Dr. Snigdha Chaturvedi, University of North Carolina, Chapel Hill gave an invited talk on Socially aware Natural Language Processing. Dr. Chaturvedi gave the talk virtually though MS Teams on 16 November. Here the summary of  Dr. Snigdha Chaturvedi’s talk:

NLP systems have made tremendous progress in recent years but lack a human-like language understanding. This is because there is a deep connection between language and people – most text is created by people and for people. Despite this strong connection between language and people, existing NLP systems remain incognizant of the social aspects of language. In this talk, she described three ways of designing socially aware NLP systems. In the first part of the talk, she described – socially aware approach to story generation by incorporating social relationships between various people to be mentioned in the story. Dr. Chaturvedi and her team use a latent-variable-based approach that generates the story by conditioning on relationships to be exhibited in the story text using the latent variable. This latent variable-based design results in a  better and explainable generation process. In the second part of the talk, she briefly described her team’s work on uncovering inherent social bias in automatically generated stories. They use a commonsense engine to reveal how such stories learn and amplify implicit social biases, especially gender biases. In the last part of the talk, she discussed methods to alleviate social biases. Specifically, she discussed debiasing text representations grounded in information theory. Using the rate-distortion function they showed how they can remove information about sensitive attributes like race or gender from pre-trained text representations. This approach can successfully remove undesirable information while being robust to non-linear probing attacks.

 Dr. Snigdha Chaturvedi is an Assistant Professor of Computer Science at the University of North Carolina, Chapel Hill. She specialises in Natural Language Processing, emphasising narrative-like and socially aware understanding, summarization, and generation of language. Previously, she was an Assistant Professor at UC-Santa Cruz, and a postdoctoral fellow at UIUC and UPenn working with Dan Roth. She obtained her Ph.D in Computer Science from UMD in 2016, where she was advised by Hal Daume III. Her research has been supported by NSF, Amazon, and IBM.

November 2023