The Power of Selecting Key Blocks with Local Pre-ranking for Long Document Information Retrieval

Autor: Li, Minghan, Popa, Diana Nicoleta, Chagnon, Johan, Cinar, Yagmur Gizem, Gaussier, Eric

On a wide range of natural language processing and information retrieval tasks, transformer-based models, particularly pre-trained language models like BERT, have demonstrated tremendous effectiveness. Due to the quadratic complexity of the self-atte

Externí odkaz: http://arxiv.org/abs/2111.09852

A Vector Space for Distributional Semantics for Entailment

Autor: Henderson, James, Popa, Diana Nicoleta

Distributional semantics creates vector-space representations that capture many forms of semantic similarity, but their relation to semantic entailment has been less clear. We propose a vector-space model which provides a formal foundation for a dist

Externí odkaz: http://arxiv.org/abs/1607.03780

The Power of Selecting Key Blocks with Local Pre-ranking for Long Document Information Retrieval.

Autor: MINGHAN LI¹ Minghan.Li@univ-grenoble-alpes.fr, POPA, DIANA NICOLETA² Eric.Gaussier@univ-grenoble-alpes.fr, CHAGNON, JOHAN³ diana.nicoleta.popa@telepathy.ai, CINAR, YAGMUR GIZEM⁴ jjrc826@uowmail.edu.au, GAUSSIER, ERIC¹ cinary@amazon.com

Publikováno v: ACM Transactions on Information Systems. Jul2023, Vol. 41 Issue 3, p1-35. 35p.

Modelling document-query interaction in a hierarchical neural model for IR

Autor: Chagnon, Johan, Popa, Diana Nicoleta, Gizem Cinar, Yagmur, Gaussier, Éric

Publikováno v: CORIA 2021
CORIA 2021, ARIA (Association Francophone de Recherche d’Information (RI) et Applications), Apr 2021, Grenoble, France. ⟨10.24348/coria.2021.court_28⟩

International audience; Recent deep approaches to information retrieval are either representation-oriented or interaction-oriented, depending on how they view the modelling of document and query representations and their interactions. We explore a hi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8e819e89aa2e6108f108abdda6625b53
https://hal.univ-grenoble-alpes.fr/hal-03367717

From lexical towards contextualized meaning representation

Autor: Popa, Diana-Nicoleta

Publikováno v: Computers and Society [cs.CY]. Université Grenoble Alpes, 2019. English. ⟨NNT : 2019GREAM037⟩

Continuous word representations (word type embeddings) are at the basis of most modern natural language processing systems, providing competitive results particularly when input to deep learning models. However, important questions are raised concern

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od_______212::afab8a84a1e2a71a9c3e206514dbd2bf
https://tel.archives-ouvertes.fr/tel-02478383/file/POPA_2019_archivage.pdf