Papers by Jacopo Urbani

2 papers
Tribrid: Stance Classification with Neural Inconsistency Detection (2021.emnlp-main)

Copied to clipboard

Challenge: a new neural architecture can be used to classify stances on social media without relying on linguistic features.
Approach: They propose a neural architecture where the input also includes automatically generated negated perspectives over a given claim.
Outcome: The proposed model improves on the original input and removes doubtful predictions over the retained information.
A Deep Dive into Word Sense Disambiguation with LSTM (C18-1)

Copied to clipboard

Challenge: LSTM-based language models have been shown effective in Word Sense Disambiguation (WSD) but neither the training data nor the source code was released.
Approach: They propose to use LSTM-based language models to perform Word Sense Disambiguation (WSD) using openly available datasets and software.
Outcome: The proposed method returned state-of-the-art performance in several benchmarks, but neither the training data nor the source code were released.

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