DISCOS: Bridging the Gap between Discourse Knowledge and Commonsense Knowledge

by   Tianqing Fang, et al.

Commonsense knowledge is crucial for artificial intelligence systems to understand natural language. Previous commonsense knowledge acquisition approaches typically rely on human annotations (e.g., ATOMIC) or text generation models (e.g., 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 too well to generate novel knowledge in high quality, thus still suffering from coverage problems. 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 mines expensive complex commonsense knowledge from more affordable linguistic knowledge resources. Experiments demonstrate that we can successfully convert discourse knowledge over eventualities from ASER, a large-scale discourse knowledge graph, into inferential 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.


page 1

page 2

page 3

page 4


TransOMCS: From Linguistic Graphs to Commonsense Knowledge

Commonsense knowledge acquisition is a key problem for artificial intell...

ASER: Towards Large-scale Commonsense Knowledge Acquisition via Higher-order Selectional Preference over Eventualities

Commonsense knowledge acquisition and reasoning have long been a core ar...

COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs

Recent years have brought about a renewed interest in commonsense repres...

Paragraph-Level Commonsense Transformers with Recurrent Memory

Human understanding of narrative texts requires making commonsense infer...

ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning

We present ATOMIC, an atlas of everyday commonsense reasoning, organized...

Scarecrow: A Framework for Scrutinizing Machine Text

Modern neural text generation systems can produce remarkably fluent and ...

HypoGen: Hyperbole Generation with Commonsense and Counterfactual Knowledge

A hyperbole is an intentional and creative exaggeration not to be taken ...