Models of Metaphor in NLP
Shutova, Ekaterina

Article Structure

Abstract

Automatic processing of metaphor can be clearly divided into two subtasks: metaphor recognition (distinguishing between literal and metaphorical language in a text) and metaphor interpretation (identifying the intended literal meaning of a metaphorical expression).

Introduction

Our production and comprehension of language is a multilayered computational process.

Theoretical Background

Four different views on metaphor have been broadly discussed in linguistics and philosophy: the comparison view (Gentner, 1983), the interaction view (Black, 1962), (Hesse, 1966), the selectional restrictions violation view (Wilks, 1975; Wilks, 1978) and the conceptual metaphor view (Lakoff and Johnson, 1980)?

Automatic Metaphor Recognition

One of the first attempts to identify and interpret metaphorical expressions in text automatically is the approach of Fass (1991).

Automatic Metaphor Interpretation

Almost simultaneously with the work of Fass (1991), Martin (1990) presents a Metaphor Interpretation, Denotation and Acquisition System (MIDAS).

Metaphor Resources

Metaphor is a knowledge-hungry phenomenon.

Metaphor Annotation in Corpora

To reflect two distinct aspects of the phenomenon, metaphor annotation can be split into two stages: identifying metaphorical senses in text (akin word sense disambiguation) and annotating source — target domain mappings underlying the production of metaphorical expressions.

Conclusion and Future Directions

The eighties and nineties provided us with a wealth of ideas on the structure and mechanisms of the phenomenon of metaphor.

Topics

WordNet

Appears in 10 sentences as: WordNet (10) wordnets (2)
In Models of Metaphor in NLP
  1. They mine WordNet (Fellbaum, 1998) for the examples of systematic polysemy, which allows to capture metonymic and metaphorical relations.
    Page 3, “Automatic Metaphor Recognition”
  2. The authors search for nodes that are relatively high up in the WordNet hierarchy and that share a set of common word forms among their descendants.
    Page 3, “Automatic Metaphor Recognition”
  3. They use hyponymy relation in WordNet and word bigram counts to predict metaphors at a sentence level.
    Page 4, “Automatic Metaphor Recognition”
  4. The world is a stage3) they verify if the two nouns involved are in hyponymy relation in WordNet , and if they are not then this sentence is tagged as containing a metaphor.
    Page 4, “Automatic Metaphor Recognition”
  5. Thus they do not deal with literal examples as such: essentially, the distinction they are making is between the senses included in WordNet, even if they are conventional metaphors, and those not included in WordNet .
    Page 4, “Automatic Metaphor Recognition”
  6. Talking Points are a set of characteristics of concepts belonging to source and target domains and related facts about the world which the authors acquire automatically from WordNet and from the web.
    Page 4, “Automatic Metaphor Interpretation”
  7. 5EuroWordNet is a multilingual database with wordnets for several European languages (Dutch, Italian, Spanish, German, French, Czech and Estonian).
    Page 5, “Metaphor Resources”
  8. The wordnets are structured in the same way as the Princeton WordNet for English.
    Page 5, “Metaphor Resources”
  9. WordNet (Lonneker and Eilts, 2004), would undoubtedly provide a new platform for experiments and enable researchers to directly compare their results.
    Page 6, “Metaphor Resources”
  10. A number of metaphorical senses are included in WordNet , however without any accompanying semantic annotation.
    Page 6, “Metaphor Annotation in Corpora”

See all papers in Proc. ACL 2010 that mention WordNet.

See all papers in Proc. ACL that mention WordNet.

Back to top.

knowledge base

Appears in 4 sentences as: knowledge base (4)
In Models of Metaphor in NLP
  1. If the system fails to recognize metonymy, it proceeds to search the knowledge base for a relevant analogy in order to discriminate metaphorical relations from anomalous ones.
    Page 2, “Automatic Metaphor Recognition”
  2. met* then searches its knowledge base for a triple containing a hypemym of both the actual argument and the desired argument and finds (thing, use, energy_source), which represents the metaphorical interpretation.
    Page 3, “Automatic Metaphor Recognition”
  3. Veale and Hao (2008), however, did not evaluate to which extent their knowledge base of Talking Points and the associated reasoning framework are useful to interpret metaphorical expressions occurring in text.
    Page 5, “Automatic Metaphor Interpretation”
  4. One of the first attempts to create a multipurpose knowledge base of source—target domain mappings is the Master Metaphor List (Lakoff et al., 1991).
    Page 5, “Metaphor Resources”

See all papers in Proc. ACL 2010 that mention knowledge base.

See all papers in Proc. ACL that mention knowledge base.

Back to top.

bigram

Appears in 3 sentences as: bigram (3)
In Models of Metaphor in NLP
  1. They use hyponymy relation in WordNet and word bigram counts to predict metaphors at a sentence level.
    Page 4, “Automatic Metaphor Recognition”
  2. Hereby they calculate bigram probabilities of verb-noun and adjective-noun pairs (including the hyponyms/hypernyms of the noun in question).
    Page 4, “Automatic Metaphor Recognition”
  3. However, by using bigram counts over verb-noun pairs Krishnakumaran and Zhu (2007) loose a great deal of information compared to a system extracting verb-object relations from parsed text.
    Page 4, “Automatic Metaphor Recognition”

See all papers in Proc. ACL 2010 that mention bigram.

See all papers in Proc. ACL that mention bigram.

Back to top.

natural language

Appears in 3 sentences as: natural language (3)
In Models of Metaphor in NLP
  1. The use of metaphor is ubiquitous in natural language text and it is a serious bottleneck in automatic text understanding.
    Page 1, “Introduction”
  2. Their system, however, does not take natural language sentences as input, but logical expressions that are representations of small discourse fragments.
    Page 4, “Automatic Metaphor Interpretation”
  3. natural language computation, whereby manually crafted rules gradually give way to more robust corpus-based statistical methods.
    Page 8, “Conclusion and Future Directions”

See all papers in Proc. ACL 2010 that mention natural language.

See all papers in Proc. ACL that mention natural language.

Back to top.

sense disambiguation

Appears in 3 sentences as: sense disambiguation (3)
In Models of Metaphor in NLP
  1. This idea originates from a similarity-based word sense disambiguation method developed by Karov and Edelman (1998).
    Page 3, “Automatic Metaphor Recognition”
  2. To reflect two distinct aspects of the phenomenon, metaphor annotation can be split into two stages: identifying metaphorical senses in text (akin word sense disambiguation ) and annotating source — target domain mappings underlying the production of metaphorical expressions.
    Page 6, “Metaphor Annotation in Corpora”
  3. Such annotation can be viewed as a form of word sense disambiguation with an emphasis on metaphoricity.
    Page 7, “Metaphor Annotation in Corpora”

See all papers in Proc. ACL 2010 that mention sense disambiguation.

See all papers in Proc. ACL that mention sense disambiguation.

Back to top.

word sense

Appears in 3 sentences as: word sense (3)
In Models of Metaphor in NLP
  1. This idea originates from a similarity-based word sense disambiguation method developed by Karov and Edelman (1998).
    Page 3, “Automatic Metaphor Recognition”
  2. To reflect two distinct aspects of the phenomenon, metaphor annotation can be split into two stages: identifying metaphorical senses in text (akin word sense disambiguation) and annotating source — target domain mappings underlying the production of metaphorical expressions.
    Page 6, “Metaphor Annotation in Corpora”
  3. Such annotation can be viewed as a form of word sense disambiguation with an emphasis on metaphoricity.
    Page 7, “Metaphor Annotation in Corpora”

See all papers in Proc. ACL 2010 that mention word sense.

See all papers in Proc. ACL that mention word sense.

Back to top.

PDF available from www.aclweb.org.
Send us an email