Compositionality and Distributional Semantic Models
Workshop organized as part of the European Summer School on Logic, Language and Information ESSLLI 2010 (http://esslli2010cph.info/), August 16-20 2010 (ESSLLI second week), Copenhagen
Workshop Organizers: Alessandro Lenci (alessandro.lenci at ling.unipi.it) Roberto Zamparelli (roberto.zamparelli at unitn.it)
In the last ten years distributional semantic models (DSMs), such as LSA, HAL, etc. have been quite successful at addressing semantic similarity, lexical ambiguity, lexical entailment, verb selectional restrictions and other word level relations. In this class of models the meaning of a content word is represented in terms of a distributed vector recording its pattern of cooccurrences (sometimes, in specific syntactic relations) with other content words within a corpus. Different types of semantic tasks and phenomena are then modeled in terms of linear algebra operations on distributional vectors.
A central question about DSMs is whether and how distributional vectors can also be used in the compositional construction of meaning for constituents larger than words, and ultimately for sentences or discourses -- the traditional domains of denotation-based formal semantics. Being able to model key aspects of semantic composition represents a crucial condition for DSMs to provide a more general model of meaning. Conversely, distributional representations might help to model those aspects of meaning that notoriously challenge semantic compositionality, such as semantic context-sensitivity, polysemy, predicate coercion, etc.
The workshop aims to bring together researchers in formal and computational semantics to chart this largely unexplored territory.
The following is a non-exhaustive list of issues that submissions to the workshop might address:
- Is it possible, and useful, to use Distributional Semantic Models to
assign a semantic representation to constituents (e.g. phrases,
- How can the notion of predication be interpreted in Distributional
- Can Distributional Semantic Models provide an alternative way to
solve puzzles concerning predicate-argument composition
(e.g. type-mismatch, coercion, etc.)?
- Can we use distributional models to capture argument structure and
its alternations, or the Aktionsart of a complex predicates?
- Can Distributional Semantic Models apply below the word level,
characterizing the notions of morpheme productivity and morpheme
composition? (e.g. can we capture distributionally the decreasingly
compositional meanings of "inter+breed", "inter+act", "inter+view"?)
- Can Distributional Semantic Models be used to model word meaning
interactions in modificational contexts, such as figurative
interpretations, context-sensitive sense shifts (e.g. "fast car"
vs. "fast guitarist"), etc.?
- How can polysemy and ambiguity be modelled in Distributional
Semantic Models? Which types of ambiguity could be resolved in a
DSM-based compositional process? Can this help the task of
resolving lexical and textual entailments?
- What is the right relation between the interpretation functions of
formal semantics and the distributional semantic representation
these models provide?
- What should be the most insightful relation between distributional
semantic representations of content words and the meaning of the
function words that combine with them?
- Can DSMs provide distributional correlates of constructions and
lexical classes that are known to be relevant in formal semantics?
(e.g. distributional models of bare plurals, the count vs. mass
distinction, generic vs. episodic predicates, etc.).
- Similarly, can these models capture different types of reference
(e.g. nouns or noun phrases that refer to objects, to kinds, to
events, to facts or propositions, etc.).
Authors are invited to submit an EXTENDED ABSTRACT for a 20-minute presentation (followed by a 10 minute discussion).
* not exceed 3 pages, including all figures and references. * be in pdf * be submitted using the Easychair interface at the URL:
http://www.easychair.org/conferences/?conf=distcomp2010 * be anonymous and, therefore, accompanied by information containing: author name(s), affiliation(s), e-mail and postal address(es), and the title of the paper (these can be filled in at the Easychair site)
The submissions will be reviewed anonymously by the workshop's programme committee. Details will be specified on the workshop homepage (http://clic.cimec.unitn.it/roberto/ESSLLI10-dsm-workshop/)
The abstracts accepted for presentation will appear in the ESSLLI web site. We are inquiring about the possibility to publish the final workshop papers, either as part of the ESSLLI proceedings or in a separate form.
Marco Baroni (University of Trento) Gemma Boleda (Universitat Politecnica de Catalunya) Katrin Erk (University of Texas) Stefan Evert (University of Osnabrueck) Graham Katz (Georgetown University) Alessandro Lenci(University of Pisa) (co-organizer) Louise McNally (Universitat Pompeu Fabra) James Pustejovsky (Brandeis University) Sebastian Pado (IMS, Stuttgart) Magnus Sahlgren (Swedish Institute of Computer Science) Gabriel Sandu (University of Helsinki) Sabine Schulte im Walde (University of Stuttgart) Hinrich Schütze (University of Stuttgart) Peter Turney (National Research Council Canada) Roberto Zamparelli (University of Trento) (co-organizer)
All workshop participants, including the authors, are required to register for ESSLLI.
Apr 12, 2010: Deadline for submission May 24, 2010: Notification Jun 1, 2010: Deadline for early registration to ESSLLI June 30, 2010: Final programme August 16-20, 2010: Workshop