Articles

This paper describes a method of automatic sense disambiguation for target word selection in Korean to English machine translation. At first, we define the concept of cluster for each sense of given verb according to corresponding target word. And then, we propose a method which selects the sense combination of …...

This paper shows how to induce an N-best translation lexicon from a bilingual text corpus using statistical properties of the corpus together with four external knowledge sources. The knowledge sources are cast as filters, so that any subset of them can be cascaded in a uniform framework. A new objective …...

We propose a novel context heterogeneity similarity measure between words and their translations in helping to compile bilingual lexicon entries from a non-parallel English-Chinese corpus. Current algorithms for bilingual lexicon compilation rely on occurrence frequencies, length or positional statistics derived from parallel texts. There is little correlation between such statistics …...

Previous work on automated dictionary construction for information extraction has relied on annotated text corpora. However, annotating a corpus is time-consuming and difficult. We propose that conceptual patterns for information extraction can be acquired automatically using only a preclassified training corpus and no text annotations. We describe a system called …...

Resea/ch based on a treebank is active for many natural language applications. However, the work to build a large scale treebank is laborious and tedious. This paper proposes a probabilistic chunker to help the development of a partially bracketed corpus. The chunker partitions the part-of-speech sequence into segments called chunks. …...

In this paper, an unsupervised approach for constructing a large-scale Chinese electronic dictionary is surveyed. The main purpose is to enable cheap and quick acquisition of a large-scale dictionary from a large untagged text corpus with the aid of the information in a small tagged seed corpus. The basic model …...

This paper presents a preliminary experiment in automatically suggesting significant terms for a predefined topic. The general method is to compare a topically focused sample created around the predefined topic with a larger and more general base sample. A set of statistical measures are used to identify significant word units …...

It is not possible to model semantics of natural language unless one can clearly establish the structure of contextual information and how "context" guides the construction of semantic identities of linguistic units. We claim that this cannot be done unless one can overcome the representational locality imposed by extensional formalisms. …...

Without properly constraining recursions in generation, no language system can effectively operate. This is especially so with morphological generation, for each well-formed word must be finite in length and is ac- cepted as such only when it actually occurs in text or ordinary usage. This difficulty is compounded when a …...

This paper describes a method of evaluating quality for developers of machine translation systems to easily check imperfections in their own systems. This evaluation method is a systematic, objective method along with test example sets in which we clarified the evaluation procedure by adding yes/no questions and explanations to the …...

We shall show how to treat shared belief revision and reference management in the process of dialogues by distinguishing three types of discourse referents: (standard) discourse referents, shared discourse referents, and the shared belief referent, using an extended version of Discourse Representa- tion Theory, called Hyper-DRS, which can represent shared …...

The techniques of image processing have been used in optical character recognition (OCR) for a long time. The recognition method evolved from early "pattern recognition" to "feature extraction" recently. The recognition rate is raised from 70% to 90%. But the character by character recognition technique has its limitation. Using language …...

Many researches found lexical preferences to be critical in resolving attachment ambiguity [WFB 90][FBK 82][ MP 80]. Most notably, information from Verb-Obj-Prep-Noun structures (VOPN) has been used to show that LA is very effective in the resolution of PP- attachment ambiguity [HR 93]. We investigated extensions to the lexical association …...

In this paper, we describe an algorithm for aligning words with their translation in a bilingual corpus. Existing algorithms require enormous bilingual data to train statistical word-to-word translation models. Using word-based approach, frequent words with consistent translation can be aligned at a high precision rate. However, less frequent words or …...

This paper presents a method to apply Hidden Markov Model (HMM) to parameter learning for Japanese morphological analyzer. We especially emphasize how the following two information sources affect the results of the parameter learning: 1) The initial value of parameters, i.e., the initial probabilities and 2) some grammatical constraints that …...

Experiences in computing alignments at the paragraph and sentence level within a project TRANSLEARN in the European Union's "LRE" programme of research and development in language engineering are reported. About 98% of the sentences in pairs of corpora in different languages have been aligned correctly by a method that uses …...

We propose a method to improve search time and space complexity in statistical machine translation architectures, by employing linguistic bracketing information on the source language sentence. It is one of the advantages of the probabilistic formulation that competing translations may be compared and ranked by a principled measure, but at …...

<Systeme Emile> is a French learning software program using network. This paper presents its implemented prototype version, Emile 1.1. It is based on the client/server model connected by a dial-up modem. The data structure, the tutoring tools and the user interface of Emile 1.1 are described in this paper. It …...

In conversation, adverbial clause subordination is most commonly achieved through temporal, conditional, concessive, and causal conjunctions, such as dang (` when'), ruguoCin, suiran (`although'), yinwei (` because'), etc. in Mandarin Chinese. This study aims at exploring adverbial clauses in spoken Mandarin conversations on the basis of quantitative analysis. There were …...

This paper investigates some of the distributional properties of word definitions in a machine- readable dictionary which • was obtained from the Oxford Text Archive. Three types of dis- tributions were examined: (1) frequency-ranked distribution of words in the definitions, (2) the length distribution of word definitions and (3) the …...