Articles

There has been recent interest in looking at what is required for a tree query language for linguis- tic corpora. One approach is to start from exist- ing formal machinery, such as tree grammars and automata, to see what kind of machine is an ap- propriate underlying one for the …...

We present KAFTIE – an incremental knowledge acquisition framework which utilizes expert knowl- edge to build high quality knowledge base annota- tors. Using KAFTIE, a knowledge base was built based on a small data set that outperforms machine learning algorithms trained on a much bigger data set for the task …...

A Dual-Type automatic speech recogniser (ASR) is a multi-pass ASR system that incorporates both a speaker-independent (SI) and a speaker-dependent (SD) ASR. The purpose of this approach is to improve the robustness of spoken dialogue systems for a broader range of applications. This paper identifies feasible Dual-Type multi-pass ASR system …...

Language samples are useful as an object of study for a diverse range of people. Samples of low-density languages in particular are often valuable in their own right, yet it is these sam- ples which are most difficult to locate, especially in a vast repository of information such as the …...

Word prediction is the problem of guessing which words are likely to follow in a given segment of a text to help a user with disabilities. As the user enters each letters of the required word, the system displays a list of the most probable words that could appear in …...

Processing unknown words is disproportionately important because of their high information con- tent. It is crucial in domains with specialist vocab- ularies where relevant training material is scarce, for example: biological text. Unknown word pro- cessing often begins with Part of Speech (POS) tag- ging, where accuracy is typically 10% …...

Speech synthesis or text-to-speech (TTS) systems are currently available for a number of the world’s major languages, but for thousands of the world’s ‘minor’ languages no such technology is available. While awaiting the development of such technology, we would like to try the stop-gap solution of using an existing TTS …...

This paper presents a statistical approach to un- known word type prediction for a deep HPSG grammar. Our motivation is to enhance robust- ness in deep processing. With a predictor which predicts lexical types for unknown words ac- cording to the context, new lexical entries can be generated on the …...

AnswerFinder is a framework for the devel- opment of question-answering systems. An- swerFinder is currently being used to test the applicability of graph representations for the de- tection and extraction of answers. In this paper we briefly describe AnswerFinder and introduce our method to learn graph patterns that link questions …...

The recognition of named entities is now a well- developed area, with a range of symbolic and machine learning techniques that deliver high accuracy identification and categorisation of a variety of entity types. However, there are still some named entity phenomena that present problems for existing techniques; in particular, relatively …...

Accurately representing synonymy using distribu- tional similarity requires large volumes of data to reliably represent infrequent words. However, the na¨ıve nearest-neighbour approach to compare con- text vectors extracted from large corpora scales poorly. The Spatial Approximation Sample Hier- archy (SASH) is a data-structure for performing ap- proximate nearest-neighbour queries, and …...

In order to arrive at a more disciplined ap- proach to the sustained development of linguis- tically rich grammars, I present a methodology for grammar validation, identifying principal di- mensions of the task, and illustrating the appli- cation of the method for one release cycle of the open-source English Resource …...

We investigate the impact of introducing finer dis- tinctions into the tagset on the accuracy of part- of-speech tagging. This is a tangential approach to most recent research in the field, which has focussed on applying different algorithms using a very simi- lar set of features. We outline the basic …...

. Fully automatic translations are far from being perfect. Non-grammatical sentences are often produced by automatic systems and there is even no guarantee that the meaning of the sentence is preserved. Nevertheless, automatic translation systems can be used to help human translators to produce high-quality translations. This is the goal …...

. User acceptance and system integration in existing IT environments are the key factors in machine translation (MT) becoming a universally implemented tool. Although output quality obviously plays a major role, it is not the sole decisive factor. User percep- tion of MT, however, is an important issue, and MT …...

. This paper proposes that quality criteria are set up for machine translation sys- tems that attempt to capture what can be considered the upper limit for the performance of MT systems. It argues that the best performance MT currently should aim for is close trans- lation, and that attempts …...

. In statistical machine translation, word alignment models are trained on bilingual corpora. Long sentences pose severe problems: 1. the high computational requirements; 2. the poor quality of the resulting word alignment. We present a sentence-segmentation method that solves these problems by splitting long sentence pairs. Our approach uses the …...

. Discriminative training methods are used in statistical machine translation to ef- fectively introduce and combine additional knowledge sources within the translation proc- ess. Although these methods are described in the accompanying literature and comparative studies are available for speech recognition, additional considerations are introduced when applying discriminative training to …...

. In this paper, we will address the question of how to efficiently integrate word confidence measures into a state-of-the-art interactive statistical machine translation system and improve prediction performance. Different methods will be presented: the selection of words according to their confidence as well as the rejection which has not …...

. Offering Machine Translation (MT) as a commercial service to end users means having to build up and regularly update large lexicons that can handle both general lan- guage and client specific terminology. This paper describes the processes developed at CLS Communication to cover the demand of users from several …...