Articles

Reasoning about how much content to generate when space is limited presents an increasingly important challenge for generation systems, as the diversity of potential delivery channels continues to grow. The problem is multi-facetted: the generated text must fit into the allocated space, the space available must be well utilised, and …...

We present the Weighted Mutual Exclu- sion Bootstrapping (WMEB) algorithm for simultaneously extracting precise seman- tic lexicons and templates for multiple cat- egories. WMEB is capable of extracting larger lexicons with higher precision than previous techniques, successfully reduc- ing semantic drift by incorporating new weighting functions and a cumulative tem- …...

Event reference identification is often treated as a sentence level classification task. However, several different event ref- erences can occur within a single sentence. We present a set of experiments involving real world event reference identification at the word level in newspaper and newswire documents, addressing the issue of effec- …...

Query expansion has long been suggested as a technique for dealing with word mismatch problem in information retrieval. In this paper, we describe a novel query expansion method which incorporates text mining techniques into query expansion for improving Chinese infor- mation retrieval performance. Unlike most of the existing query expansion …...

Many workplace tasks are managed through email communication, involving the exchange of requests and commitments. Our aim is to build a tool that can automatically identify and manage such requests and commitments. A detailed analysis of real data, however, re- veals a range of interesting edge cases that make even …...

In this paper we present interface tech- niques that support the writing pro- cess of machine-oriented controlled natu- ral languages which are well-defined and tractable fragments of English that can be translated unambiguously into a formal tar- get language. Since these languages have grammatical and lexical restrictions, it is important …...

The limitations of existing data sets for train- ing parsers has led to a need for additional data. However, the cost of manually annotat- ing the amount and range of data required is prohibitive. For a number of simple facts like those sought in Question Answering, we com- pile a …...

The Lexical Access (LA) problem in Com- puter Science aims to match a phoneme se- quence produced by the user to a correctly spelled word in a lexicon, with minimal hu- man intervention and in a short amount of time. Lexical Access is useful in the case where the user …...

Syntactic Features for Text Categorisation Ari Chanen School of Information Technologies University of Sydney Sydney, Australia, 2006 ari@it.usyd.edu.au Jon Patrick School of Information Technologies University of Sydney Sydney, Australia, 2006 jonpat@it.usyd.edu.au Abstract Good performance on Text Classifica- tion (TC) tasks depends on effective and statistically significant features. Typ- ically, the …...

Sentiment classifiers attempt to determine whether a document expresses a generally positive or negative sentiment about its topic. Previous work has shown that overall per- formance can be improved by combining per-document classifications with information about agreement between documents. This paper explores approaches to sentiment clas- sification of U.S Congressional …...

Manually maintaining comprehensive databases of multi-word expressions, for example Verb-Particle Constructions (VPCs), is infeasible. We describe a new type level classifier for potential VPCs, which uses information in the Google Web1T corpus to perform a simple lin- guistic constituency test. Specifically, we consider the fronting test, comparing the frequencies of …...

Research in Question Answering (QA) has been dominated by the TREC methodology of black-box system evaluation. This makes it difficult to evaluate the effectiveness of in- dividual components and requires human in- volvement. We have collected a set of an- swer locations within the AQUAINT corpus for a sample of …...

Statistical named entity recognisers require costly hand-labelled training data and, as a result, most existing corpora are small. We exploit Wikipedia to create a massive corpus of named entity annotated text. We transform Wikipedia’s links into named en- tity annotations by classifying the target ar- ticles into common entity types …...

We develop a data set of Malay lexemes la- belled with count classifiers, that are attested in raw or lemmatised corpora. A maximum entropy classifier based on simple, language- inspecific features generated from context to- kens achieves about 50% F-score, or about 65% precision when a suite of binary classi- …...

While the intuition that morphological pre- processing of languages in various applica- tions can be beneficial appears to be often true, especially in the case of morphologi- cally richer languages, it is not always the case. Previous work on translation between Nordic languages, including the morphologi- cally rich Finnish, found …...

Previous work has shown that Chinese word seg- mentation is useful for machine translation to En- glish, yet the way different segmentation strategies affect MT is still poorly understood. In this pa- per, we demonstrate that optimizing segmentation for an existing segmentation standard does not al- ways yield better MT …...

Chinese word segmentation (CWS) is a necessary step in Chinese-English statisti- cal machine translation (SMT) and its per- formance has an impact on the results of SMT. However, there are many settings in- volved in creating a CWS system such as various specifications and CWS methods. This paper investigates the …...

In recent years, the quantity of parallel train- ing data available for statistical machine trans- lation has increased far more rapidly than the performance of individual computers, re- sulting in a potentially serious impediment to progress. Parallelization of the model- building algorithms that process this data on computer clusters is …...

This document describes the approach by the NLP Group at the Technical University of Cat- alonia (UPC-LSI), for the shared task on Au- tomatic Evaluation of Machine Translation at the ACL 2008 Third SMT Workshop. 1...

Previous studies have shown automatic evalu- ation metrics to be more reliable when com- pared against many human translations. How- ever, multiple human references may not al- ways be available. It is more common to have only a single human reference (extracted from parallel texts) or no reference at all. …...