FromTo/JK is a Japanese-to-Korean machine translation system based on direct translation approach due to the syntactic similarity between Japanese and Korean. To resolve the target word ambiguity, transfer uses collocation information of nouns and postpositions, and case frame information of verb. It is evaluated with existing MT systems and shows the best performance.

The paper discusses a new knowledgebased and sublanguage-oriented model for anaphora resolution, which integrates syntactic, semantic, discourse, domain and heuristical knowledge for the sublanguage of computer science. Special attention is paid to a new approach for tracking the center throughout a discourse segment, which plays an imtx~rtant role in proposing the most likely antecedent to the...

Question Answering research has long recognised that the identification of the type of answer being requested is a fundamental step in the interpretation of a question as a whole. Previous strategies have ranged from trivial keyword matches, to statistical analyses, to well-defined algorithms based on shallow syntactic parses with userinteraction for ambiguity resolution. A novel strategy combi...

This study aims to present an accessible model of some frequent nonfinite adverbial types occurring in English prose fiction. As its main syntactic argument, it recognizes that these adverbials are mostly elliptical in that there are some dependent-clause markers one can assume to be implicit when supplying those elements back into the clause complex. Some comments are provided at the end on th...

We propose a system for analyzing texts written in languages which don't make use of punctuation, with syntactic tagging in mind. The core system is a simple chart parser, but to cope with the complexity and ambiguity problems, we use simpliied nite-state automata, which guide the analysis. An application to Ancient Egyptian texts is introduced.

We focus on syntactic aspects of di¤erential awareness that give rise to contractual disputes. Boundedly rational parties use a common language, but do not share a common understanding of the world, leading to ambiguity in both syntactic and semantic forms. In contractual relationships, ambiguity leads to disagreement and disputes. We show that the agents may prefer simpler less ambiguous contr...

of seven types of structural ambiguity. In addition, it ap~ ~ ~ ~ f i ~ ~ t ~ have shown that prosody is used by human ]ispeared that the relative size and location of prosodic phrase teners to disambiguate spoken language and, in particular, that boundaries provided the principal prosodic clue for resolvthe relative size and location of prosodic phrase boundaries proing ambiguities. Thus, it s...

We present evidence that, for English, ambiguity is an active factor in the choice of relativization strategy and that, in speech, prosody plays a role in resolution of ambiguity over the internal role of the relativized constituent. The evidence is based on (semi-)automatic analysis and comparison of automatically-parsed written and spoken portions of the British National Corpus (BNC, Leech, 1...

Trees with labeled edges have widespread applicability, for example for the representation of dependency syntax trees. Given a fixed number of nodes and constraints on how edges may be drawn between them, the task of finding solution trees is known as a configuration problem. In this paper, we formalize the configuration problem of labeled trees and argue that it can be regarded as a constraint...

Unsupervised part-of-speech induction involves the discovery of syntactic categories in a text, given no additional information other than the text itself. One requirement of an induction system is the ability to handle multiple categories for each word, in order to deal with word sense ambiguity. We construct an algorithm for unsupervised part-of-speech induction, treating the problem as one o...