Articles

In this paper, we describe an integrated approach to entity mention detection that yields a monolithic, almost language in- dependent system. It is optimal in the sense that all categorical constraints are si- multaneously considered. The system is compact and easy to develop and main- tain, since only a single …...

Distributions of the senses of words are often highly skewed. This fact is exploited by word sense disambiguation (WSD) sys- tems which back off to the predominant sense of a word when contextual clues are not strong enough. The domain of a doc- ument has a strong influence on the …...

We present a system for deciding whether a given sentence can be inferred from text. Each sentence is represented as a directed graph (extracted from a depen- dency parser) in which the nodes repre- sent words or phrases, and the links repre- sent syntactic and semantic relationships. We develop a …...

Instant Messaging (IM) chat sessions are real-time, text-based conversations which can be analyzed using dialogue-act mod- els. Dialogue acts represent the seman- tic information of an utterance, however, messages must be segmented into utter- ances before classification can take place. We describe and compare two statistical methods for automatic utterance …...

We present an approach to multi-device dia- logue that evaluates and selects amongst candi- date dialogue moves based on features at mul- tiple levels. Multiple sources of information can be combined, multiple speech recognition and parsing hypotheses tested, and multiple de- vices and moves considered to choose the high- est …...

The paper outlines the development and design of a speech driven control for a personal in-car navigation system which runs on a standard Pocket PC. The modified system enables speech driven menu navigation, speech shortcut commands and interactive dialogues. The speech recognition method is presented, sources of inaccurate recognition are …...

A fundamental problem for systems that re- quire natural language understanding capabili- ties is the identification of instances of semantic equivalence and paraphrase in text. The PAS- CAL Recognising Textual Entailment (RTE) challenge is a recently proposed research ini- tiative that addressed this problem by provid- ing an evaluation framework …...

In this paper we describe a modular system ar- chitecture for distributed parse annotation us- ing interactive correction. This involves inter- actively adding constraints to an existing parse until the returned parse is correct. Using a mixed initiative approach, human annotators in- teract live with distributed ccg parser servers through …...

Previous systems that automatically tag text with FrameNet labels have been trained from the FrameNet example data, as there is no FrameNet annotated corpus. The FrameNet data is systemat- ically biased by the criteria for the examples’ se- lection, as annotators attempt to select simple sen- tences that include the …...

We argue it is better to program in a natural lan- guage such as English, instead of a programming language like Java. A natural language interface for programming should result in greater readabil- ity, as well as making possible a more intuitive way of writing code. In contrast to previous …...

- This paper proposes a dual-iterative method, a hierarchical inner and outer iteration method (HIO), to acquire concept words from a large-scale, un-segmented Chinese corpus. It has two levels of iteration: the EM-CLS algorithm and the Viterbi-C/S algorithm constitute the inner iteration for generating concept words, and the concept word …...

In this paper we present work in progress on the PoS annotation of an Italian Corpus (CORIS) developed at CILTA (University of Bologna). We aim to automatically induce the PoS tagset by analysing the distributional behaviour of Italian words by relying only on theory-neutral linguistic knowledge. To this end, we …...

This paper explores the differences in words and word usage in two corpora – one derived from newspaper text and the other from the web. A corpus of web pages is compiled from a con- trolled traversal of the web, producing a topic- diverse collection of 2 billion words of …...

This paper proposes an approach to sentence- level paraphrase identification by text canon- icalization. The source sentence pairs are first converted into surface text that approxi- mates canonical forms. A decision tree learn- ing module which employs simple lexical match- ing features then takes the output canonical- ized texts as …...

This paper presents a method for detecting compound nominalisations from open data, and providing a semantic intepretation. It uses a statistical model based on confidence intervals over frequencies extracted from a large, bal- anced corpus. Using three paraphrases of the given compound nominalisation, and interpre- tation preferences of its components, …...

Recent studies of sentiment classification (determining whether a text is “positive” or “negative”) using Appraisal theory have provided mixed results. While some good results have been obtained, it is difficult to tell what aspects of Appraisal are particularly useful for this task. In this paper, we present a series of …...

This paper considers the popular but ques- tionable technique of ‘round-trip transla- tion’ (RTT) as a means of evaluating free on-line Machine Translation systems. Two experiments are reported, both relat- ing to common requirements of lay-users of MT on the web. In the first we see whether RTT can accurately …...

Documents are typically marked up to enable ren- dering and to facilitate reuse. However, retargetting a document often requires pervasive changes to the markup. Power et al. have proposed a new level of representation called document structure which captures just those aspects of graphical organisation that are significant for conveying …...

In this paper, I argue that grammatical description of language is a type of information which is ideally suited to presentation as a multimedia object structured with hypertext. I examine three existing language resources, constructed for different audiences, and discuss various features of each which bear on the design issues …...

This work concerns a question answering tool that uses multiple Web search engines and Web question answering systems to retrieve snippets of text that may contain an exact answer for a natural language question. The method de- scribed here treats each Web information re- trieval system in a unique manner …...