Semantic classifications for detection of verb metaphors

Klebanov, Beata Beigman; Leong, Chee Wee; Gutiérrez, E. Dario; Shutova, Ekaterina; Flor, Michael

doi:10.18653/v1/p16-2017

Cited by 47 publications

(43 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We follow the approach proposed by Klebanov et al (2016) to use the lemmatizing strategy. The first module in our model is a lemmatizer.…”

Section: Cnn-lstm Model With Crf or Softmax Inferencementioning

confidence: 99%

“…Existing computational approaches to detect metaphors are mainly based on lexicons (Mohler et al, 2013;Dodge et al, 2015) and supervised methods (Turney et al, 2011;Heintz et al, 2013;Klebanov et al, 2014Klebanov et al, , 2015Klebanov et al, , 2016. Lexiconbased methods are free from data annotation, but they are unable to detect novel metaphorical usages and capture the contextual information.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Neural Metaphor Detecting with CNN-LSTM Model

Wu¹,

Wu²,

Chen³

et al. 2018

Proceedings of the Workshop on Figurative Language Processing

View full text Add to dashboard Cite

Metaphors are figurative languages widely used in daily life and literatures. It's an important task to detect the metaphors evoked by texts. Thus, the metaphor shared task is aimed to extract metaphors from plain texts at word level. We propose to use a CNN-LSTM model for this task. Our model combines CNN and LSTM layers to utilize both local and long-range contextual information for identifying metaphorical information. In addition, we compare the performance of the softmax classifier and conditional random field (CRF) for sequential labeling in this task. We also incorporated some additional features such as part of speech (POS) tags and word cluster to improve the performance of model. Our best model achieved 65.06% F-score in the all POS testing subtask and 67.15% in the verbs testing subtask.

show abstract

“…We follow the approach proposed by Klebanov et al (2016) to use the lemmatizing strategy. The first module in our model is a lemmatizer.…”

Section: Cnn-lstm Model With Crf or Softmax Inferencementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Neural Metaphor Detecting with CNN-LSTM Model

Wu¹,

Wu²,

Chen³

et al. 2018

Proceedings of the Workshop on Figurative Language Processing

View full text Add to dashboard Cite

show abstract

“…The lemmatized form of the verb has improved generalization in other systems(Beigman Klebanov et al, 2016).3 We use the default parameters of the XGBoost package: a maximum tree depth of 3, 100 trees, and η = 0.1.…”

mentioning

confidence: 99%

Learning Outside the Box: Discourse-level Features Improve Metaphor Identification

Mu¹,

Yannakoudakis

Shutova³

2019

Proceedings of the 2019 Conference of the North

Self Cite

View full text Add to dashboard Cite

Most current approaches to metaphor identification use restricted linguistic contexts, e.g. by considering only a verb's arguments or the sentence containing a phrase. Inspired by pragmatic accounts of metaphor, we argue that broader discourse features are crucial for better metaphor identification. We train simple gradient boosting classifiers on representations of an utterance and its surrounding discourse learned with a variety of document embedding methods, obtaining near state-of-the-art results on the 2018 VU Amsterdam metaphor identification task without the complex metaphorspecific features or deep neural architectures employed by other systems. A qualitative analysis further confirms the need for broader context in metaphor processing.

show abstract

“…In their baseline paper (Beigman Klebanov et al, 2016) demonstrate the positive influence of features derived from the WordNet dictionary.…”

Section: Adding General Inquirer Datamentioning

confidence: 99%

Detecting Figurative Word Occurrences Using Recurrent Neural Networks

Mykowiecka¹,

Wawer²,

Marciniak³

2018

Proceedings of the Workshop on Figurative Language Processing

View full text Add to dashboard Cite

The paper addresses the detection of figurative usage of words in English text. The chosen method was to use neural nets fed by pre-trained word embeddings. The obtained results show that simple solutions, based on word embeddings only, are comparable to complex solutions, using additional information as a result of taggers or a psycholinguistic database. This approach can be easily applied to other languages, even less-studied, for which we only have raw texts available.

show abstract

Semantic classifications for detection of verb metaphors

Cited by 47 publications

References 15 publications

Neural Metaphor Detecting with CNN-LSTM Model

Neural Metaphor Detecting with CNN-LSTM Model

Learning Outside the Box: Discourse-level Features Improve Metaphor Identification

Detecting Figurative Word Occurrences Using Recurrent Neural Networks

Contact Info

Product

Resources

About