Papers by Felipe Urra

1 papers
Multilingual Corpus Creation for Multilingual Semantic Similarity Task (2020.lrec-1)

Copied to clipboard

Challenge: Existing monolingual corpora are limited for semantic similarity tasks . a major factor affecting the success of deep neural networks is the availability of large and good quality corpors.
Approach: They propose a semi-automated framework to create a multilingual corpus for a semantic similarity task.
Outcome: The proposed framework can be applied to government, insurance, banking domains provided a bilingual website exists.

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