Learning to Recognize Affective Polarity in Similes

Qadir, Ashequl; Riloff, Ellen; Walker, Marilyn A.

doi:10.18653/v1/d15-1019

Cited by 30 publications

(37 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For the second layer, they link these common-sense qualities in a support graph [34]. Qadir et al [26] use lexical features, semantic features and sentiment features to infer the affective polarity of simile in twitters to build classifiers. Qadir et al [27] infer implicit properties by using syntactic structure, dictionary definitions, statistical co-occurrence and word embeddings.…”

Section: Metaphor Analysismentioning

confidence: 99%

A hybrid representation-based simile component extraction

Zhang

et al. 2020

Neural Comput & Applic

View full text Add to dashboard Cite

Simile, a special type of metaphor, can help people to express their ideas more clearly. Simile component extraction is to extract tenors and vehicles from sentences. This task has a realistic significance since it is useful for building cognitive knowledge base. With the development of deep neural networks, researchers begin to apply neural models to component extraction. Simile components should be in cross-domain. According to our observations, words in cross-domain always have a different concept. Thus, concept is important when identifying whether two words are simile components or not. However, existing models do not integrate concept into their models. It is difficult for these models to identify the concept of a word. What's more, corpus about simile component extraction is limited. There are a number of rare words or unseen words and the representations of these words are always nor proper enough. Exiting models can hardly extract simile components accurately when there are low frequency words in sentences. To solve

show abstract

Section: Metaphor Analysismentioning

confidence: 99%

A hybrid representation-based simile component extraction

Zhang

et al. 2020

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…Qadir et al (2016) used syntactic structures, dictionary definitions, statistical cooccurrence, and word embedding vectors to infer implicit properties in similes. Qadir et al (2015) also built a classifier with lexical features, semantic features, and sentiment features to infer the affective polarity of simile in twitters. Veale and Hao (2007) and Veale (2012a) utilized knowledge generated by similes to deal with metaphor and irony, and Veale (2012b) built a lexical stereotype model from similes.…”

Section: Metaphor/simile Analysismentioning

confidence: 99%

Neural Multitask Learning for Simile Recognition

Liu¹,

Hu²,

Song³

et al. 2018

Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

Simile is a special type of metaphor, where comparators such as like and as are used to compare two objects. Simile recognition is to recognize simile sentences and extract simile components, i.e., the tenor and the vehicle. This paper presents a study of simile recognition in Chinese. We construct an annotated corpus for this research, which consists of 11.3k sentences that contain a comparator. We propose a neural network framework for jointly optimizing three tasks: simile sentence classification, simile component extraction and language modeling. The experimental results show that the neural network based approaches can outperform all rule-based and feature-based baselines. Both simile sentence classification and simile component extraction can benefit from multitask learning. The former can be solved very well, while the latter is more difficult.

show abstract

“…A simile is a figure of speech that directly compares two things using connecting words such as ''like'' or ''as'' [10]. Recently, there are more and more researches about similes, which include sentiment analysis [12], [13], implicit properties inference [14] and components recognition in simile sentences [10]. In this paper, we focus on the simile recognition task.…”

Section: Related Work a Simile Analysismentioning

confidence: 99%

Combining Part-of-Speech Tags and Self-Attention Mechanism for Simile Recognition

et al. 2019

View full text Add to dashboard Cite

Simile recognition is to find simile sentences and extract the tenor and vehicle from these sentences. Previous works illustrate that tenors and vehicles are typically noun phrases. A word may have different part-of-speech (POS) labels (e.g., adjectives, adverbs, nouns, and verbs) in different sentences. It is important for the simile recognition task to identify a certain POS information for each word in a sentence. However, existing models use the same word embedding to represent a word, which cannot accurately represent the POS information of this word in different sentences. In this paper, we propose a neural network framework explicitly integrating the POS information into simile recognition task, with additional self-attention mechanism to better capture long term dependencies between any two tokens in sentences. The experimental results show that our proposed models significantly outperform previous state-of-the-art methods in the simile recognition task. We also present an analysis showing that the POS information and self-attention mechanism are effective for the simile recognition task. INDEX TERMS Simile recognition, part-of-speech, self-attention mechanism.

show abstract

Learning to Recognize Affective Polarity in Similes

Cited by 30 publications

References 17 publications

A hybrid representation-based simile component extraction

A hybrid representation-based simile component extraction

Neural Multitask Learning for Simile Recognition

Combining Part-of-Speech Tags and Self-Attention Mechanism for Simile Recognition

Contact Info

Product

Resources

About