27 Result(s)

Chapter and Conference Paper

The Need for Application-Dependent WSD Strategies: A Case Study in MT

It is generally agreed that the ultimate goal of research into Word Sense Disambiguation (WSD) is to provide a technology which can benefit applications; however, most of the work in this area has focused on t...

Lucia Specia… in Computational Processing of the Portuguese… (2006)

Chapter and Conference Paper

Exploiting the Translation Context for Multilingual WSD

We propose a strategy to support Word Sense Disambiguation (WSD) which is designed specifically for multilingual applications, such as Machine Translation. Co-occurrence information extracted from the translat...

Lucia Specia, Maria das Graças Volpe Nunes in Text, Speech and Dialogue (2006)

Chapter and Conference Paper

A Hybrid Approach for Relation Extraction Aimed at the Semantic Web

We present an approach for relation extraction from texts aimed to enrich the semantic annotations produced by a semantic web portal. The approach exploits linguistic and empirical strategies, by means of a pi...

Lucia Specia, Enrico Motta in Flexible Query Answering Systems (2006)

Chapter and Conference Paper

Word Sense Disambiguation Using Inductive Logic Programming

The identification of the correct sense of a word is necessary for many tasks in automatic natural language processing like machine translation, information retrieval, speech and text processing. Automatic Wor...

Lucia Specia, Ashwin Srinivasan, Ganesh Ramakrishnan… in Inductive Logic Programming (2007)

Chapter and Conference Paper

n-Best Reranking for the Efficient Integration of Word Sense Disambiguation and Statistical Machine Translation

Although it has been always thought that Word Sense Disambiguation (WSD) can be useful for Machine Translation, only recently efforts have been made towards integrating both tasks to prove that this assumption...

Lucia Specia, Baskaran Sankaran… in Computational Linguistics and Intelligent … (2008)

Chapter and Conference Paper

Translating from Complex to Simplified Sentences

We address the problem of simplifying Portuguese texts at the sentence level by treating it as a “translation task”. We use the Statistical Machine Translation (SMT) framework to learn how to translate from co...

Lucia Specia in Computational Processing of the Portuguese Language (2010)

Article

Machine translation evaluation versus quality estimation

Most evaluation metrics for machine translation (MT) require reference translations for each sentence in order to produce a score reflecting certain aspects of its quality. The de facto metrics, BLEU and NIST,...

Lucia Specia, Dhwaj Raj, Marco Turchi in Machine Translation (2010)

Article

Pushing the frontier of Statistical Machine Translation: Preface

Lucia Specia, Nicola Cancedda in Machine Translation (2010)

Chapter and Conference Paper

Ranking Machine Translation Systems via Post-editing

In this paper we investigate ways in which information from the post-editing of machine translations can be used to rank translation systems for quality. In addition to the commonly used edit distance between ...

Wilker Aziz, Ruslan Mitkov, Lucia Specia in Text, Speech, and Dialogue (2013)

Article

Quality estimation for machine translation: preface

Lucia Specia, Radu Soricut in Machine Translation (2013)

Article

Kirsten Malmkjær and Kevin Windle (eds.): The Oxford handbook of translation studies

Lucia Specia in Machine Translation (2013)

Article

Investigating the contribution of linguistic information to quality estimation

This paper describes a study on the contribution of linguistically-informed features to the task of quality estimation for machine translation at sentence level. A standard regression algorithm is used to buil...

Mariano Felice, Lucia Specia in Machine Translation (2013)

Chapter and Conference Paper

Statistical Relational Learning to Recognise Textual Entailment

We propose a novel approach to recognise textual entailment (RTE) following a two-stage architecture – alignment and decision – where both stages are based on semantic representations. In the alignment stage t...

Miguel Rios, Lucia Specia, Alexander Gelbukh… in Computational Linguistics and Intelligent … (2014)

Chapter and Conference Paper

Divergences in the Usage of Discourse Markers in English and Mandarin Chinese

Statistical machine translation (SMT) has, in recent years, improved the accuracy of automated translations. However, SMT systems often fail to deliver human quality translations especially with complex senten...

David Steele, Lucia Specia in Text, Speech and Dialogue (2014)

Article

A Bayesian non-linear method for feature selection in machine translation quality estimation

We perform a systematic analysis of the effectiveness of features for the problem of predicting the quality of machine translation (MT) at the sentence level. Starting from a comprehensive feature set, we appl...

Kashif Shah, Trevor Cohn, Lucia Specia in Machine Translation (2015)

Chapter

Final Remarks

QE, as presented in this book, is the task of predicting the quality of a given output of an NLP application without relying on comparisons against manually produced references. More specifically, QE focuses o...

Lucia Specia, Carolina Scarton… in Quality Estimation for Machine Translation (2018)

Chapter

Introduction

Quality Estimation (QE) for Natural Language Processing (NLP) applications is an area of emerging interest. The goal is to provide an estimate on how good or reliable the results returned by an application are...

Lucia Specia, Carolina Scarton… in Quality Estimation for Machine Translation (2018)