SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2101.00154 · 2021

DISCOS: Bridging the Gap between Discourse Knowledge and Commonsense Knowledge

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

Commonsense knowledge is crucial for artificial intelligence systems to understand natural language. Previous commonsense knowledge acquisition approaches typically rely on human annotations (for example, ATOMIC) or text generation models (for example, COMET.) Human annotation could provide high-quality commonsense knowledge, yet its high cost often results in relatively small scale and low coverage. On the other hand, generation models have the potential to automatically generate more knowledge. Nonetheless, machine learning models often fit the training data well and thus struggle to generate high-quality novel knowledge. To address the limitations of previous approaches, in this paper, we propose an alternative commonsense knowledge acquisition framework DISCOS (from DIScourse to COmmonSense), which automatically populates expensive complex commonsense knowledge to more affordable linguistic knowledge resources. Experiments demonstrate that we can successfully convert discourse knowledge about eventualities from ASER, a large-scale discourse knowledge graph, into if-then commonsense knowledge defined in ATOMIC without any additional annotation effort. Further study suggests that DISCOS significantly outperforms previous supervised approaches in terms of novelty and diversity with comparable quality. In total, we can acquire 3.4M ATOMIC-like inferential commonsense knowledge by populating ATOMIC on the core part of ASER. Codes and data are available at https://github.com/HKUST-KnowComp/DISCOS-commonsense.

For agents

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

get_harvested_code_for_paper("2101.00154")
get_code_for_paper("2101.00154")
have("2101.00154")

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

curl https://syntology.ai/api/ran/2101.00154.json

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

[![Syntology run record](https://syntology.ai/api/ran/2101.00154.svg)](https://syntology.ai/paper/2101.00154)

Connect an agent — have() is free.