Search Results for author: Soumya Ray

Found 9 papers, 2 papers with code

Hybrid Semantics for Goal-Directed Natural Language Generation

no code implementations ACL 2022 Connor Baumler, Soumya Ray

In particular, we consider using two meaning representations, one based on logical semantics and the other based on distributional semantics.

Text Generation

Beyond Fair Pay: Ethical Implications of NLP Crowdsourcing

no code implementations NAACL 2021 Boaz Shmueli, Jan Fell, Soumya Ray, Lun-Wei Ku

Ethical discussion regarding the use of crowdworkers within the NLP research community is typically confined in scope to issues related to labor conditions such as fair pay.

Ethics Misconceptions

SocialNLP EmotionGIF 2020 Challenge Overview: Predicting Reaction GIF Categories on Social Media

no code implementations24 Feb 2021 Boaz Shmueli, Lun-Wei Ku, Soumya Ray

We present an overview of the EmotionGIF2020 Challenge, held at the 8th International Workshop on Natural Language Processing for Social Media (SocialNLP), in conjunction with ACL 2020.

Reactive Supervision: A New Method for Collecting Sarcasm Data

1 code implementation EMNLP 2020 Boaz Shmueli, Lun-Wei Ku, Soumya Ray

Sarcasm detection is an important task in affective computing, requiring large amounts of labeled data.

Sarcasm Detection

Bayesian Hierarchical Reinforcement Learning

no code implementations NeurIPS 2012 Feng Cao, Soumya Ray

We describe an approach to incorporating Bayesian priors in the maxq framework for hierarchical reinforcement learning (HRL).

Hierarchical Reinforcement Learning reinforcement-learning

Multiple-Instance Active Learning

no code implementations NeurIPS 2007 Burr Settles, Mark Craven, Soumya Ray

In particular, we consider the case in which an MI learner is allowed to selectively query unlabeled instances in positive bags.

Active Learning text-classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.