Articles

This paper describes measures for evaluating the three determinants of how well a probabilistic elas- sifter performs on a given test set. These determi- nants are the appropriateness, for the test set, of the results of (1)feature selection, (2) formulation of the parametric form of the model, and (3) pa- …...

This paper describes an experimental compari- son of seven different learning algorithms on the problem of learning to disambiguate the meaning of a word from context. The algorithms tested include statistical, neural-network, decision-tree, rule-based, and case-based classification tech- niques. The specific problem tested involves dis- ambiguating six senses of the …...

This paper investigates model merging, a tech- nique for deriving Markov models from text or speech corpora. Models are derived by starting with a large and specific model and by successi- vely combining states to build smaller and more general models. We present methods to reduce the time complexity of …...

In language modeling for speech recognition the goal is to constrain the search of the speech recognizer by providing a model which can, given a context, indicate what the next most likely word will be. In this paper, we explore how the addition of information to the text, in particular …...

We describe an implemented system for robust domain-independent syntactic parsing of English, using a unification-based grammar of part-of- speech and punctuation labels coupled with a probabilistic LR parser. We present evaluations of the system's performance along several differ- ent dimensions; these enable us to assess the con- tribution that each …...

We describe a novel parsing strategy we are employing for Chinese. We believe progress in Chinese parsing technology has been slowed by the excessive ambiguity that typically arises in pure context-free grammars. This problem has inspired a modified formalism that enhances our ability to write and main- tain robust large …...

The first step in most corpus-based mul- tilingual NLP work is to construct a de- tailed map of the correspondence between a text and its translation. Several auto- matic methods for this task have been pro- posed in recent years. "Yet even the best of these methods can err by …...

We present a novel new word extraction method from Japanese texts based on expected word frequencies. First, we compute expected word frequencies from Japanese texts using a robust stochastic N-best word segmenter. We then ex- tract new words by filtering out erroneous word hypotheses whose expected word frequencies are lower …...

During the last 10 years, there have been many efforts in some areas of Natural Language Processing to encode the normal text or documents into machine readable form. If we encode written data using a canonical form which can be recognized by a computer, we can extract needed information and …...

We present a quantitative evaluation of one well-known word alignment algorithm, as well as an analysis of frequent errors in terms of this model's underlying assumptions. Despite error rates that range from 22% to 32%, we argue that this technology can be put to good use in certain automated aids …...

Real-world natural language sentences are long and complex, and always contain unexpected grammatical constructions. It even includes noise and ungrammaticality. This paper describes the Controlled Skip Parser, a program that parses such real-world sentences by skipping some of the words in the sentence. The new feature of this parser is …...

: The sign languages used by deaf communities around the world represent a linguistic challenge that natural language researchers in A.I. have only recently begun to take up. ZARDOZ is a system which tackles the cross-modal machine-translation problem, translating speech and text into fluid sign language. This paper presents an …...

With the progress of information-oriented trade and commerce many companies have recog- nized that the trade on and with the existing and emerging communication technologies is an essential element for the maintenance of the advantage of competition. Significant business reengineering efforts are underway to taming the complexity of both business …...

Being consistent in technical translations is difficult. Using translation memory software could be one remedy, but the effectiveness of these tools rests on the assumption that most repeated source sentences correspond isomorphically to repeated target sentences. With the help of a discrepancy tool to identify inconsistencies between source and target …...

Sentence alignment is the problem of making explicit the relations that exist between the sentences of two texts that are known to be mutual translations. Automatic sentence alignment methods typically face two kinds of difficulties. First, there is the question of robustness. In real life, discrepancies between the source-text and …...

This paper describes a new approach to word sense disambiguation (WSD) based on automatically acquired "word sense division. The semantically related sense entries in a bilingual dictionary are arranged in clusters using a heuristic labeling algorithm to provide a more complete and appropriate sense division for WSD. Multiple translations of …...

The Defense Advanced Research Projects Agency (DARPA) Machine Translation (MT) Initiative spanned four years. One outcome of this effort was a methodology for evaluating the core technology of MT systems which differ widely in approach, maturity, platform, and language combination. This black box methodology, which proved capable of measuring performance …...

The history of MT shows how the shortcomings of one approach become the catalyst for a new approach. New systems are designed in reaction to old systems' weaknesses. Yet some old systems have survived and are being used increasingly in the "real world" of translation. One of these systems is …...

This paper describes the use of verb class memberships as a means of capturing gener- alizations about manner-of-motion verbs in Synchronous Tree Adjoining Grammars, STAGs, [20, 21, 22]. This approach allows STAGs, which are essentially transfer-based, to take advan- tage of the same types of generalizations which are generally thought …...

: This paper examines differences between two professional translations into English of the same Spanish newspaper article. Among other explanations for these differences, such as outright errors and free variation, we find a significant number of differences that can be explained on the basis of differing beliefs on the part …...