and hypothesize on the impact of precision and recall on both sys- …...

In this paper we propose a competition learning approach to coreference resolu- tion. Traditionally, supervised machine learning approaches adopt the single- candidate model. Nevertheless the prefer- ence relationship between the antecedent candidates cannot be determined accu- rately in this model. By contrast, our ap- proach adopts a twin-candidate learning model. …...

We apply a decision tree based approach to pronoun resolution in spoken dialogue. Our system deals with pronouns with NP- and non-NP-antecedents. We present a set of features designed for pronoun resolu- tion in spoken dialogue and determine the most promising features. We evaluate the system on twenty Switchboard dialogues …...

Often, the training procedure for statisti- cal machine translation models is based on maximum likelihood or related criteria. A general problem of this approach is that there is only a loose relation to the final translation quality on unseen text. In this paper, we analyze various training criteria which directly …...

Truecasing is the process of restoring case information to badly-cased or non- cased text. This paper explores truecas- ing issues and proposes a statistical, lan- guage modeling based truecaser which achieves an accuracy of ∼98% on news articles. Task based evaluation shows a 26% F-measure improvement in named entity recognition …...

Standard IR systems can process queries such as “web NOT internet”, enabling users who are interested in arachnids to avoid documents about computing. The docu- ments retrieved for such a query should be irrelevant to the negated query term. Most systems implement this by reprocessing re- sults after retrieval to …...