Work

Multi-Step Inference for Reasoning Over Paragraphs

Year: 2020

Type: conference-paper

Abstract: Complex reasoning over text requires understanding and chaining together free-form predicates and logical connectives.Prior work has largely tried to do this either symbolically or with black-box transformers.We present a middle ground between these two extremes: a compositional model reminiscent of neural module networks that can perform chained logical reasoning.This model first finds relevant sentences in the context and then chains them together using neural modules.Our model gives significant performance improvements (up to 29% relative error reduction when combined with a reranker) on ROPES, a recentlyintroduced complex reasoning dataset.

Source: Conference on Empirical Methods in Natural Language Processing (EMNLP)

DOI: 10.18653/v1/2020.emnlp-main.245

Authors: Jiangming Liu, Matt Gardner, Shay B. Cohen, Mirella Lapata

Institutions: Allen Institute for Artificial Intelligence, University of Edinburgh

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: Horizon 2020 Framework Programme, H2020 European Research Council

Awards: G495187929, Translating from Multiple Modalities into Text