Papers by Tyler Farghly

1 papers
Span-ConveRT: Few-shot Span Extraction for Dialog with Pretrained Conversational Representations (2020.acl-main)

Copied to clipboard

Challenge: Span-ConveRT is a light-weight model for dialog slot-filling . we show consistent gains over a span extractor and a BERT-based model .
Approach: They propose a model for dialog slot-filling which frames the task as a turn-based span extraction task.
Outcome: The proposed model is especially useful for few-shot learning scenarios.

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