Now showing items 1-10 of 10

  • Automatic taxonomy generation: a use-case in the legal domain 

    Robin, Cécile; O'Neill, James; Buitelaar, Paul (LTC'17, 8th Language & Technology Conference, 2017-11-17)
    A key challenge in the legal domain is the adaptation and representation of the legal knowledge expressed through texts, in order for legal practitioners and researchers to access this information more easily and faster ...
  • Benchmarking Domain-Specific Expert Search Using Workshop Program Committees 

    Bordea, Georgeta; Buitelaar, Paul (ACM, 2013)
    Traditionally, relevance assessments for expert search have been gathered through self-assessment or based on the opinions of co-workers. We introduce three benchmark datasets1 for expert search that use conference workshops ...
  • Classifying sentential modality in legal language: A use case in financial regulations, acts and directives 

    O'Neill, James; Buitelaar, Paul; Robin, Cécile; O'Brien, Leona (ACM, 2017-06-12)
    Texts expressed in legal language are often di cult and time consuming for lawyers to read through, particularly for the purpose of identifying relevant deontic modalities (obligations, prohibitions and permissions). ...
  • A comparison of emotion annotation schemes and a new annotated data set 

    Wood, Ian D.; McCrae, John P.; Andryushechkin, Vladimir; Buitelaar, Paul (European Languages Resources Association (ELRA), 2018-05-07)
    While the recognition of positive/negative sentiment in text is an established task with many standard data sets and well developed methodologies, the recognition of more nuanced affect has received less attention, and ...
  • Domain-independent term extraction through domain modelling 

    Bordea, Georgeta; Buitelaar, Paul; Polajnar, Tamara (10th International Conference on Terminology and Artificial Intelligence, 2013-09-11)
    Extracting general or intermediate level terms is a relevant problem that has not received much attention in literature. Current approaches for term extraction rely on contrastive corpora to identify domain-specific terms, ...
  • Hot Topics and Schisms in NLP: Community and Trend Analysis with Saffron on ACL and LREC Proceedings 

    Buitelaar, Paul; Bordea, Georgeta; Coughlan, Barry (2014)
    In this paper we present a comparative analysis of two series of conferences in the field of Computational Linguistics, the LREC conference and the ACL conference. Conference proceedings were ...
  • Multimodal multimodel emotion analysis as linked data 

    Sánchez-Rada, J. Fernando; Iglesias, Carlos A.; Sagha, Hesam; Schuller, Björn; Wood, Ian; Buitelaar, Paul (IEEE, 2018-02-01)
    The lack of a standard emotion representation model hinders emotion analysis due to the incompatibility of annotation formats and models from different sources, tools and annotation services. This is also a limiting factor ...
  • Multimodal multimodel emotion analysis as linked data 

    Sánchez-Rada, J. Fernando; Iglesias, Carlos A.; Sagha, Hesam; Schuller, Björn; Ian D. Wood, Ian D.; Buitelaar, Paul (IEEE, 2017-10-23)
    The lack of a standard emotion representation model hinders emotion analysis due to the incompatibility of annotation formats and models from different sources, tools and annotation services. This is also a limiting ...
  • SemEval-2016 Task 13: Taxonomy Extraction Evaluation (TExEval-2) 

    Bordea, Georgeta; Lefever, Els; Buitelaar, Paul (Insight Centre for Data Analytics, 2016-06-16)
    This paper describes the second edition of the shared task on Taxonomy Extraction Evaluation organised as part of SemEval 2016. This task aims to extract hypernym-hyponym relations between a given list of domain-specific ...
  • Teanga: a linked data based platform for natural language processing 

    Ziad, Housam; McCrae, John Philip; Buitelaar, Paul (Language Resources and Evaluation Conference (LREC 2018), 2018-05-07)
    In this paper, we describe Teanga, a linked data based platform for natural language processing (NLP). Teanga enables the use of many NLP services from a single interface, whether the need was to use a single service or ...