Papers by Sameera Lanka

2 papers
Studying word order through iterative shuffling (2021.emnlp-main)

Copied to clipboard

Challenge: Recent work on large language models has made this hypothesis popular . but, word order is not important enough to make sentence structure relevant .
Approach: They propose an efficient procedure that finds word order having highest likelihood under a fixed language model.
Outcome: The proposed procedure can be used to find the ordering of a bag of words having the highest likelihood under a fixed language model.
GPT Perdetry Test: Generating new meanings for new words (2021.naacl-main)

Copied to clipboard

Challenge: We create a set of nonce words and prompt GPT-3 to generate their dictionary definitions.
Approach: They create a set of nonce words and prompt GPT-3 to generate their dictionary definitions.
Outcome: The proposed model can process new words and make them 'neologisms' . it can also adapt to and extend a changing vocabulary, the authors found .

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