Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

13

ACL
2009

favoriteEmaildiscussreport

113views Computational Linguistics» more ACL 2009»

Detecting Compositionality in Multi-Word Expressions

13 years 2 months ago

Detecting Compositionality in Multi-Word Expressions

Download www-users.cs.york.ac.uk

Identifying whether a multi-word expression (MWE) is compositional or not is important for numerous NLP applications. Sense induction can partition the context of MWEs into semantic uses and therefore aid in deciding compositionality. We propose an unsupervised system to explore this hypothesis on compound nominals, proper names and adjective-noun constructions, and evaluate the contribution of sense induction. The evaluation set is derived from WordNet in a semisupervised way. Graph connectivity measures are employed for unsupervised parameter tuning.

Ioannis Korkontzelos, Suresh Manandhar

Real-time Traffic

ACL 2009 | Computational Linguistics | Graph Connectivity Measures | Numerous Nlp Applications | Sense Induction |

claim paper

Related Content

» Increasing Expressiveness of Composite Events Using Parameter Contexts

» Temporal order optimizations of incremental joins for composite event detection

» Composite Events for Active Databases Semantics Contexts and Detection

» Filtering Features for a Composite Event Definition Language

» Correlation and prediction of gene expression level from amino acid and dipeptide composit...

» Occluded Facial Expression Tracking

» Error Mining for Regular Expression Patterns

» An event detection algebra for reactive systems

» Querying Composite Objects in Semistructured Data

Post Info
More Details (n/a)

Added	16 Feb 2011
Updated	16 Feb 2011
Type	Journal
Year	2009
Where	ACL
Authors	Ioannis Korkontzelos, Suresh Manandhar

Comments (0)