November 06, 2015

Expert Workshop on Topic Models and Corpus Analysis

Organised by DARIAH Text & Data Analytics Working Group (TDAWG)


December 14th (full-day) and 15th (half-day) 2015


ADAPT Centre Dublin City University, Glasnevin, Dublin 9 Ireland


With the increasing availability of large digital text resources, quantitative methods of analysis have found their way into a wide range of humanities disciplines and increasingly allow supplementing, and framing qualitative approaches in quantitative terms, leveraging the properties of large-scale data resources. Special relevance in this respect belongs to Natural Language Processing as a core sub-discipline of computer science. Recent advances in statistical approaches to recognising word embeddings and topic models have been leveraged successfully by scholars in diverse areas such as history, literary studies and linguistics.

The DARIAH TDA-WG invite participation from practitioners, researchers, scholars and experts in areas including topic modelling, word embedding, literary scholarship, history and the digital humanities. A portion of the workshop will be dedicated to organising and planning future WG activities, both Virtual and Physical.

This expert workshop agenda will include position papers and experience reports on the use of corpus analysis and topic modelling tools, their implications in different domains.

How To Register

Registration is free, You can register on the Eventbrite Event Page

For any queries, please do email

Please include any dietary, access or other requirements in your email


Time 14th December 15th December
09:30 Arrival & Registration Munelly et al.
10:00 Keynote Rybicki
10:30 Keynote Jannidis
11:00 Coffee Coffee
11:30 Maryl/Piasecki/Młynarczyk WG planning
12:00 Riddell/Dalen-Oskam WG planning
12:30 Leavy Concluding Remarks
13:00 Lunch Lunch & Departure
14:00 Schnober/Gurevych  
14:30 Grefenstette/Muchemi  
15:00 Coffee  
15:30 Eder/Piasecki/Walkowiak  
16:00 Panel Discussion  
17:00 End of Day 1  

Talk Abstracts


Machine Translation and Cognition: Perception, Productivity and the Professional

Recent advances in data driven machine translation have resulted in considerable levels of deployment in commercial translation scenarios, with reasonable success for some language pairs and domains. Consequently, professional translators find themselves engaged with a new paradigm, which is at least as disruptive as the translation memory revolution that took place in the 1990s. An uneasy symbiosis has emerged between the professional translator and the machine, with organisational and technological aspects potentially playing a significant role in the acceptance or rejection of the technology. While professional translators struggle with the new paradigm, consumers of content find themselves in a position where they can translate at the click of a button, at least for gisting purposes. The growth of machine translation has, therefore, impacted many. This talk will focus on machine translation from a cognitive ergonomic viewpoint moving through the stages of MT evaluation, to post- editing and its support technologies, to usability assessment for end users.

Speaker Bio

Sharon O’Brien is a senior lecturer in translation and language technology in the School of Applied Language and Intercultural Studies, Dublin City University. Her research to date has focused on the interaction between translators and technology (including Translation Memory and Machine Translation), cognitive aspects of translation, research methods, including eye tracking and keyboard logging, localisation and content authoring. She is Director of the Centre for Translation and Textual Studies ( and a funded investigator in the cross-institutional research centre Adapt ( She previously worked as a language technology specialist in the localisation industry.

Meal Details

A reservation has been made at Brasserie Sixty6 in Dublin City Centre at 19:00 on Monday night.

For public transport, you can take Bus route 9 to Exchequer Street.