Exploring the Value of Multi-View Learning for Session-Aware Query Representation

no code implementations • Findings (NAACL) 2022 • Diego Ortiz, Jose Moreno, Gilles Hubert, Karen Pinel-Sauvagnat, Lynda Tamine

Recent years have witnessed a growing interest towards learning distributed query representations that are able to capture search intent semantics.

Document Ranking MULTI-VIEW LEARNING +2

Does Structure Matter? Leveraging Data-to-Text Generation for Answering Complex Information Needs

1 code implementation • 8 Dec 2021 • Hanane Djeddal, Thomas Gerald, Laure Soulier, Karen Pinel-Sauvagnat, Lynda Tamine

In this work, our aim is to provide a structured answer in natural language to a complex information need.

Data-to-Text Generation Retrieval

TSSuBERT: Tweet Stream Summarization Using BERT

1 code implementation • 16 Jun 2021 • Alexis Dusart, Karen Pinel-Sauvagnat, Gilles Hubert

The development of deep neural networks and the emergence of pre-trained language models such as BERT allow to increase performance on many NLP tasks.

Studying Catastrophic Forgetting in Neural Ranking Models

1 code implementation • 18 Jan 2021 • Jesus Lovon-Melgarejo, Laure Soulier, Karen Pinel-Sauvagnat, Lynda Tamine

Several deep neural ranking models have been proposed in the recent IR literature.

Domain Adaptation

Rouletabille at SemEval-2019 Task 4: Neural Network Baseline for Identification of Hyperpartisan Publishers

no code implementations • SEMEVAL 2019 • Jose G. Moreno, Yoann Pitarch, Karen Pinel-Sauvagnat, Gilles Hubert

This paper describes the Rouletabille participation to the Hyperpartisan News Detection task.

General Classification Position +2