Home » Publication » 24728

Dettaglio pubblicazione

2021, Proceedings of the 59th Annual Meeting of the Association for ComputationalLinguistics and the 11th International Joint Conference on NaturalLanguage Processing, {ACL/IJCNLP} 2021, (Volume 1: Long Papers), VirtualEvent, August 1-6, 2021, Pages 3091-3104

Database reasoning over text (04b Atto di convegno in volume)

Thorne James, Yazdani Majid, Saeidi Marzieh, Silvestri Fabrizio, Riedel Sebastian, Halevy Alon Y.

Neural models have shown impressive performance gains in answering queries from natural language text. However, existing works are unable to support database queries, such as "List/Count all female athletes who were born in 20th century", which require reasoning over sets of relevant facts with operations such as join, filtering and aggregation. We show that while state-of-the-art transformer models perform very well for small databases, they exhibit limitations in processing noisy data, numerical operations, and queries that aggregate facts. We propose a modular architecture to answer these database-style queries over multiple spans from text and aggregating these at scale. We evaluate the architecture using WikiNLDB, a novel dataset for exploring such queries. Our architecture scales to databases containing thousands of facts whereas contemporary models are limited by how many facts can be encoded. In direct comparison on small databases, our approach increases overall answer accuracy from 85% to 90%. On larger databases, our approach retains its accuracy whereas transformer baselines could not encode the context.
Gruppo di ricerca: Algorithms and Data Science, Gruppo di ricerca: Theory of Deep Learning
© Università degli Studi di Roma "La Sapienza" - Piazzale Aldo Moro 5, 00185 Roma