Collocation lists as instruments for metaphor detection in corpora

Sardinha, Tony Berber

doi:10.1590/s0102-44502006000200002

Cited by 3 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Ferrari (1996) proposed an approach based on the analysis of syntactic patterns and used textual cues such as metaphorically, figuratively and like to detect metaphors. The works in (Sardinha, 2002;Sardinha, 2006) suggested using corpus-based metrics such as collocations list, word frequency and semantic-distance for metaphor detection. Turney et al (2011) observed that metaphorical usage is directly correlated with the degree of abstractness in a word's contextual usage.…”

Section: Some Researchersmentioning

confidence: 99%

Supervised Metaphor Detection using Conditional Random Fields

Rai¹,

Chakraverty²,

Tayal³

2016

Proceedings of the Fourth Workshop on Metaphor in NLP

View full text Add to dashboard Cite

In this paper, we propose a novel approach for supervised classification of linguistic metaphors in an open domain text using Conditional Random Fields (CRF). We analyze CRF based classification model for metaphor detection using syntactic, conceptual, affective, and word embeddings based features which are extracted from MRC Psycholinguistic Database (MRCPD) and WordNet-Affect. We use word embeddings given by Huang et al. to capture information such as coherence and analogy between words. To tackle the bottleneck of limited coverage of psychological features in MRCPD, we employ synonymy relations from WordNet ®. A comparison of our approach with previous approaches shows the efficacy of CRF classifier in detecting metaphors. The experiments conducted on VU Amsterdam metaphor corpus provides an accuracy of more than 92% and Fmeasure of approximately 78%. Results shows that inclusion of conceptual features improves the recall by 5% whereas affective features do not have any major impact on metaphor detection in open text.

show abstract

Section: Some Researchersmentioning

confidence: 99%

Supervised Metaphor Detection using Conditional Random Fields

Rai¹,

Chakraverty²,

Tayal³

2016

Proceedings of the Fourth Workshop on Metaphor in NLP

View full text Add to dashboard Cite

show abstract

“…Ao buscar apreender metáforas em corpora, partimos do princípio de que, assim como acontece com outras estruturas linguísticas, é possível identificar padrões de ocorrência também nas metáforas, tais como o uso recorrente de palavras de um determinado campo semântico para referir domínios conceptuais (por exemplo, 'luta', 'guerra', 'batalha', 'guerreira', 'heroína' [guerra]; ou, ainda, 'viagem', 'caminho', 'estrada', 'percurso' [viagem]). A pesquisa em corpora permite, também, identificar os padrões de combinações (colocados) recorrentes nas metáforas (BERBER SARDINHA, 2006, 2012.…”

Section: Introductionunclassified

“Quero que vocês me acompanhem nessa jornada”: análise da emergência de metáforas em narrativas sobre o câncer de mama a partir de estratégias de Linguística de Corpus / “I want you to come with me in this journey”: analysis of the emergence of metaphors in breast cancer narratives based on Corpus Linguistics strategies

Salgado¹,

Vanin

Gomes

et al. 2021

RELIN

View full text Add to dashboard Cite

show abstract

Using Figurative Language

Colston

2015

View full text Add to dashboard Cite

Using Figurative Language presents results from a multidisciplinary decades-long study of figurative language that addresses the question, 'Why don't people just say what they mean?' This research empirically investigates goals speakers or writers have when speaking (writing) figuratively, and concomitantly, meaning effects wrought by figurative language usage. These 'pragmatic effects' arise from many kinds of figurative language including metaphors (e.g. 'This computer is a dinosaur'), verbal irony (e.g. 'Nice place you got here'), idioms (e.g. 'Bite the bullet'), proverbs (e.g. 'Don't put all your eggs in one basket') and others. Reviewed studies explore mechanisms - linguistic, psychological, social and others - underlying pragmatic effects, some traced to basic processes embedded in human sensory, perceptual, embodied, cognitive, social and schematic functioning. The book should interest readers, researchers and scholars in fields beyond psychology, linguistics and philosophy that share interests in figurative language - including language studies, communication, literary criticism, neuroscience, semiotics, rhetoric and anthropology.

show abstract

Collocation lists as instruments for metaphor detection in corpora

Cited by 3 publications

References 13 publications

Supervised Metaphor Detection using Conditional Random Fields

Supervised Metaphor Detection using Conditional Random Fields

Using Figurative Language

Contact Info

Product

Resources

About