Search Results for author: Teresa Lynn

Found 22 papers, 2 papers with code

A human evaluation of English-Irish statistical and neural machine translation

no code implementations EAMT 2020 Meghan Dowling, Sheila Castilho, Joss Moorkens, Teresa Lynn, Andy Way

With official status in both Ireland and the EU, there is a need for high-quality English-Irish (EN-GA) machine translation (MT) systems which are suitable for use in a professional translation environment.

Machine Translation Translation

Annotating MWEs in the Irish UD Treebank

no code implementations UDW (COLING) 2020 Sarah McGuinness, Jason Phelan, Abigail Walsh, Teresa Lynn

This paper reports on the analysis and annotation of Multiword Expressions in the Irish Universal Dependency Treebank.

TwittIrish: A Universal Dependencies Treebank of Tweets in Modern Irish

no code implementations ACL 2022 Lauren Cassidy, Teresa Lynn, James Barry, Jennifer Foster

Modern Irish is a minority language lacking sufficient computational resources for the task of accurate automatic syntactic parsing of user-generated content such as tweets.

Dependency Parsing

Annotating Verbal MWEs in Irish for the PARSEME Shared Task 1.2

no code implementations COLING (MWE) 2020 Abigail Walsh, Teresa Lynn, Jennifer Foster

This paper describes the creation of two Irish corpora (labelled and unlabelled) for verbal MWEs for inclusion in the PARSEME Shared Task 1. 2 on automatic identification of verbal MWEs, and the process of developing verbal MWE categories for Irish.

gaBERT -- an Irish Language Model

1 code implementation27 Jul 2021 James Barry, Joachim Wagner, Lauren Cassidy, Alan Cowap, Teresa Lynn, Abigail Walsh, Mícheál J. Ó Meachair, Jennifer Foster

The BERT family of neural language models have become highly popular due to their ability to provide sequences of text with rich context-sensitive token encodings which are able to generalise well to many Natural Language Processing tasks.

Language Modelling

Towards transparency in NLP shared tasks

no code implementations11 May 2021 Carla Parra Escartín, Teresa Lynn, Joss Moorkens, Jane Dunne

This article reports on a survey carried out across the Natural Language Processing (NLP) community.

Treebanking User-Generated Content: a UD Based Overview of Guidelines, Corpora and Unified Recommendations

no code implementations3 Nov 2020 Manuela Sanguinetti, Lauren Cassidy, Cristina Bosco, Özlem Çetinoğlu, Alessandra Teresa Cignarella, Teresa Lynn, Ines Rehbein, Josef Ruppenhofer, Djamé Seddah, Amir Zeldes

This article presents a discussion on the main linguistic phenomena which cause difficulties in the analysis of user-generated texts found on the web and in social media, and proposes a set of annotation guidelines for their treatment within the Universal Dependencies (UD) framework of syntactic analysis.

Treebanking User-Generated Content: A Proposal for a Unified Representation in Universal Dependencies

no code implementations LREC 2020 Manuela Sanguinetti, Cristina Bosco, Lauren Cassidy, {\"O}zlem {\c{C}}etino{\u{g}}lu, Aless Cignarella, ra Teresa, Teresa Lynn, Ines Rehbein, Josef Ruppenhofer, Djam{\'e} Seddah, Amir Zeldes

The paper presents a discussion on the main linguistic phenomena of user-generated texts found in web and social media, and proposes a set of annotation guidelines for their treatment within the Universal Dependencies (UD) framework.

Ilfhocail: A Lexicon of Irish MWEs

no code implementations WS 2019 Abigail Walsh, Teresa Lynn, Jennifer Foster

This paper describes the categorisation of Irish MWEs, and the construction of the first version of a lexicon of Irish MWEs for NLP purposes (Ilfhocail, meaning {`}Multiwords{'}), collected from a number of resources.


Ethical Considerations in NLP Shared Tasks

no code implementations WS 2017 Carla Parra Escart{\'\i}n, Wessel Reijers, Teresa Lynn, Joss Moorkens, Andy Way, Chao-Hong Liu

Shared tasks are increasingly common in our field, and new challenges are suggested at almost every conference and workshop.

Machine Translation

Is all that Glitters in Machine Translation Quality Estimation really Gold?

no code implementations COLING 2016 Yvette Graham, Timothy Baldwin, Meghan Dowling, Maria Eskevich, Teresa Lynn, Lamia Tounsi

Human-targeted metrics provide a compromise between human evaluation of machine translation, where high inter-annotator agreement is difficult to achieve, and fully automatic metrics, such as BLEU or TER, that lack the validity of human assessment.

Machine Translation Translation

Irish Treebanking and Parsing: A Preliminary Evaluation

no code implementations LREC 2012 Teresa Lynn, {\"O}zlem {\c{C}}etino{\u{g}}lu, Jennifer Foster, Elaine U{\'\i} Dhonnchadha, Mark Dras, Josef van Genabith

This paper describes the early stages in the development of new language resources for Irish ― namely the first Irish dependency treebank and the first Irish statistical dependency parser.

Machine Translation POS

Cannot find the paper you are looking for? You can Submit a new open access paper.