Andy Way

Dublin City University, School of Computing, Faculty Member

Followers

102

Following

120

Co-authors

Public Views

Full Professor at Dublin City University and Deputy Director of the ADAPT Centre for Digital Content Technology

less

InterestsView All (7)

Uploads

Papers by Andy Way

Translating with examples: the LFG-DOT models of translation

Download

The Integration of Machine Translation and Translation Memory

A dissertation submitted in fulfilment of the requirements for the award of Contents Abstract i A... more

Download

Translating with examples

ABSTRACT

Andy Way-ekin elkarrizketa, itzulpengintza automatikoan aditua

Disambiguation Strategies for Data-Oriented Translation

The Data-Oriented Translation (DOT) model -originally proposed in and based on Data-Oriented Pars... more The Data-Oriented Translation (DOT) model -originally proposed in and based on Data-Oriented Parsing (DOP) (e.g. (Bod, Scha, & Sima'an, 2003)) -is best described as a hybrid model of translation as it combines examples, linguistic information and a statistical translation model. Although theoretically interesting, it inherits the computational complexity associated with DOP. In this paper, we focus on one computational challenge for this model: efficiently selecting the 'best' translation to output. We present four different disambiguation strategies in terms of how they are implemented in our DOT system, along with experiments which investigate how they compare in terms of accuracy and efficiency.

Download

Using Percolated Dependencies for Phrase Extraction in SMT

Statistical Machine Translation (SMT) systems rely heavily on the quality of the phrase pairs ind... more Statistical Machine Translation (SMT) systems rely heavily on the quality of the phrase pairs induced from large amounts of training data. Apart from the widely used method of heuristic learning of n-gram phrase translations from word alignments, there are numerous methods for extracting these phrase pairs. One such class of approaches uses translation information encoded in parallel treebanks to extract phrase pairs. Work to date has demonstrated the usefulness of translation models induced from both constituency structure trees and dependency structure trees. Both syntactic annotations rely on the existence of natural language parsers for both the source and target languages. We depart from the norm by directly obtaining dependency parses from constituency structures using head percolation tables. The paper investigates the use of aligned chunks induced from percolated dependencies in French-English SMT and contrasts it with the aforementioned extracted phrases. We observe that adding phrase pairs from any other method improves translation performance over the baseline n-gram-based system, percolated dependencies are a good substitute for parsed dependencies, and that supplementing with our novel head percolation-induced chunks shows a general trend toward improving all system types across two data sets up to a 5.26% relative increase in BLEU.

Download

2006. Lost in Translation: the Problems of Using Mainstream MT Evaluation Metrics for Sign Language Translation

In this paper we consider the problems of applying corpus-based techniques to minority languages ... more In this paper we consider the problems of applying corpus-based techniques to minority languages that are neither politically recognised nor have a formally accepted writing system, namely sign languages. We discuss the adoption of an annotated form of sign language data as a suitable corpus for the development of a data-driven machine translation (MT) system, and deal with issues that arise from its use. Useful software tools that facilitate easy annotation of video data are also discussed. Furthermore, we address the problems of using traditional MT evaluation metrics for sign language translation. Based on the candidate translations produced from our example-based machine translation system, we discuss why standard metrics fall short of providing an accurate evaluation and suggest more suitable evaluation methods.

format_quoteThe system achieved a Sentence Error Rate of 96% and a Words Error Rate of 119%, but scored zero on BLEU due to missing closed class words.format_quote

Download

An Example-Based Approach to Translating Sign Language

Users of sign languages are often forced to use a language in which they have reduced competence ... more Users of sign languages are often forced to use a language in which they have reduced competence simply because documentation in their preferred format is not available. While some research exists on translating between natural and sign languages, we present here what we believe to be the first attempt to tackle this problem using an example-based (EBMT) approach.

Download

Joining hands: Developing a sign language machine translation system with and for the deaf community

This paper discusses the development of an automatic machine translation (MT) system for translat... more This paper discusses the development of an automatic machine translation (MT) system for translating spoken language text into signed languages (SLs). The motivation for our work is the improvement of accessibility to airport information announcements for D/deaf and hard of hearing people. This paper demonstrates the involvement of Deaf colleagues and members of the D/deaf community in Ireland in three areas of our research: the choice of a domain for automatic translation that has a practical use for the D/deaf community; the human translation of English text into Irish Sign Language (ISL) as well as advice on ISL grammar and linguistics; and the importance of native ISL signers as manual evaluators of our translated output.

Download

Teaching machine translation and translation technology: a contrastive study

The Machine Translation course at Dublin City University is taught to undergraduate students in A... more The Machine Translation course at Dublin City University is taught to undergraduate students in Applied Computational Linguistics, while Computer-Assisted Translation is taught on two translator-training programmes, one undergraduate and one postgraduate. Given the differing backgrounds of these sets of students, the course material, methods of teaching and assessment all differ. We report here on our experiences of teaching these courses over a number of years, which we hope will be of interest to lecturers of similar existing courses, as well as providing a reference point for others who may be considering the introduction of such material.

Download

Unknown

this article considerably. All remaining errors are our own

Hybridity in MT: experiments on the Europarl corpus

(Way & Gough, 2005) demonstrate that their Marker-based EBMT system is capable of outperforming a... more (Way & Gough, 2005) demonstrate that their Marker-based EBMT system is capable of outperforming a word-based SMT system trained on reasonably large data sets. (Groves & Way, 2005) take this a stage further and demonstrate that while the EBMT system also outperforms a phrase-based SMT (PBSMT) system, a hybrid 'example-based SMT' system incorporating marker chunks and SMT sub-sentential alignments is capable of outperforming both baseline translation models for French{English translation. In this paper, we show that similar gains are to be had from constructing a hybrid 'statistical EBMT' system capable of outperforming the baseline system of (Way & Gough, 2005). Using the Europarl (Koehn, 2005) training and test sets we show that this time around, although all 'hybrid' variants of the EBMT system fall short of the quality achieved by the baseline PBSMT system, merging elements of the marker-based and SMT data, as in (Groves & Way, 2005), to create a hybrid &#3...

Download

Hybrid Example-Based SMT: the Best of Both Worlds

by Declan Groves and Andy Way

provide an indepth comparison of their Example-Based Machine Translation (EBMT) system with a Sta... more provide an indepth comparison of their Example-Based Machine Translation (EBMT) system with a Statistical Machine Translation (SMT) system constructed from freely available tools. According to a wide variety of automatic evaluation metrics, they demonstrated that their EBMT system outperformed the SMT system by a factor of two to one. Nevertheless, they did not test their EBMT system against a phrase-based SMT system. Obtaining their training and test data for English-French, we carry out a number of experiments using the Pharaoh SMT Decoder. While better results are seen when Pharaoh is seeded with Giza++ word-and phrase-based data compared to EBMT sub-sentential alignments, in general better results are obtained when combinations of this 'hybrid' data is used to construct the translation and probability models. While for the most part the EBMT system of (Gough & Way, 2004b) outperforms any flavour of the phrasebased SMT systems constructed in our experiments, combining the data sets automatically induced by both Giza++ and their EBMT system leads to a hybrid system which improves on the EBMT system per se for French-English.

Download

Hybrid example-based SMT

Proceedings of the ACL Workshop on Building and Using Parallel Texts - ParaText '05, 2005

ABSTRACT (Way and Gough, 2005) provide an in-depth comparison of their Example-Based Machine Tran... more ABSTRACT (Way and Gough, 2005) provide an in-depth comparison of their Example-Based Machine Translation (EBMT) system with a Statistical Machine Translation (SMT) system constructed from freely available tools. According to a wide variety of automatic evaluation metrics, they demonstrated that their EBMT system outperformed the SMT system by a factor of two to one. Nevertheless, they did not test their EBMT system against a phrase-based SMT system. Obtaining their training and test data for English--French, we carry out a number of experiments using the Pharaoh SMT Decoder. While better results are seen when Pharaoh is seeded with Giza++ word- and phrase-based data compared to EBMT sub-sentential alignments, in general better results are obtained when combinations of this &#39;hybrid&#39; data is used to construct the translation and probability models. While for the most part the EBMT system of (Gough &amp; Way, 2004b) outperforms any flavour of the phrase-based SMT systems constructed in our experiments, combining the data sets automatically induced by both Giza++ and their EBMT system leads to a hybrid system which improves on the EBMT system per se for French--English.

Translating with Examples: The LFG-DOT Models of Translation

Text, Speech and Language Technology, 2003

Download

Robust Sub-Sentential Alignment of Phrase-Structure Trees

by Declan Groves and Andy Way

Data-Oriented Translation (DOT), based on Data-Oriented Parsing (DOP), is a language-independent ... more Data-Oriented Translation (DOT), based on Data-Oriented Parsing (DOP), is a language-independent MT engine which exploits parsed, aligned bitexts to produce very high quality translations. However, data acquisition constitutes a serious bottleneck as DOT requires parsed sentences aligned at both sentential and sub-structural levels. Manual substructural alignment is time-consuming, error-prone and requires considerable knowledge of both source and target languages and how they are related. Automating this process is essential in order to carry out the large-scale translation experiments necessary to assess the full potential of DOT. We present a novel algorithm which automatically induces sub-structural alignments between context-free phrase structure trees in a fast and consistent fashion requiring little or no knowledge of the language pair. We present results from a number of experiments which indicate that our method provides a serious alternative to manual alignment.

format_quoteManual alignments outperform automatic alignments across all link depths, indicating issues in translation coverage and performance limitations of automatic methods.format_quote

Download

Toward a Hybrid Integrated Translation Environment

Lecture Notes in Computer Science, 2002

Download

EBMT in a Controlled Environment

Text, Speech and Language Technology, 2003

ABSTRACT One key to the success of EBMT is the removal of the boundaries limiting the potential o... more ABSTRACT One key to the success of EBMT is the removal of the boundaries limiting the potential of Translation Memories (TMs). We discuss a linguistically enhanced TM system, a Phrasal Lexicon (PL), which takes advantage of the huge, underused resources available in existing translation aids. We claim that PL and EBMT systems can provide valuable translation solutions for restricted domains, especially where controlled language restrictions are imposed. When integrated into a hybrid and/or multi-engine MT environment, the PL will yield significant improvements in translation quality. We establish a future model of translation usage and anticipate that EBMT and the PL will have a central place in future hybrid integrated translation platforms.

Standard Language Variety Conversion for Content Localisation Via SMT

Some Transfer Problems in translating between English and Irish

Andy Way

Uploads

Papers by Andy Way

Log In