SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.01898 · ACL · 2020

Probabilistic Assumptions Matter: Improved Models for Distantly-Supervised Document-Level Question Answering

Hao Cheng, Ming-Wei Chang, Kenton Lee, Kristina Toutanova

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We address the problem of extractive question answering using document-level distant supervision, pairing questions and relevant documents with answer strings. We compare previously used probability space and distant supervision assumptions (assumptions on the correspondence between the weak answer string labels and possible answer mention spans). We show that these assumptions interact, and that different configurations provide complementary benefits. We demonstrate that a multiobjective model can efficiently combine the advantages of multiple assumptions and outperform the best individual formulation. Our approach outperforms previous state-of-the-art models by 4.3 points in F1 on TriviaQA-Wiki and 1.7 points in Rouge-L on NarrativeQA summaries. 1

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2005.01898")
get_code_for_paper("2005.01898")
have("2005.01898")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2005.01898.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2005.01898.svg)](https://syntology.ai/paper/2005.01898)

Connect an agent — have() is free.