Improved Sentiment Detection via Label Transfer from Monolingual to Synthetic Code-Switched Text

Samanta, Bidisha; Ganguly, Niloy; Chakrabarti, Soumen

doi:10.18653/v1/p19-1343

Cited by 7 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To mitigate this issue, we can apply techniques from image forensics [88,89,90] to detect the authenticity of an image. Regarding guided instructions, for example, hate speech detection [91,92,93,94] can help to filter out malicious texts and prevent from producing controversial results with ethics concerns.…”

Section: Conclusion and Discussionmentioning

confidence: 99%

Language-Driven Image Style Transfer

Wang

2021

Preprint

View full text Add to dashboard Cite

Despite having promising results, style transfer, which requires preparing style images in advance, may result in lack of creativity and accessibility. Following human instruction, on the other hand, is the most natural way to perform artistic style transfer that can significantly improve controllability for visual effect applications. We introduce a new task-language-driven image style transfer (LDIST)-to manipulate the style of a content image, guided by a text. We propose contrastive language visual artist (CLVA) that learns to extract visual semantics from style instructions and accomplish LDIST by the patch-wise style discriminator. The discriminator considers the correlation between language and patches of style images or transferred results to jointly embed style instructions. CLVA further compares contrastive pairs of content image and style instruction to improve the mutual relativeness between transfer results. The transferred results from the same content image can preserve consistent content structures. Besides, they should present analogous style patterns from style instructions that contain similar visual semantics. The experiments show that our CLVA is effective and achieves superb transferred results on LDIST.Project website: https://ai-sub.github.io/ldist/ Preprint. Under review.

show abstract

Section: Conclusion and Discussionmentioning

confidence: 99%

Language-Driven Image Style Transfer

Wang

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Synthetic data construction is a popular direction in NLP community, which effectively helps relieve the data annotation issues, such as data scarcity [57], label imbalance [6] and cross-lingual data [25].…”

Section: Synthetic Corpus Constructionmentioning

confidence: 99%

On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Training

Fei

Chua

et al. 2022

ACM Trans. Inf. Syst.

View full text Add to dashboard Cite

Aspect-based sentiment analysis (ABSA) aims at automatically inferring the specific sentiment polarities towards certain aspects of products or services behind the social media texts or reviews, which has been a fundamental application to the real-world society. Within recent decade, ABSA has achieved extraordinarily high accuracy with various deep neural models. However, existing ABSA models with strong in-house performances may fail to generalize to some challenging cases where the contexts are variable, i.e., being low robustness to real-world environment. In this study, we propose to enhance the ABSA robustness by systematically rethinking the bottlenecks from all possible angles, including model, data and training. First, we strengthen the current best-robust syntax-aware models by further incorporating the rich external syntactic dependencies and the labels with aspect simultaneously with a universal-syntax graph convolutional network. In the corpus perspective, we propose to automatically induce high-quality synthetic training data with various types, allowing models to learn sufficient inductive bias for better robustness. Lastly, we based on the rich pseudo data perform adversarial training to enhance the resistance to the context perturbation, and meanwhile employ contrastive learning to reinforce the representations of instances with contrastive sentiments. Extensive robustness evaluations are conducted. The results demonstrate that our enhanced syntax-aware model achieves better robustness performances than all the state-of-the-art baselines. By additionally incorporating our synthetic corpus, the robust testing results are pushed with around 10% accuracy, which are then further improved by installing the advanced training strategies. In-depth analyses are presented for revealing the factors influencing the ABSA robustness.

show abstract

“…Aguilar and Solorio (2020) augment morphological clues to language models and uses them for transfer learning from English to code-switched data with labels. Samanta et al (2019) uses translation API to create synthetic code-switched text from English datasets and use this for transfer learning from English to code-switched text without labels in the codeswitched case. Qin et al (2020) use synthetically generated code-switched data to enhance zero-shot cross-lingual transfer learning.…”

Section: Related Workmentioning

confidence: 99%

Progressive Sentiment Analysis for Code-Switched Text Data

Ranjan¹,

Mekala²,

Shang³

2022

Findings of the Association for Computational Linguistics: EMNLP 2022

View full text Add to dashboard Cite

Multilingual transformer language models have recently attracted much attention from researchers and are used in cross-lingual transfer learning for many NLP tasks such as text classification and named entity recognition. However, similar methods for transfer learning from monolingual text to code-switched text have not been extensively explored mainly due to the following challenges: (1) Codeswitched corpus, unlike monolingual corpus, consists of more than one language and existing methods can't be applied efficiently, (2) Codeswitched corpus is usually made of resourcerich and low-resource languages and upon using multilingual pre-trained language models, the final model might bias towards resourcerich language. In this paper, we focus on code-switched sentiment analysis where we have a labelled resource-rich language dataset and unlabelled code-switched data. We propose a framework that takes the distinction between resource-rich and low-resource language into account. Instead of training on the entire code-switched corpus at once, we create buckets based on the fraction of words in the resource-rich language and progressively train from resource-rich language dominated samples to low-resource language dominated samples. Extensive experiments across multiple language pairs demonstrate that progressive training helps low-resource language dominated samples.

show abstract

Improved Sentiment Detection via Label Transfer from Monolingual to Synthetic Code-Switched Text

Cited by 7 publications

References 29 publications

Language-Driven Image Style Transfer

Language-Driven Image Style Transfer

On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Training

Progressive Sentiment Analysis for Code-Switched Text Data

Contact Info

Product

Resources

About