Papers by Samuel Louvan

2 papers
IndoNLI: A Natural Language Inference Dataset for Indonesian (2021.emnlp-main)

Copied to clipboard

Challenge: XLM-R model outperforms other pre-trained models in annotated data.
Approach: They adapt the data collection protocol for MNLI and collect 18K sentence pairs annotated by crowd workers and experts.
Outcome: The proposed dataset outperforms other pre-trained models on the expert-annotated data.
Recent Neural Methods on Slot Filling and Intent Classification for Task-Oriented Dialogue Systems: A Survey (2020.coling-main)

Copied to clipboard

Challenge: In recent years, neural-network based models have been used for a wide range of tasks, including slot filling and intent classification.
Approach: They propose three neural architectures to model slot filling and intent classification . they propose independent models, joint models and transfer learning models that exploit the mutual benefit of the two tasks simultaneously and scale the model to new domains.
Outcome: The proposed models model SF and IC separately, exploit mutual benefit of the two tasks simultaneously and scale the model to new domains.

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