Articles

Error-correcting output codes (ECOC) have emerged in machine learning as a success- ful implementation of the idea of distributed classes. Monadic class symbols are replaced by bit strings, which are learned by an ensem- ble of binary-valued classifiers (dichotomizers). In this study, the idea of ECOC is applied to memory-based …...

We present a novel approach to the problem of overfitting in the training of stochastic mod- els for selecting parses generated by attribute- valued grammars. In this approach, statistical features are merged according to the frequency of linguistic elements within the features. The resulting models are more general than the …...

Article choice can pose difficult problems in ap- plications such as machine translation and auto- mated summarization. In this paper, we investi- gate the use of corpus data to collect statistical generalizations about article use in English in order to be able to generate articles automati- cally to supplement a …...

I describe two methods for incorporating infor- mation about the relative positions of bilingual word pairs into a Maximum Entropy/Minimum Divergence translation model. The better of the two achieves over 40% lower test corpus perplex- ity than an equivalent combination of a trigram language model and the classical IBM transla- …...

This paper describes a set of comparative exper- iments, including cross-corpus evaluation, be- tween five alternative algorithms for supervised Word Sense Disambiguation (WSD), namely Naive Bayes, Exemplar-based learning, SNOW, Decision Lists, and Boosting. Two main conclu- sions can be drawn: 1) The LazyBoosting algo- rithm outperforms the other four state-of-the- …...

This paper describes algorithms and software developed to characterise and detect generic intelligent language-like features in an input signal, using natural language learning tech- niques: looking for characteristic statistical "language-signatures" in test corpora. As a first step towards such species-independent language-detection, we present a suite of pro- grams to analyse …...

The prevailing dual-route model of oral read- ing claims that a lexical route is used for the pronunciation of words and a non-lexical route processes nonwords. Neurological data from pa- tients with acquired dyslexias have been high- lighted to support this claim. Models using a lexicon alone are generally held …...

This article summarizes work on developing a learning theory account for the major learning and statistics based approaches used in natural language processing. It shows that these ap- proaches can all be explained using a single dis- tribution free inductive principle related to the pac model of learning. Furthermore, they …...

Broad-coverage grammars tend to be highly am- biguous. When such grammars are used in a restricted domain, it may be desirable to spe- cialize them, in effect trading some coverage for a reduction in ambiguity. Grammar specializa- tion is here given a novel formulation as an opti- mization problem, in …...

Computer learner corpora have been widely used by SLA/EFL specialists since mid 1990s to gain better insights into authentic learner language. The work presented in this paper examines the inter-language of Taiwanese learners of English from a part-of-speech sequence perspective. Two pre-tagged corpora (one learner corpus and one native corpus) …...

A new effective log-based approach for interactive Web search is presented in this paper. The most important feature of the proposed approach is that the suggested terms corresponding to the user’s query are extracted from similar query sessions, rather than from the contents of the retrieved documents. The experiment results …...

This paper introduces a Chinese summarizier called ThemePicker. Though the system incorporates both statistical and text analysis models, the statistical model plays a major role during the automated process. In addition to word segmentation and proper names identification, phrasal chunk extraction and content density calculation are based on a semantic …...

Usually, there are various non-alphabet symbols (“/”, “:”, “-”, etc.) occurring in Mandarin texts. Such symbols may be pronounced more than one oral expression with respect to its sense category. In our previous works, we proposed the multi-layer decision classifier to disambiguate the sense category of non-alphabet symbols; the elementary …...

Due to grammatical similarities, even a one-to-one mapping between Korean and Japanese words (or morphemes) can usually result in a high quality Korean-to-Japanese machine translation. However, multi-word translation units (MWTU) such as idioms, compound words, etc., need an n-to-m mapping, and their component words often do not appear adjacently, resulting …...

In this paper, parsing-as-deduction and constraint pro- gramming are brought together to outline a procedure for the specification of constraint-based chart parsers. Fol- lowing the proposal in Shieber et al. (1995), we show how to directly realize the inference rules for deductive parsers as Constraint Handling Rules (Fr¨uhwirth, 1998) by …...

The goal of text categorization is to classify documents into a certain number of pre- defined categories. The previous works in this area have used a large number of labeled training documents for supervised learning. One problem is that it is difficult to create the labeled training documents. While it …...

In Japanese, case structure analysis is very im- portant to handle several troublesome charac- teristics of Japanese such as scrambling, omis- sion of case components, and disappearance of case markers. However, for lack of a wide- coverage case frame dictionary, it has been dif- ficult to perform case structure analysis …...

This paper describes a hybrid parsing method for Japanese which uses both a hand-crafted gram- mar and a statistical technique. The key feature of our system is that in order to estimate likeli- hood for a parse tree, the system uses informa- tion taken from alternative partial parse trees gen- …...

Srinivas (97) enriches traditional morpho-syntactic POS tagging with syntactic information by introducing Supertags. Unfortunately, words are assigned on average a much higher number of Supertags than traditional POS. In this paper, we develop the notion of Hypertag, first introduced in Kinyon (00a) and in Kinyon (00b), which allows to factor …...

Automatic transliteration problem is to transcribe foreign words in one’s own alphabet. Machine generated transliteration can be useful in various applications such as indexing in an information retrieval system and pronunciation synthesis in a text-to-speech system. In this paper we present a model for statistical English- to-Korean transliteration that generates …...