Difference between revisions of "Models of metaphor in NLP"

Revision as of 18:39, 7 October 2012

Citation

E. Shutova. 2010. Models of Metaphor in NLP. In Proceedings of ACL 2010, Uppsala, Sweden.

Online version

Introduction

This is a review paper of modeling metaphors in NLP. The author devised it into two main tasks: "metaphor recognition" and "metaphor interpretation".

Metaphor Recognition

Met* System (Fass, 1991)

First attempt to identify and interpret metaphorical expression
Using selectional preference and hand-coded knowledge base
3-Stage Approaches

Detect selectional preference violation
If find violations, tested for being a metonymic relation using hand-coded patterns
If not metonymy, search the knowledge base for a relevant analogy in order to discriminate metaphorical relations

Problem

Detects any kind of non-literalness in language (metaphors, metonymies and others), and not only metaphors
Fail to detect high conventionality of metaphor

Goatly (1997)

Identify a set of linguistic cues indicate metaphor
- metaphorically speaking, utterly, completely, so to speak and, surprisingly, literally.

Peters & Peters (2000)

Detect figurative language in the WordNet
Search for systematic polysemy, which allows to capture metonymic and metaphorical relations

CorMet System (Mason, 2004)

The first attempt for source-target domain mapping
A corpus-based approach to find systematic variations in domain-specific selectional preferences
Take Master Metaphor List (Lakoff et al., 1991) as baseline, and achieve an accuracy

of 77% (judged by human)

TroFi System(Birke & Sarkar, 2006)

Gedigan et al. (2006)

Krishnakumaran & Zhu (2007)

Metaphor Interpretation

MIDAS System (Martin, 1990)

KARMA System (Narayanan, 1997), ATT-Meta (Barnden and Lee, 2002)

Veale and Hao (2008)

Shutova (2010)

Metaphor Resources

Metaphor Annotation in Corpora

Metaphor & Polysemy

Metaphor Identification

Pragglejaz Procedure

Source - Target Domain Vocabulary

Annotating Source and target Domains

Related papers

The widely cited Pang et al EMNLP 2002 paper was influenced by this paper - but considers supervised learning techniques. The choice of movie reviews as the domain was suggested by the (relatively) poor performance of Turney's method on movies.

An interesting follow-up paper is Turney and Littman, TOIS 2003 which focuses on evaluation of the technique of using PMI for predicting the semantic orientation of words.

@@ Line 35: / Line 35: @@
 === CorMet System (Mason, 2004) ===
-* The *first attempt for source-target domain mapping*
+* The '''first attempt for source-target domain mapping'''
+* A corpus-based approach to find systematic variations in '''domain-specific selectional preferences'''
-This is done by
+* Take Master Metaphor List (Lakoff et al., 1991) as baseline, and achieve an accuracy
-“finding systematic variations in domain-specific
+of 77% (judged by human)
-selectional preferences, which are inferred from
-large, dynamically mined Internet corpora”. For
-example, Mason collects texts from the LAB domain
-and the FINANCE domain, in both of which
-pour would be a characteristic verb. In the LAB
-domain pour has a strong selectional preference
-for objects of type liquid, whereas in the FINANCE
-domain it selects for money. From this
-Mason’s system infers the domain mapping FINANCE
-– LAB and the concept mapping money
-– liquid. He compares the output of his system
-against the Master Metaphor List (Lakoff et al.,
-) containing hand-crafted metaphorical mappings
-between concepts. Mason reports an accuracy
-of 77%, although it should be noted that as
-any evaluation that is done by hand it contains an
-element of subjectivity.
 === TroFi System(Birke & Sarkar, 2006) ===