Under Review/ To Appear:
Gerard Lynch. Strange Bedfellows: Shifting Paradigms in the Corpus-Based Analyses of Literary Translations. INTRALINEA : Special Issue on Corpus Linguistics and Translation Studies , Under Review, Draft
Gerard Lynch and Carl Vogel. The translator’s visibility: Detecting translatorial fingerprints in contemporaneous parallel translations. Computer, Speech and Language Journal, Under Review.
Gerard Lynch. Every Word You Set: Simulating the cognitive process of linguistic creativity with the PUNdit system. International Journal of Mind, Brain & Cognition, December 2015, Draft
Erwan Moreau, Arun Jayapal, Gerard Lynch and Carl Vogel. Author Verification: Basic Stacked Generalization Applied To Predictions from a Set of Heterogeneous Learners – Notebook for PAN at CLEF 2015.
Terrence Szymanski and Gerard Lynch. UCD : Diachronic Text Classification with Word, Character and Syntactic N-grams. In Proceedings of SEMEVAL 2015. (Paper)
Carmen Klaussner and Gerard Lynch and Carl Vogel. Following the trail of source languages in literary translations In Thirty-fourth SGAI International Conference Cambridge, UK 2014.
Daniel Isemann and Gerard Lynch and Raffaela Lanino. Towards a robust framework for the semantic representation of temporal expressions in cultural legacy data In Proceedings of the 3rd Workshop on Semantic Web and Information Extraction (SWAIE), Coling2014, Dublin,Ireland 2014.
Gerard Lynch. A Supervised Learning Approach for Profiling the Preservation of Authorial Style in Translations. In Proceedings of the 25th International Conference on Computational Linguistics (Coling), Dublin, Ireland 2014. (Blog post)
Gerard Lynch and Padraig Cunningham. Linguistically Motivated Tweet Categorisation for Online Reputation Management In Proceedings of the Fifth Workshop on Subjectivity and Sentiment Analysis (WASSA) 2014.
Carl Vogel and Ger Lynch and Erwan Moreau and Liliana Mamani Sanchez and Phil Ritchie. Found in Translation: Computational Discovery of Translation Effects. Translation Spaces 2013.
Gerard Lynch and Carl Vogel. Towards the automatic detection of the source language of a literary translation. In Coling 2012: Twenty-Fourth International Conference on Computational Linguistics, IIT Bombay, Mumbai, India. ICCL, 2012. 2012. (Blog post)
Gerard Lynch, Erwan Moreau, and Carl Vogel. A Naive Bayes classifier for automatic correction of preposition and determiner errors in ESL text. In Proceedings of the Seventh Workshop on Innovative Use of NLP for Building Educational Applications, Montreal, Canada, 7th June 2012. ACL, 2012.
Gerard Lynch and Carl Vogel. Chasing the Ghosts of Ibsen: A Computational Stylistic Analysis of Drama in Translation. In Digital Humanities 2009: University of Maryland, College Park, MD, USA, page 192. ALLC/ACH, 2009. (Paper)
Carl Vogel and Gerard Lynch. Computational Stylometry: Who’s in a Play? In Verbal and Nonverbal Features of Human-Human and Human-Machine Interaction, page 169. Springer, 2009. (Blog post)
Francesca Frontini, Gerard Lynch, and Carl Vogel. Revisiting the Donation of Constantine. In AISB 2008 Convention Communication, Interaction and Social Intelligence, volume 7, pages 1–9, 2008. (Blog post)
Jerom Janssen, Gerard Lynch, and Carl Vogel. Universum Inference and Corpus Homogeneity. In AI-2008 Twenty-Eighth SGAI International Conference on Artificial Intelligence, pages 367–372. Springer, 2008. (Poster)
Gerard Lynch. A computational stylometric analysis of characterization by playwrights. In Glucksman Memorial Symposium. Trinity College Dublin. Long Room Hub, 2008.
Gerard Lynch and Carl Vogel. Automatic Character Assignation. In AI-2007 Twenty-seventh SGAI International Conference on Artificial Intelligence, pages 335–348. Springer, 2007. (Blog post)
Gerard Lynch. Identifying Translation Effects in English Natural Language Text Trinity College Dublin, 2013 (download)
Gerard Lynch. Computational Stylometry and Analysis of Style: A Study of Characterization in Playwrights, Trinity College Dublin, 2009 (download)
Gerard Lynch. The Implementation and Evaluation of a Speech Recognition Component for a Meeting Browser, Trinity College Dublin, 2006 (download)
Friday February 17th 2017, 4pm Salmon Theatre, Trinity College Dublin, Ireland
Speaker: Gerard Lynch
Title: The Generation Game: Exploring Natural Language Generation for clinical and creative purposes
The first half of this talk will discuss some of the challenges which have arisen in the process of implementing a clinically-focused natural language generation system at babylon, a leading healthcare startup employing artificial intelligence for the purposes of offering affordable and accessible healthcare to all.
The second half of the talk will discuss a personal project examining the application of language generation in the context of creating topically relevant creative titles for news articles and other creative pieces of writing using a range of NLP techniques.
Friday April 24th 2015, 4pm Dublin Institute of Technology, Kevin Street, Dublin, Ireland
Speaker: Gerard Lynch
Title: In Search of Lost Time (stamps?): Diachronic Text Classification
using Supervised Learning and N-Gram Feature Representations
This talk discusses a recent submission (with Terrence Szymanski of The
Insight Centre) to the SemEval 2015 Shared Task on Diachronic Text
evaluation. We approach the task of assigning a date of publication to a
text as a multi-class classification problem. We extract features from a
collection of historical news texts at the letter, word, and syntactic
level, and use these to train a classifier on date-labeled training data.
We also incorporate date probabilities of syntactic features as estimated
from the Google Books Ngram corpus. Our system achieved the highest
performance of all systems on subtask 2: identifying texts by
specific time language use.
Speaker: Gerard Lynch
Title: Detecting the source language of a literary translation
In recent times there has been an increased interest in problems in
translation stylistics from researchers in computational linguistics. Baroni and Bernardini (2006) spearheaded this new movement of collaboration between
translation studies and the computational sciences with their study which
applied machine learning techniques from the text classification
literature to learn textual features which distinguish between
translated and non-translated Italian journalistic text. Their work was
also novel for their experiment which compared human
classification/identification of translated text with the performance of
computational methods on the same task. A related task was examined by van
Halteren (2008) who used similar methods to detect the source language of
translated text from the Europarl corpus in several
European languages. Our work examines this question but in relation to literary
translations, the question remains whether one can detect the source
language of a literary translation, a genre for which automatic
classification could be considered more complex due to the varying nature
of literary style. A corpus of 19th century literary works was assembled
for experimental purposes, including translations from
German, French and Russian. In reference to Bernardini et al, English
original texts were also included in the classification task. We
present results on our classification experiments including analysis of
the textual features found to be discriminatory in our task (word and POS
ngrams and document statistics such as type-token ratio etc ).
Classification results were found to be comparable to the state of the
art(ca. 80%) based on 10-fold cross validation experiments and testing on
a held out set. Testing on unseen data resulted in lower accuracy however
results were still well above the baseline.