We explore the ConceptNet 4 common-sense knowledge base using the tools of network analysis. This exploration is interesting in its own right, but a primary goal is developing methods that are potentially useful for improving the performance of the knowledge base on various common-sense reasoning tasks. ConceptNet has been used by its creators and others for various tasks, and ConceptNet 4 has ...

In this paper, we propose commonsense knowledge enhanced embeddings (KEE) for solving the Pronoun Disambiguation Problems (PDP). The PDP task we investigate in this paper is a complex coreference resolution task which requires the utilization of commonsense knowledge. This task is a standard first round test set in the 2016 Winograd Schema Challenge1. In this task, traditional linguistic featur...

When general purpose software agents fail, it’s often because they’re brittle and need more background commonsense knowledge. In this paper we present relation properties as a valuable type of commonsense knowledge that can be automatically inferred at scale by reading the Web. People base many commonsense inferences on their knowledge of relation properties such as functionality, transitivity,...

The crucial part of uncertain reasoning is not the process of forming a best conclusion from the facts known so far, but rather of knowing where to turn when those facts fall short. When confronted by a paradox such as the Nixon Diamond, or the Yale shooting problem, commonsense dictates that more information is required. We argue that while the concept of minimal knowledge is in some sense fun...

The crucial part of uncertain reasoning is not the process of forming a best conclusion from the facts known so far, but rather of knowing where to turn when those facts fall short. When confronted by a paradox such as the Nixon Diamond, or the Yale shooting problem, commonsense dictates that more information is required. We argue that while the concept of minimal knowledge is in some sense fun...

Existing deep learning-based methods for detecting fake news are uninterpretable, and they do not use external knowledge related to the news. As a result, authors of paper propose graph matching-based approach combined with detect The focuses on extracting commonsense from texts through extraction, background content entity extraction disambiguation, using as evidence identification, interpreti...

Abstractive dialogue summarization is the task of capturing highlights a and rewriting them into concise version. In this paper, we present novel multi-speaker summarizer to demonstrate how large-scale commonsense knowledge can facilitate understanding summary generation. detail, consider utterance as two different types data design Dialogue Heterogeneous Graph Network (D-HGN) for modeling both...

Knowledge acquisition is the essential process of extracting and encoding knowledge, both domain specific and commonsense, to be used in intelligent systems. While many large knowledge bases have been constructed, none is close to complete. This paper presents an approach to improving a knowledge base efficiently under resource constraints. Using a guiding knowledge base, questions are generate...

Commonsense knowledge representation and reasoning is key for tasks such as natural language understanding. Since common-sense consists of information that humans take for granted, however, gathering it is an extremely difficult task. The game engine for commonsense knowledge acquisition (GECKA) aims to collect common-sense from game designers through the development of serious games. GECKA mer...

The Winograd Schema Challenge has recently been proposed as an alternative to the Turing test. A Winograd Schema consists of a sentence and question pair such that the answer to the question depends on the resolution of a definite pronoun in the sentence. The answer is fairly intuitive for humans but is difficult for machines because it requires commonsense knowledge about words or concepts in ...