Articles

This paper presents an update on PENG Light, a lightweight and portable controlled natural language processor that can be used to translate a well-defined subset of En- glish unambiguously into a formal target language. We illustrate by example of a Firefox extension that provides a simple in- terface to the …...

Attempts to profile authors based on their characteristics, including native language, have drawn attention in recent years, via sev- eral approaches using machine learning with simple features. In this paper we investigate the potential usefulness to this task of con- trastive analysis from second language acquis- tion research, which postulates …...

This paper investigates reduplication in In- donesian. In particular, we focus on verb redu- plication that has the agentive voice affix meN, exhibiting a homorganic nasal. We outline the recent changes we have made to the imple- mentation of our Indonesian grammar, and the motivation for such changes. There are …...

In the last eighteen months, a consensus has emerged from researchers in various disci- plines that a vital piece of research infrastruc- ture is lacking in Australia, namely, a substantial collection of computerised lan- guage data. A result of this consensus is an ini- tiative aimed at the establishment of …...

Named Entity (NE) information is criti- cal for Information Extraction (IE) tasks. However, the cost of manually annotating sufficient data for training purposes, espe- cially for multiple languages, is prohibitive, meaning automated methods for develop- ing resources are crucial. We investigate the automatic generation of NE annotated data in German …...

Information is fundamental to Finance, and un- derstanding how it flows from official sources to news agencies is a central problem. Readers need to digest information rapidly from high vol- ume news feeds, which often contain duplicate and irrelevant stories, to gain a competitive ad- vantage. We propose a text …...

Parsers are often the bottleneck for data ac- quisition, processing text too slowly to be widely applied. One way to improve the efficiency of parsers is to construct more confident statistical models. More training data would enable the use of more sophis- ticated features and also provide more ev- idence …...

Generic relation identification (GRI) aims to build models of relation-forming entity pairs that can be transferred across domains without modification of model parameters. GRI has high utility in terms of cheap com- ponents for applications like summarisa- tion, automated data exploration and ini- tialisation of bootstrapping of relation ex- traction. …...

There is an inherent redundancy in natural languages whereby certain common phrases (or n-grams) appear frequently in general sen- tences, each time with the same syntactic anal- ysis. We explore the idea of exploiting this re- dundancy by pre-constructing the parse struc- tures for these frequent n-grams. When pars- ing …...

Collocations constitute a subclass of multi-word expressions that are particu- larly problematic for machine translation, due 1) to their omnipresence in texts, and 2) to their morpho-syntactic proper- ties, allowing virtually unlimited variation and leading to long-distance dependen- cies. Since existing MT systems incorpo- rate mostly local information, these are …...

The paper presents a study of a challeng- ing task in machine translation and cross- language information retrieval – transla- tion of toponyms. Due to their linguistic and extra-linguistic nature, toponyms de- serve a special treatment. The overall translation process includes two stages of processing: dictionary-based and out-of- vocabulary toponym …...

We present an environment for the recog- nition and translation of Named Entities (NEs). The environment consists of a new formalism for the Named Entity Recognition and Translation (NERT), a parsing mechanism that reads the rules, recognizes Named Entities in given texts and suggests their translation, as well as a …...

We investigate the impact of the original source language (SL) on French–English PB-SMT. We train four configurations of a state-of-the-art PB-SMT system based on French–English parallel corpora which differ in terms of the original SL, and con- duct experiments in both translation direc- tions. We see that data containing orig- …...

Segmentation is widely used in adapting Statistical Machine Translation to highly inflected languages as Basque. The way this segmentation is carried out impacts on the quality of the translation. In or- der to look for the most adequate segmen- tation for a Spanish-Basque system, we have tried different segmentation options …...

This paper presents an extension for a bilingual n-gram statistical machine translation (SMT) system based on al- lowing translation units with gaps. Our gappy translation units can be seen as a first step towards introducing hierar- chical units similar to those employed in hierarchical MT systems. Our goal is double. …...

This paper presents three successful tech- niques to translate prepositions heading verbal complements by means of rich lin- guistic information, in the context of a rule-based Machine Translation system for an agglutinative language with scarce re- sources. This information comes in the form of lexicalized syntactic dependency triples, verb subcategorization …...

In this paper, a human evaluation of a Catalan-Spanish Ngram-based statistical machine translation system is used to de- velop specific techniques based on the use of grammatical categories, lexical cate- gorisation and text processing, for the en- hancement of the final translation. The system is successfully improved when test- ing …...

This paper reports an experiment on eval- uating and improving MT quality of light-verb construction (LVCs) – com- binations of a ‘semantically depleted’ verb and its complement. Our method uses construction-level human evaluation for systematic discovery of mistranslated contexts and creating automatic pre-edit- ing rules, which make the constructions more …...

We investigate the problem of predicting the quality of sentences produced by ma- chine translation systems when reference translations are not available. The prob- lem is addressed as a regression task and a method that takes into account the con- tribution of different features is proposed. We experiment with this …...

Recently novel MT evaluation metrics have been presented which go beyond pure string matching, and which corre- late better than other existing metrics with human judgements. Other research in this area has presented machine learning methods which learn directly from human judgements. In this paper, we present a novel combination …...