Articles

This paper presents ECOLE, a look-ahead text editor that supports authors writing seemingly informal specifications in PENG, a computer-processable controlled natural language. ECOLE communicates via a socket interface with the controlled language processor of the PENG system. After each word form entered the look- ahead editor displays appropriate look- ahead …...

This paper describes a project currently under way at SAP dealing with the task of post-editing MT output. As a concrete re- sult of the project, a standard post-editing guide to be used by translator end users is currently being created. The purpose of this post-editing guide is not only …...

AECMA Simplified English for aircraft maintenance manuals is one of the best- known examples of a controlled language. In this paper we describe the development of its equivalent for Spanish. We also present a prototype validating parser and outline its evaluation. 1...

This paper presents the results of an analysis of eight Controlled English rule sets. The objective of this analysis was to discover the extent to which Controlled Language rule sets shared common rules and to try to establish a core set of CL rules for English. The analysis reveals that, …...

This paper describes the Cataloguing Tool of the Mkbeem multilingual eCommerce mediation system. The Cataloguing Tool is used by product suppliers to provide necessary product information in a form required by the mediation system. The relevant information includes product ar- ticles that are maintained in a pivot lan- guage and …...

Machine translation can play an impor- tant role nowadays, helping communica- tion between people. One of the projects in this field is TransType2 1. Its purpose is to develop an innovative, interactive machine translation system. TransType2 aims at facilitating the task of producing high-quality translations, and make the translation task …...

It is a general assumption that 1) the readability and clarity of LSP texts written in a controlled language are better than uncontrolled texts and 2) that controlled languages produce bet- ter results with machine translation than uncontrolled languages. Con- trolled languages impose lexical, syn- tactic and pragmatic restrictions on …...

By this paper, we present the INTERLINGUA Project1: its design and current work. The goal of the project is achieving fully-automatic (no pre-edition, no post-edition) translation of emails in the virtual campus of the Open University of Catalonia (UOC). The problem of un- supervised machine translation of emails is discussed. …...

A serious bottleneck in the development of trainable text summarization systems is the shortage of training data. Constructing such data is a very tedious task, especially because there are in general many different correct ways to summarize a text. Fortunately we can utilize the Internet as a source of suitable …...

This paper describes an unsupervised algo- rithm for placing unknown words into a taxon- omy and evaluates its accuracy on a large and varied sample of words. The algorithm works by first using a large corpus to find semantic neighbors of the unknown word, which we ac- complish by combining …...

We propose a gold standard for evaluating two types of information extraction output -- noun phrase (NP) chunks (Abney 1991; Ramshaw and Marcus 1995) and technical terms (Justeson and Katz 1995; Daille 2000; Jacquemin 2002). The gold standard is built around the notion that since different semantic and syntactic variants …...

We present a new part-of-speech tagger that demonstrates the following ideas: (i) explicit use of both preceding and following tag con- texts via a dependency network representa- tion, (ii) broad use of lexical features, includ- ing jointly conditioning on multiple consecu- tive words, (iii) effective use of priors in con- …...

Statistical measures of word similarity have ap- plication in many areas of natural language pro- cessing, such as language modeling and in- formation retrieval. We report a comparative study of two methods for estimating word co- occurrence frequencies required by word sim- ilarity measures. Our frequency estimates are generated from …...

This paper investigates bootstrapping for statis- tical parsers to reduce their reliance on manu- ally annotated training data. We consider both a mostly-unsupervised approach, co-training, in which two parsers are iteratively re-trained on each other’s output; and a semi-supervised approach, corrected co-training, in which a human corrects each parser’s output …...

We introduce two probabilistic models that can be used to identify elementary discourse units and build sentence-level discourse parse trees. The models use syntactic and lexical features. A discourse parsing algorithm that implements these models derives discourse parse trees with an error reduction of 18.8% over a state-of- the-art decision-based …...

Conditional random fields for sequence label- ing offer advantages over both generative mod- els like HMMs and classifiers applied at each sequence position. Among sequence labeling tasks in language processing, shallow parsing has received much attention, with the devel- opment of standard evaluation datasets and ex- tensive comparison among methods. …...

This paper investigates adapting a lexicalized probabilistic context-free grammar (PCFG) to a novel domain, using maximum a posteriori (MAP) estimation. The MAP framework is gen- eral enough to include some previous model adaptation approaches, such as corpus mixing in Gildea (2001), for example. Other approaches falling within this framework are …...

We present an application of ambiguity pack- ing and stochastic disambiguation techniques for Lexical-Functional Grammars (LFG) to the domain of sentence condensation. Our system incorporates a linguistic parser/generator for LFG, a transfer component for parse reduc- tion operating on packed parse forests, and a maximum-entropy model for stochastic output selection. …...

We present a simple method for language inde- pendent and task independent text categoriza- tion learning, based on character-level n-gram language models. Our approach uses simple information theoretic principles and achieves effective performance across a variety of lan- guages and tasks without requiring feature se- lection or extensive pre-processing. To …...

We describe a syntax-based algorithm that au- tomatically builds Finite State Automata (word lattices) from semantically equivalent transla- tion sets. These FSAs are good representa- tions of paraphrases. They can be used to ex- tract lexical and syntactic paraphrase pairs and to generate new, unseen sentences that express the same …...