Leveraging Sentiment Distributions to Distinguish Figurative From Literal Health Reports on Twitter

Biddle, Rhys; Joshi, Aditya; Liu, Shaowu; Paris, Cécile; Xu, Guandong

doi:10.1145/3366423.3380198

Cited by 35 publications

(26 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(4) Most of the state-of-the-art multi-source domain adaptation methods perform better than single-source domain adaptation methods by considering domain-invariant features and fusing information across all domains. However, MDAN [83], which has 3 The first 5 points are based on Table 1, and the last point is based on Table 2.…”

Section: Results On Reviews-5 Datasetmentioning

confidence: 99%

“…Among different multimedia modalities, text, the one focused on in this paper, is the most direct and popular one [13]. Recent studies [3,11,20,35,39,69,70,76,82] have shown that deep neural networks (DNNs) achieve the state-of-the-art performance on textual sentiment analysis. However, training a DNN to maximize its capacity usually requires large-scale labeled data, which is expensive and time-consuming to obtain.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Curriculum CycleGAN for Textual Sentiment Domain Adaptation with Multiple Sources

Zhao

Xiao

Guo

et al. 2021

Proceedings of the Web Conference 2021

View full text Add to dashboard Cite

Sentiment analysis of user-generated reviews or comments on products and services in social networks can help enterprises to analyze the feedback from customers and take corresponding actions for improvement. To mitigate large-scale annotations on the target domain, domain adaptation (DA) provides an alternate solution by learning a transferable model from other labeled source domains. Existing multi-source domain adaptation (MDA) methods either fail to extract some discriminative features in the target domain that are related to sentiment, neglect the correlations of different sources and the distribution difference among different sub-domains even in the same source, or cannot reflect the varying optimal weighting during different training stages. In this paper, we propose a novel instance-level MDA framework, named curriculum cycle-consistent generative adversarial network (C-CycleGAN), to address the above issues. Specifically, C-CycleGAN consists of three components: (1) pre-trained text encoder which encodes textual input from different domains into a continuous representation space, (2) intermediate domain generator with curriculum instance-level adaptation which bridges the gap across source and target domains, and (3) task classifier trained on the intermediate domain for final sentiment classification. C-CycleGAN transfers source samples at instance-level to an intermediate domain that is closer to the target domain with sentiment semantics preserved and without losing discriminative features. Further, our dynamic instance-level weighting mechanisms can assign the optimal weights to different * Corresponding author.† Equal contribution.This paper is published under the Creative Commons Attribution 4.0 International (CC-BY 4.0) license. Authors reserve their rights to disseminate the work on their personal and corporate Web sites with the appropriate attribution.

show abstract

Section: Results On Reviews-5 Datasetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Curriculum CycleGAN for Textual Sentiment Domain Adaptation with Multiple Sources

Zhao

Xiao

Guo

et al. 2021

Proceedings of the Web Conference 2021

View full text Add to dashboard Cite

show abstract

“…This has generally been considered to be the key distinguishing property between idioms (IEs) and MWEs in general, although the boundary between IEs and non-idiom MWEs is not clearly defined. (Baldwin and Kim, 2010;Fadaee et al, 2018;Biddle et al, 2020). Metaphors are a form of figurative speech used to make an implicit comparison at an attribute level between two things seemingly unrelated on the surface.…”

Section: Realistic Evaluationmentioning

confidence: 99%

“…Borrowing the terminology from Haagsma et al (2020), we call these phrases potentially idiomatic expressions (PIEs) to account for the contextual semantic ambiguity. Indeed, prior work has identified the challenges that PIEs pose to many NLP applications, such as machine translation (Fadaee et al, 2018;Salton et al, 2014), paraphrase generation (Ganitkevitch et al, 2013), and sentiment analysis Biddle et al, 2020). Accordingly, making applications idiomaware, either by identifying them before or during the task, has been found to be effective (Korkontzelos and Manandhar, 2010;Nivre and Nilsson, 2004;Nasr et al, 2015).…”

Section: Introductionmentioning

confidence: 99%

Idiomatic Expression Identification using Semantic Compatibility

Zeng

Bhat

2021

Transactions of the Association for Computational Linguistics

View full text Add to dashboard Cite

Idiomatic expressions are an integral part of natural language and constantly being added to a language. Owing to their non-compositionality and their ability to take on a figurative or literal meaning depending on the sentential context, they have been a classical challenge for NLP systems. To address this challenge, we study the task of detecting whether a sentence has an idiomatic expression and localizing it when it occurs in a figurative sense. Prior research for this task has studied specific classes of idiomatic expressions offering limited views of their generalizability to new idioms. We propose a multi-stage neural architecture with attention flow as a solution. The network effectively fuses contextual and lexical information at different levels using word and sub-word representations. Empirical evaluations on three of the largest benchmark datasets with idiomatic expressions of varied syntactic patterns and degrees of non-compositionality show that our proposed model achieves new state-of-the-art results. A salient feature of the model is its ability to identify idioms unseen during training with gains from 1.4% to 30.8% over competitive baselines on the largest dataset.

show abstract

“…Recent studies [3,11,20,35,39,68,69,75,81] have shown that deep neural networks (DNNs) achieve the state-of-the-art performance on textual sentiment analysis. However, training a DNN to maximize its capacity usually requires large-scale labeled data, which is expensive and time-consuming to obtain.…”

Section: Introductionmentioning

confidence: 99%

Curriculum CycleGAN for Textual Sentiment Domain Adaptation with Multiple Sources

Zhao

Xiao

Guo

et al. 2020

Preprint

View full text Add to dashboard Cite

Sentiment analysis of user-generated reviews or comments on products and services on social media can help enterprises to analyze the feedback from customers and take corresponding actions for improvement. Training deep neural networks for textual sentiment analysis requires large-scale labeled data, which is expensive and time-consuming to obtain. Domain adaptation (DA) provides an alternate solution by learning a transferable model from another labeled source domain to the unlabeled or sparsely labeled target domain. Since the labeled data may be from multiple sources, multi-source domain adaptation (MDA) would be more practical to effectively exploit the complementary information from different domains. Existing MDA methods for textual sentiment analysis mainly focus on extracting domain-invariant features of different domains, aligning each source and the target separately, or assigning weights to the source samples statically. However, they might fail to extract some discriminative features in the target domain that are related to sentiment, neglect the correlations of different sources as well as the distribution difference among different subdomains even in the same source, and cannot reflect the varying optimal weighting during different training stages.In this paper, we propose an instance-level multi-source domain adaptation framework, named curriculum cycle-consistent generative adversarial network (C-CycleGAN), to address the above issues. Specifically, C-CycleGAN consists of three components: (1) pre-trained text encoder which encodes textual input from different domains into a continuous representation space, (2) intermediate * Corresponding author.† Equal contribution.

show abstract

Leveraging Sentiment Distributions to Distinguish Figurative From Literal Health Reports on Twitter

Cited by 35 publications

References 26 publications

Curriculum CycleGAN for Textual Sentiment Domain Adaptation with Multiple Sources

Curriculum CycleGAN for Textual Sentiment Domain Adaptation with Multiple Sources

Idiomatic Expression Identification using Semantic Compatibility

Curriculum CycleGAN for Textual Sentiment Domain Adaptation with Multiple Sources

Contact Info

Product

Resources

About