We extend SPLADE, a sparse information retrieval model, as our first stage ranker for the conversational task. This end-to-end approach achieves a high recall (as measure on TREC CAsT 2021). To further increase the effectiveness of our approach, we …
QuestEval is a reference-less metric used in text-to-text tasks, that compares the generated summaries directly to the source text, by automatically asking and answering questions. Its adaptation to Data-to-Text tasks is not straightforward, as it …
Summarization evaluation remains an open research problem: current metrics such as ROUGE are known to be limited and to correlate poorly with human judgments. To alleviate this issue, recent work has proposed evaluation metrics which rely on question …
In neural Information Retrieval, ongoing research is directed towards improving the first retriever in ranking pipelines. Learning dense embeddings to conduct retrieval using efficient approximate nearest neighbors methods has proven to work well. …
Due to the discrete nature of words, language GANs require to be optimized from rewards provided by discriminator networks, via reinforcement learning methods. This is a much harder setting than for continuous tasks, which enjoy gradient flows from …
Les modèles de RI basés sur les Transformers sont aujourd’hui état de l’art en Recherche d’Information ad-hoc, mais leur comportement reste encore incompris. Des travaux récents ont montré que BERT ne satisfait pas les axiomes classiques de la RI. …
Transformer-based models are nowadays state-of-the-art in adhoc Information Retrieval, but their behavior are far from being understood. Recent work has claimed that BERT does not satisfy the classical IR axioms. However, we propose to dissect the …
We introduce a novel approach for sequence decoding, Discriminative Adversarial Search (DAS), which has the desirable properties of alleviating the effects of exposure bias without requiring external metrics. Inspired by Generative Adversarial …