Conf: EACL 2014, Tutorial on Computational modelling of metaphor, Gothenburg, Sweden, 26 April 2014

Thierry Hamon hamon at LIMSI.FR
Tue Mar 11 21:23:12 UTC 2014

Date: Tue, 11 Mar 2014 08:20:16 +0100
From: peter ljunglöf <peter.ljunglof at>
Message-Id: <2E3333F1-B861-470B-BCE5-E2ED3D3DC9F4 at>


EACL 2014 Tutorial on Computational modelling of metaphor  

Gothenburg, Sweden, 26 April

Instructors: Ekaterina Shutova and Tony Veale


Metaphor processing is a rapidly growing area in NLP.  Characteristic to
all areas of human activity (from the ordinary to the poetic or the
scientific) and, thus, to all types of discourse, metaphor poses an
important problem for NLP systems. Its ubiquity in language has been
established in a number of corpus studies and the role it plays in human
reasoning has been confirmed in psychological experiments. This makes
metaphor an important research area for computational and cognitive
linguistics, and its automatic identification and interpretation
indispensable for any semantics-oriented NLP application.

Computational work on metaphor in NLP and AI ignited in the 1970s and
gained momentum in the 1980s, providing a wealth of ideas on the form,
structure and mechanisms of the phenomenon. The last decade has
witnessed a technological leap in natural language computation, as
manually crafted rules have gradually given way to more robust
corpus-based statistical methods. This is also the case for metaphor
research. In the recent years, the problem of metaphor modeling has been
steadily gaining interest within the NLP community, with a growing
number of approaches exploiting statistical techniques. Compared to more
traditional approaches based on hand-coded resources, these more recent
methods boast of a wider coverage, as well as greater efficiency and
robustness. However, even the statistical metaphor processing approaches
largely focus on a limited domain or a subset of conceptual
phenomena. At the same time, recent work on computational lexical
semantics and lexical acquisition techniques, as well as a wide range of
NLP methods applying machine learning to open-domain semantic tasks,
opens many new avenues for creation of large-scale robust tools for the
recognition and interpretation of metaphor.

Despite a growing recognition of the importance of metaphor to the
semantic and affective processing of language, and despite the
availability of new NLP tools that enable us to take metaphor processing
to the next level, educational initiatives for introducing the NLP
community to this fascinating area of research have been relatively few
in number. Our proposed tutorial thus addresses this gap, by aiming to:

introduce a CL audience to the main linguistic, conceptual and cognitive
properties of metaphor;

cover the history of metaphor modelling and the state-of-the-art
approaches to metaphor identification and interpretation

analyse the trends in computational metaphor research and compare
different types of approaches, aiming to identify the most promising
system features and techniques in metaphor modelling

discuss potential applications of metaphor processing in wider NLP

relate the problem of metaphor modelling to that of other types of
figurative language

The tutorial is targeted both at participants who are new to the field
and need a comprehensive overview of metaphor processing techniques and
applications, as well as at experienced scientists who want to stay up
to date on the recent advances in metaphor research.


Introduction: Linguistic, cognitive and cultural properties of metaphor
Linguistic metaphor
Conceptual metaphor
Metaphorical inference
Extended metaphor / metaphor in discourse
Conventional and novel metaphor
Metaphor in corpora and lexical resources

Computational approaches to metaphor identification
Knowledge-based methods
Lexical resource-based methods
Metaphor and selectional preferences
Metaphor and abstractness
Metaphor and cultural stereotypes
Word similarity and association-based methods
Supervised learning for metaphor identification
Weakly-supervised and unsupervised methods

Computational approaches to metaphor interpretation
Knowledge-based methods
Metaphor interpretation by explanation (SlipNet)
Metaphor interpretation as paraphrasing (supervised and unsupervised)
Challenges in metaphor generation

Applications of metaphor processing systems
Metaphor in machine translation 
Metaphor in opinion mining
Metaphor in information retrieval
Metaphor in educational applications
Metaphor in social science
Metaphor in psychology

Metaphor and other types of figurative language
Metaphor and blending
Metaphor and simile
Metaphor and analogy
Metaphor and irony

We look forward to seeing you at the tutorial!

Katia and Tony

Message diffuse par la liste Langage Naturel <LN at>
Informations, abonnement :
English version       : 
Archives                 :

La liste LN est parrainee par l'ATALA (Association pour le Traitement
Automatique des Langues)
Information et adhesion  :

ATALA décline toute responsabilité concernant le contenu des
messages diffusés sur la liste LN

More information about the Ln mailing list