Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Soroush Vosoughi

Soroush Vosoughi

Embedding Heterogeneous Networks into Hyperbolic Space Without Meta-path


Jun 18, 2021
Lili Wang, Chongyang Gao, Chenghan Huang, Ruibo Liu, Weicheng Ma, Soroush Vosoughi

Figure 1 for Embedding Heterogeneous Networks into Hyperbolic Space Without Meta-path
Figure 2 for Embedding Heterogeneous Networks into Hyperbolic Space Without Meta-path
Figure 3 for Embedding Heterogeneous Networks into Hyperbolic Space Without Meta-path
Figure 4 for Embedding Heterogeneous Networks into Hyperbolic Space Without Meta-path
* In proceedings of the 35th AAAI Conference on Artificial Intelligence 
  Access Paper or Ask Questions

A Survey of Data Augmentation Approaches for NLP


May 29, 2021
Steven Y. Feng, Varun Gangal, Jason Wei, Sarath Chandar, Soroush Vosoughi, Teruko Mitamura, Eduard Hovy

Figure 1 for A Survey of Data Augmentation Approaches for NLP
Figure 2 for A Survey of Data Augmentation Approaches for NLP
Figure 3 for A Survey of Data Augmentation Approaches for NLP
Figure 4 for A Survey of Data Augmentation Approaches for NLP
* Accepted to ACL 2021 Findings. GitHub repo with paper list at https://github.com/styfeng/DataAug4NLP 
  Access Paper or Ask Questions

Mitigating Political Bias in Language Models Through Reinforced Calibration


Apr 30, 2021
Ruibo Liu, Chenyan Jia, Jason Wei, Guangxuan Xu, Lili Wang, Soroush Vosoughi

Figure 1 for Mitigating Political Bias in Language Models Through Reinforced Calibration
Figure 2 for Mitigating Political Bias in Language Models Through Reinforced Calibration
Figure 3 for Mitigating Political Bias in Language Models Through Reinforced Calibration
Figure 4 for Mitigating Political Bias in Language Models Through Reinforced Calibration
* In proceedings of the 35th AAAI Conference on Artificial Intelligence 
  Access Paper or Ask Questions

BigGreen at SemEval-2021 Task 1: Lexical Complexity Prediction with Assembly Models


Apr 19, 2021
Aadil Islam, Weicheng Ma, Soroush Vosoughi

Figure 1 for BigGreen at SemEval-2021 Task 1: Lexical Complexity Prediction with Assembly Models
Figure 2 for BigGreen at SemEval-2021 Task 1: Lexical Complexity Prediction with Assembly Models
Figure 3 for BigGreen at SemEval-2021 Task 1: Lexical Complexity Prediction with Assembly Models
Figure 4 for BigGreen at SemEval-2021 Task 1: Lexical Complexity Prediction with Assembly Models
* In Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021). Colocated with ACL-IJCNLP 2021 
  Access Paper or Ask Questions

Lone Pine at SemEval-2021 Task 5: Fine-Grained Detection of Hate Speech Using BERToxic


Apr 08, 2021
Yakoob Khan, Weicheng Ma, Soroush Vosoughi

Figure 1 for Lone Pine at SemEval-2021 Task 5: Fine-Grained Detection of Hate Speech Using BERToxic
Figure 2 for Lone Pine at SemEval-2021 Task 5: Fine-Grained Detection of Hate Speech Using BERToxic
Figure 3 for Lone Pine at SemEval-2021 Task 5: Fine-Grained Detection of Hate Speech Using BERToxic
Figure 4 for Lone Pine at SemEval-2021 Task 5: Fine-Grained Detection of Hate Speech Using BERToxic
* 7 pages, 3 figures. Accepted at SemEval-2021 Workshop, ACL-IJCNLP 2021 
  Access Paper or Ask Questions

Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning


Mar 12, 2021
Jason Wei, Chengyu Huang, Soroush Vosoughi, Yu Cheng, Shiqi Xu

Figure 1 for Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning
Figure 2 for Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning
Figure 3 for Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning
Figure 4 for Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning
* To appear at NAACL 2021 
  Access Paper or Ask Questions

Feature Selection for Multivariate Time Series via Network Pruning


Feb 11, 2021
Kang Gu, Soroush Vosoughi, Temiloluwa Prioleau

Figure 1 for Feature Selection for Multivariate Time Series via Network Pruning
Figure 2 for Feature Selection for Multivariate Time Series via Network Pruning
Figure 3 for Feature Selection for Multivariate Time Series via Network Pruning
Figure 4 for Feature Selection for Multivariate Time Series via Network Pruning

  Access Paper or Ask Questions

Text Augmentation in a Multi-Task View


Jan 14, 2021
Jason Wei, Chengyu Huang, Shiqi Xu, Soroush Vosoughi

Figure 1 for Text Augmentation in a Multi-Task View
Figure 2 for Text Augmentation in a Multi-Task View
Figure 3 for Text Augmentation in a Multi-Task View
* Accepted to EACL 2021 
  Access Paper or Ask Questions

Political Depolarization of News Articles Using Attribute-aware Word Embeddings


Jan 05, 2021
Ruibo Liu, Lili Wang, Chenyan Jia, Soroush Vosoughi

Figure 1 for Political Depolarization of News Articles Using Attribute-aware Word Embeddings
Figure 2 for Political Depolarization of News Articles Using Attribute-aware Word Embeddings
Figure 3 for Political Depolarization of News Articles Using Attribute-aware Word Embeddings
Figure 4 for Political Depolarization of News Articles Using Attribute-aware Word Embeddings
* In Proceedings of the 15th International AAAI Conference on Weblogs and Social Media (ICWSM 2021) 
  Access Paper or Ask Questions

Social media data reveals signal for public consumer perceptions


Dec 26, 2020
Neeti Pokhriyal, Abenezer Dara, Benjamin Valentino, Soroush Vosoughi

Figure 1 for Social media data reveals signal for public consumer perceptions
Figure 2 for Social media data reveals signal for public consumer perceptions
Figure 3 for Social media data reveals signal for public consumer perceptions
Figure 4 for Social media data reveals signal for public consumer perceptions
* In Proceedings of the ACM International Conference on AI in Finance (ICAIF '20) 
  Access Paper or Ask Questions

Multi-modal Identification of State-Sponsored Propaganda on Social Media


Dec 24, 2020
Xiaobo Guo, Soroush Vosoughi

Figure 1 for Multi-modal Identification of State-Sponsored Propaganda on Social Media
Figure 2 for Multi-modal Identification of State-Sponsored Propaganda on Social Media
Figure 3 for Multi-modal Identification of State-Sponsored Propaganda on Social Media
Figure 4 for Multi-modal Identification of State-Sponsored Propaganda on Social Media
* Proceedings of the 25th International Conference on Pattern Recognition (ICPR 2020) 
  Access Paper or Ask Questions

Improvements and Extensions on Metaphor Detection


Dec 07, 2020
Weicheng Ma, Ruibo Liu, Lili Wang, Soroush Vosoughi

Figure 1 for Improvements and Extensions on Metaphor Detection
Figure 2 for Improvements and Extensions on Metaphor Detection
Figure 3 for Improvements and Extensions on Metaphor Detection
Figure 4 for Improvements and Extensions on Metaphor Detection

  Access Paper or Ask Questions

Dartmouth CS at WNUT-2020 Task 2: Informative COVID-19 Tweet Classification Using BERT


Dec 07, 2020
Dylan Whang, Soroush Vosoughi

Figure 1 for Dartmouth CS at WNUT-2020 Task 2: Informative COVID-19 Tweet Classification Using BERT
Figure 2 for Dartmouth CS at WNUT-2020 Task 2: Informative COVID-19 Tweet Classification Using BERT
Figure 3 for Dartmouth CS at WNUT-2020 Task 2: Informative COVID-19 Tweet Classification Using BERT
Figure 4 for Dartmouth CS at WNUT-2020 Task 2: Informative COVID-19 Tweet Classification Using BERT
* Proceedings of the 6th Workshop on Noisy User-generated Text (W-NUT) at EMNLP 2020 
  Access Paper or Ask Questions

Big Green at WNUT 2020 Shared Task-1: Relation Extraction as Contextualized Sequence Classification


Dec 07, 2020
Chris Miller, Soroush Vosoughi

Figure 1 for Big Green at WNUT 2020 Shared Task-1: Relation Extraction as Contextualized Sequence Classification
Figure 2 for Big Green at WNUT 2020 Shared Task-1: Relation Extraction as Contextualized Sequence Classification
* Proceedings of the 6th Workshop on Noisy User-generated Text (W-NUT) at EMNLP 2020 
  Access Paper or Ask Questions

An Empirical Survey of Unsupervised Text Representation Methods on Twitter Data


Dec 07, 2020
Lili Wang, Chongyang Gao, Jason Wei, Weicheng Ma, Ruibo Liu, Soroush Vosoughi

Figure 1 for An Empirical Survey of Unsupervised Text Representation Methods on Twitter Data
Figure 2 for An Empirical Survey of Unsupervised Text Representation Methods on Twitter Data
Figure 3 for An Empirical Survey of Unsupervised Text Representation Methods on Twitter Data
* In proceedings of the 6th Workshop on Noisy User-generated Text (W-NUT) at EMNLP 2020 
  Access Paper or Ask Questions

Enhanced Offensive Language Detection Through Data Augmentation


Dec 05, 2020
Ruibo Liu, Guangxuan Xu, Soroush Vosoughi

Figure 1 for Enhanced Offensive Language Detection Through Data Augmentation
Figure 2 for Enhanced Offensive Language Detection Through Data Augmentation
Figure 3 for Enhanced Offensive Language Detection Through Data Augmentation
Figure 4 for Enhanced Offensive Language Detection Through Data Augmentation
* In ICWSM 2020 Data Challenge. Online 
  Access Paper or Ask Questions

Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generation


Dec 05, 2020
Ruibo Liu, Guangxuan Xu, Chenyan Jia, Weicheng Ma, Lili Wang, Soroush Vosoughi

Figure 1 for Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generation
Figure 2 for Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generation
Figure 3 for Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generation
Figure 4 for Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generation
* In proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020). Online 
  Access Paper or Ask Questions

Embedding Node Structural Role Identity into Hyperbolic Space


Nov 03, 2020
Lili Wang, Ying Lu, Chenghan Huang, Soroush Vosoughi

Figure 1 for Embedding Node Structural Role Identity into Hyperbolic Space
Figure 2 for Embedding Node Structural Role Identity into Hyperbolic Space
Figure 3 for Embedding Node Structural Role Identity into Hyperbolic Space
* In Proceedings of the 29th ACM International Conference on Information and Knowledge Management (CIKM '20), October 19-23, 2020, Virtual Event, Ireland 
  Access Paper or Ask Questions

Towards Improved Model Design for Authorship Identification: A Survey on Writing Style Understanding


Sep 30, 2020
Weicheng Ma, Ruibo Liu, Lili Wang, Soroush Vosoughi

Figure 1 for Towards Improved Model Design for Authorship Identification: A Survey on Writing Style Understanding
Figure 2 for Towards Improved Model Design for Authorship Identification: A Survey on Writing Style Understanding
Figure 3 for Towards Improved Model Design for Authorship Identification: A Survey on Writing Style Understanding

  Access Paper or Ask Questions

Emoji Prediction: Extensions and Benchmarking


Jul 14, 2020
Weicheng Ma, Ruibo Liu, Lili Wang, Soroush Vosoughi

Figure 1 for Emoji Prediction: Extensions and Benchmarking
Figure 2 for Emoji Prediction: Extensions and Benchmarking
Figure 3 for Emoji Prediction: Extensions and Benchmarking
Figure 4 for Emoji Prediction: Extensions and Benchmarking
* In Proceedings of the 9th KDD Workshop on Issues of Sentiment Discovery and Opinion Mining (WISDOM 20). San Diego, CA, USA, 7 pages 
  Access Paper or Ask Questions

Query-Free Adversarial Transfer via Undertrained Surrogates


Jul 01, 2020
Chris Miller, Soroush Vosoughi

Figure 1 for Query-Free Adversarial Transfer via Undertrained Surrogates
Figure 2 for Query-Free Adversarial Transfer via Undertrained Surrogates
Figure 3 for Query-Free Adversarial Transfer via Undertrained Surrogates
Figure 4 for Query-Free Adversarial Transfer via Undertrained Surrogates

  Access Paper or Ask Questions

Salienteye: Maximizing Engagement While Maintaining Artistic Style on Instagram Using Deep Neural Networks


Jun 13, 2020
Lili Wang, Ruibo Liu, Soroush Vosoughi

Figure 1 for Salienteye: Maximizing Engagement While Maintaining Artistic Style on Instagram Using Deep Neural Networks
Figure 2 for Salienteye: Maximizing Engagement While Maintaining Artistic Style on Instagram Using Deep Neural Networks
Figure 3 for Salienteye: Maximizing Engagement While Maintaining Artistic Style on Instagram Using Deep Neural Networks
* Proceedings of the 2020 International Conference on Multimedia Retrieval. 2020 
  Access Paper or Ask Questions

What Are People Asking About COVID-19? A Question Classification Dataset


May 26, 2020
Jerry Wei, Chengyu Huang, Soroush Vosoughi, Jason Wei

Figure 1 for What Are People Asking About COVID-19? A Question Classification Dataset
Figure 2 for What Are People Asking About COVID-19? A Question Classification Dataset
Figure 3 for What Are People Asking About COVID-19? A Question Classification Dataset
Figure 4 for What Are People Asking About COVID-19? A Question Classification Dataset

  Access Paper or Ask Questions

Tweet2Vec: Learning Tweet Embeddings Using Character-level CNN-LSTM Encoder-Decoder


Jul 26, 2016
Soroush Vosoughi, Prashanth Vijayaraghavan, Deb Roy

Figure 1 for Tweet2Vec: Learning Tweet Embeddings Using Character-level CNN-LSTM Encoder-Decoder
Figure 2 for Tweet2Vec: Learning Tweet Embeddings Using Character-level CNN-LSTM Encoder-Decoder
Figure 3 for Tweet2Vec: Learning Tweet Embeddings Using Character-level CNN-LSTM Encoder-Decoder
* SIGIR 2016, July 17-21, 2016, Pisa. Proceedings of SIGIR 2016. Pisa, Italy (2016) 
  Access Paper or Ask Questions

DeepStance at SemEval-2016 Task 6: Detecting Stance in Tweets Using Character and Word-Level CNNs


Jun 17, 2016
Prashanth Vijayaraghavan, Ivan Sysoev, Soroush Vosoughi, Deb Roy

Figure 1 for DeepStance at SemEval-2016 Task 6: Detecting Stance in Tweets Using Character and Word-Level CNNs
Figure 2 for DeepStance at SemEval-2016 Task 6: Detecting Stance in Tweets Using Character and Word-Level CNNs
Figure 3 for DeepStance at SemEval-2016 Task 6: Detecting Stance in Tweets Using Character and Word-Level CNNs
Figure 4 for DeepStance at SemEval-2016 Task 6: Detecting Stance in Tweets Using Character and Word-Level CNNs
* SemEval 2016, San Diego, California. In Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016). San Diego, California 
  Access Paper or Ask Questions

Enhanced Twitter Sentiment Classification Using Contextual Information


May 17, 2016
Soroush Vosoughi, Helen Zhou, Deb Roy

Figure 1 for Enhanced Twitter Sentiment Classification Using Contextual Information
Figure 2 for Enhanced Twitter Sentiment Classification Using Contextual Information
Figure 3 for Enhanced Twitter Sentiment Classification Using Contextual Information
Figure 4 for Enhanced Twitter Sentiment Classification Using Contextual Information
* EMNLP 2015 workshop, WASSA 2015, Lisbon, Portugal. In proceedings of the IEEE ICDM 2015 workshop on Event Analytics using Social Media Data (EASM). Atlantic City, New Jersey 
  Access Paper or Ask Questions

Digital Stylometry: Linking Profiles Across Social Networks


May 17, 2016
Soroush Vosoughi, Helen Zhou, Deb Roy

Figure 1 for Digital Stylometry: Linking Profiles Across Social Networks
Figure 2 for Digital Stylometry: Linking Profiles Across Social Networks
Figure 3 for Digital Stylometry: Linking Profiles Across Social Networks
Figure 4 for Digital Stylometry: Linking Profiles Across Social Networks
* SocInfo'15, Beijing, China. In proceedings of the 7th International Conference on Social Informatics (SocInfo 2015). Beijing, China 
  Access Paper or Ask Questions

Tweet Acts: A Speech Act Classifier for Twitter


May 17, 2016
Soroush Vosoughi, Deb Roy

Figure 1 for Tweet Acts: A Speech Act Classifier for Twitter
Figure 2 for Tweet Acts: A Speech Act Classifier for Twitter
Figure 3 for Tweet Acts: A Speech Act Classifier for Twitter
Figure 4 for Tweet Acts: A Speech Act Classifier for Twitter
* ICWSM'16, May 17-20, Cologne, Germany. In Proceedings of the 10th AAAI Conference on Weblogs and Social Media (ICWSM 2016). Cologne, Germany 
  Access Paper or Ask Questions