Papers by Giuseppe Rizzo
Framing Named Entity Linking Error Types (L18-1)
Copied to clipboard
| Challenge: | Named Entity Linking (NEL) and relation extraction forms the backbone of Knowledge Base Population tasks. |
| Approach: | They propose a taxonomy to frame common errors and apply it to four well-known Named Entity Linking systems. |
| Outcome: | The proposed taxonomy was applied to four well-known Named Entity Linking systems on three gold standards. |
Sanaphor++: Combining Deep Neural Networks with Semantics for Coreference Resolution (L18-1)
Copied to clipboard
Julien Plu, Roman Prokofyev, Alberto Tonon, Philippe Cudré-Mauroux, Djellel Eddine Difallah, Raphaël Troncy, Giuseppe Rizzo
| Challenge: | Coreference resolution is a challenging task in Natural Language Processing . since a few years, the biggest step forward has been made using deep neural networks . |
| Approach: | They propose to improve coreference resolution by adding semantic features to a top-level deep neural network system . they evaluate a shared task dataset and compare it to the state-of-the-art system based on Stanford deep-coref . |
| Outcome: | The proposed system achieves 1.13% gain over the CoNLL 2012 dataset and the state-of-the-art system. |
MTSI-BERT: A Session-aware Knowledge-based Conversational Agent (2020.lrec-1)
Copied to clipboard
| Challenge: | Several models have been published achieving promising results in all the major linguistic tasks. |
| Approach: | They propose to exploit a BERT-based model to handle multi-turn conversations . they propose to use PuffBot to monitor asthma patients . |
| Outcome: | The proposed model can handle multi-turn conversations, a type of conversations that differs from single-turn by the presence of multiple related interactions. |