Commonsense knowledge has proven to be beneficial to a variety of application areas, including question answering and natural language understanding. Previous work explored collecting commonsense knowledge triples automatically from text to increase the coverage of current commonsense knowledge graphs. We investigate a few machine learning approaches to mining commonsense knowledge triples using dictionary term definitions as inputs and provide some initial evaluation of the results. We start from extracting candidate triples using part-of-speech tag patterns from text, and then compare the performance of three existing models for triple scoring. Our experiments show that term definitions contain some valid and novel commonsense knowledge triples for some semantic relations, and also indicate some challenges with using existing triple scoring models.

This observation--that to understand Proust's text requires knowledge of various kinds--is not a new one. We came across it before, in the context of the Cyc project. Remember that Cyc was supposed to be given knowledge corresponding to the whole of consensus reality, and the Cyc hypothesis was that this would yield human-level general intelligence. Researchers in knowledge-based AI would be keen for me to point out to you that, decades ago, they anticipated exactly this issue. But it is not obvious that just continuing to refine deep learning techniques will address this problem.

Commonsense knowledge is essential for many AI applications, including those in natural language processing, visual processing, and planning. Consequently, many sources that include commonsense knowledge have been designed and constructed over the past decades. Recently, the focus has been on large text-based sources, which facilitate easier integration with neural (language) models and application on textual tasks, typically at the expense of the semantics of the sources. Such practice prevents the harmonization of these sources, understanding their coverage and gaps, and may hinder the semantic alignment of their knowledge with downstream tasks. Efforts to consolidate commonsense knowledge have yielded partial success, but provide no clear path towards a comprehensive consolidation of existing commonsense knowledge. The ambition of this paper is to organize these sources around a common set of dimensions of commonsense knowledge. For this purpose, we survey a wide range of popular commonsense sources with a special focus on their relations. We consolidate these relations into 13 knowledge dimensions, each abstracting over more specific relations found in sources. This consolidation allows us to unify the separate sources and to compute indications of their coverage, overlap, and gaps with respect to the knowledge dimensions. Moreover, we analyze the impact of each dimension on downstream reasoning tasks that require commonsense knowledge, observing that the temporal and desire/goal dimensions are very beneficial for reasoning on current downstream tasks, while distinctness and lexical knowledge have little impact. These results reveal focus towards some dimensions in current evaluation, and potential neglect of others.

When answering a question, people often draw upon their rich world knowledge in addition to the particular context. While recent works retrieve supporting facts/evidence from commonsense knowledge bases to supply additional information to each question, there is still ample opportunity to advance it on the quality of the evidence. It is crucial since the quality of the evidence is the key to answering commonsense questions, and even determines the upper bound on the QA systems performance. In this paper, we propose a recursive erasure memory network (REM-Net) to cope with the quality improvement of evidence. To address this, REM-Net is equipped with a module to refine the evidence by recursively erasing the low-quality evidence that does not explain the question answering. Besides, instead of retrieving evidence from existing knowledge bases, REM-Net leverages a pre-trained generative model to generate candidate evidence customized for the question. We conduct experiments on two commonsense question answering datasets, WIQA and CosmosQA. The results demonstrate the performance of REM-Net and show that the refined evidence is explainable.

A riddle is a mystifying, puzzling question about everyday concepts. For example, the riddle "I have five fingers but I am not alive. What am I?" asks about the concept of a glove. Solving riddles is a challenging cognitive process for humans, in that it requires complex commonsense reasoning abilities and an understanding of figurative language. However, there are currently no commonsense reasoning datasets that test these abilities. We propose RiddleSense, a novel multiple-choice question answering challenge for benchmarking higher-order commonsense reasoning models, which is the first large dataset for riddle-style commonsense question answering, where the distractors are crowdsourced from human annotators. We systematically evaluate a wide range of reasoning models over it and point out that there is a large gap between the best-supervised model and human performance -- pointing to interesting future research for higher-order commonsense reasoning and computational creativity.

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.

In social settings, much of human behavior is governed by unspoken rules of conduct. For artificial systems to be fully integrated into social environments, adherence to such norms is a central prerequisite. We investigate whether contemporary NLG models can function as behavioral priors for systems deployed in social settings by generating action hypotheses that achieve predefined goals under moral constraints. Moreover, we examine if models can anticipate likely consequences of (im)moral actions, or explain why certain actions are preferable by generating relevant norms. For this purpose, we introduce 'Moral Stories', a crowd-sourced dataset of structured, branching narratives for the study of grounded, goal-oriented social reasoning. Finally, we propose decoding strategies that effectively combine multiple expert models to significantly improve the quality of generated actions, consequences, and norms compared to strong baselines, e.g. though abductive reasoning.

Sources of commonsense knowledge aim to support applications in natural language understanding, computer vision, and knowledge graphs. These sources contain complementary knowledge to each other, which makes their integration desired. Yet, such integration is not trivial because of their different foci, modeling approaches, and sparse overlap. In this paper, we propose to consolidate commonsense knowledge by following five principles. We apply these principles to combine seven key sources into a first integrated CommonSense Knowledge Graph (CSKG). We perform analysis of CSKG and its various text and graph embeddings, showing that CSKG is a well-connected graph and that its embeddings provide a useful entry point to the graph. Moreover, we show the impact of CSKG as a source for reasoning evidence retrieval, and for pre-training language models for generalizable downstream reasoning. CSKG and all its embeddings are made publicly available to support further research on commonsense knowledge integration and reasoning.

Language comprehension and commonsense knowledge validation by machines are challenging tasks that are still under researched and evaluated for Arabic text. In this paper, we present a benchmark Arabic dataset for commonsense explanation. The dataset consists of Arabic sentences that does not make sense along with three choices to select among them the one that explains why the sentence is false. Furthermore, this paper presents baseline results to assist and encourage the future evaluation of research in this field. The dataset is distributed under the Creative Commons CC-BY-SA 4.0 license and can be found on GitHub

OAKLAND, California, Dec. 14, 2020 /Press Release/ -- Silicon Valley Robotics, the world's largest cluster of innovation in robotics, announces the inaugural'Good Robot' Industry Awards, celebrating the robotics, automation and Artificial Intelligence (AI) that will help us solve global challenges. These 52 companies and individuals have all contributed to innovation that will improve the quality of our lives, whether it's weed-free pesticide-free farming, like FarmWise or Iron Ox; supporting health workers and the elderly manage health care treatment regimes, like Catalia Health or Multiply Labs; or reimagining the logistics industry so that the transfer of physical goods becomes as efficient as the transfer of information, like Cruise, Embark, Matternet and Zipline. The categories Innovation, Vision and Commercialization represent the stages robotics companies go through, firstly with an innovative technology or product, then with a vision to change the world (and occasionally the investment to match), and finally with real evidence of customer traction. The criteria for our Commercialization Award is achieving $1 million in revenue, which is a huge milestone for a startup building a new invention. Tessa Lau, Founder and CEO of Dusty Robotics, an Innovation Awardee said "We're almost there. Dusty Robotics' FieldPrinter automates the painstaking, time-consuming process of marking building plans in the field, replacing a traditional process using measuring tape and chalk lines that hasn't changed in 5000 years. The company's vision of creating robot-powered tools for the modern construction workforce resonates strongly with commercial construction companies. Dusty's robot fleet is now in production, producing highly accurate layouts in record time on every floor of two multi-family residential towers going up in San Francisco. The SVR'Good Robot' Industry Awards also highlight diverse robotics companies. In our Visionary Category, Zoox is the first billion dollar company led by an African-American woman, Aicha Evans, and Robust AI shows diversity at every level of the organization. Diversity of thought will be critical as Robust AI tackles the challenge of building a cognitive engine for robotics that incorporates common sense reasoning. "Robotics and AI will shape the next century in the same way the Industrial revolution shaped the 20th century.