Articles

Many acoustic approaches to prosodic la- beling in English have employed only lo- cal classifiers, although text-based classifi- cation has employed some sequential mod- els. In this paper we employ linear chain and factorial conditional random fields (CRFs) in conjunction with rich, contextually-based prosodic features, to exploit sequential de- pendencies …...

Language understanding (LU) modules for spoken dialogue systems in the early phases of their development need to be (i) easy to construct and (ii) robust against vari- ous expressions. Conventional methods of LU are not suitable for new domains, be- cause they take a great deal of effort to make …...

Automatic estimation of word significance oriented for speech-based Information Re- trieval (IR) is addressed. Since the sig- nificance of words differs in IR, automatic speech recognition (ASR) performance has been evaluated based on weighted word er- ror rate (WWER), which gives a weight on errors from the viewpoint of IR, …...

To relax the Term Independence Assump- tion, Term Dependency is introduced and it has improved retrieval precision dramati- cally. There are two kinds of term depend- encies, one is defined by term proximity, and the other is defined by linguistic de- pendencies. In this paper, we take a com- parative …...

As the amount of information created by human beings is explosively grown in the last decade, it is getting extremely harder to obtain necessary information by conven- tional information access methods. Hence, creation of drastically new technology is needed. For developing such new technol- ogy, search engine infrastructures are re- …...

In Cross Language Information Retrieval (CLIR), query terms can be translated to the document language using Bilingual Dictionaries (BDs) or Statistical Transla- tion Models (STMs). Combining different translation resources can also be used to improve the performance. Unfortunately, the most studies on combining multiple re- sources use simple methods such …...

The web is growing at a rapid speed and it is almost impossible for a web crawler to download all new pages. Pages reporting breaking news should be stored into search engine index as soon as they are published, while others whose content is not time-related can be left for …...

With the popularity of the Internet at a phe- nomenal rate, an ever-increasing number of documents in languages other than English are available in the Internet. Cross lan- guage text categorization has attracted more and more attention for the organization of these heterogeneous document collections. In this paper, we focus …...

We describe a graph-based approach to Sce- nario Template Creation, which is the task of creating a representation of multiple re- lated events, such as reports of different hur- ricane incidents. We argue that context is valuable to identify important, semantically similar text spans from which template slots could be …...

This paper presents a strategy to generate ge- neric summary of documents using Probabilistic Latent Semantic Indexing. Generally a docu- ment contains several topics rather than a single one. Summaries created by human beings tend to cover several topics to give the readers an overall idea about the original document. …...

In this paper we propose a new approach based on Sequence Segmentation Models (SSM) to the extractive document summa- rization, in which summarizing is regarded as a segment labeling problem. Comparing with the previous work, the difference of our approach is that the employed features are obtained not only from …...

In this paper we explore the benefits from and shortcomings of entity-driven noun phrase rewriting for multi-document sum- marization of news. The approach leads to 20% to 50% different content in the sum- mary in comparison to an extractive sum- mary produced using the same underlying approach, showing the promise …...

Document clustering and classification is usually done by representing the documents using a bag of words scheme. This scheme ignores many of the linguistic and semantic features contained in text documents. We propose here an alternative representation for documents using Lexical Chains. We compare the performance of the new repre- …...

Most research related to unithood were con- ducted as part of a larger effort for the deter- mination of termhood. Consequently, nov- elties are rare in this small sub-field of term extraction. In addition, existing work were mostly empirically motivated and derived. We propose a new probabilistically-derived measure, independent of …...

The automatic compilation of bilingual dic- tionaries from comparable corpora has been successful for single-word terms (SWTs), but remains disappointing for multi-word terms (MWTs). One of the main problems is the insufficient coverage of the bilingual dic- tionary. Using the compositional translation method improved the results, but still shows some …...

We describe clustering experiments for cross-document coreference for the first Web People Search Evaluation. In our ex- periments we apply agglomerative cluster- ing to group together documents potentially referring to the same individual. The algo- rithm is informed by the results of two dif- ferent summarization strategies and an off- …...

This paper presents an effective dependency parsing approach of incorporating short de- pendency information from unlabeled data. The unlabeled data is automatically parsed by a deterministic dependency parser, which can provide relatively high performance for short dependencies between words. We then train another parser which uses the informa- tion on …...

A pair of sentences in different newspaper articles on an event can have one of sev- eral relations. Of these, we have focused on two, i.e., equivalence and transition. Equiv- alence is the relation between two sentences that have the same information on an event. Transition is the relation between …...

Transliteration is the process of transcribing words from a source script to a target script. These words can be content words or proper nouns. They may be of local or foreign ori- gin. In this paper we present a more dis- cerning method which applies different tech- niques based on …...

Name origin recognition is to identify the source language of a personal or location name. Some early work used either rule- based or statistical methods with single knowledge source. In this paper, we cast the name origin recognition as a multi-class classification problem and approach the problem using Maximum Entropy …...