Papers by Rachel Keraron

2 papers
Synthetic Data Augmentation for Zero-Shot Cross-Lingual Question Answering (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods to improve Question Answering performance on non-English data are expensive and limited to evaluation set.
Approach: They propose a method to improve Question Answering performance without additional annotations by leveraging Question Generation models to produce synthetic samples in a cross-lingual fashion.
Outcome: The proposed method outperforms baselines on four datasets in English significantly . the proposed model outperformed baselines in english and is comparable to the validation set of the original SQuAD.
Project PIAF: Building a Native French Question-Answering Dataset (2020.lrec-1)

Copied to clipboard

Challenge: a lack of data for non-English languages is limiting the development of downstream tasks such as Question Answering.
Approach: They propose to collect a native French Question Answering Dataset using a participatory setup.
Outcome: The proposed tool allows volunteers to participate in crowdsourced annotations in French.

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