Papers by Shayan Hooshmand

2 papers
Context Matters for Image Descriptions for Accessibility: Challenges for Referenceless Evaluation Metrics (2022.emnlp-main)

Copied to clipboard

Challenge: Existing referenceless metrics do not take context into account, whereas contextual information is highly valued by BLV users.
Approach: They propose a contextual version of the referenceless metric CLIPScore which addresses the disconnect to the BLV data.
Outcome: The proposed evaluation metrics are based on a proof-of-concept with blind and low vision (BLV) participants.
CHoRaL: Collecting Humor Reaction Labels from Millions of Social Media Users (2021.emnlp-main)

Copied to clipboard

Challenge: Humor detection is difficult due to individualistic and cultural differences in humor perception . authors propose a framework to generate perceived humor labels on Facebook posts .
Approach: They propose a framework to generate perceived humor labels on Facebook posts . they use the naturally available user reactions to these posts to generate the labels .
Outcome: The proposed framework generates perceived humor labels on Facebook posts with no manual annotation needed.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations