The Winograd Schema (WS) challenge has been proposed as an alternative to the Turing Test as a test for machine intelligence. In this short paper we "situate" the WS challenge in the data-information-knowledge continuum, suggesting in the process what a good WS is. Furthermore, we suggest that the WS is a special case of a more general phenomenon in language understanding, namely the phenomenon of the "missing text". In particular, we will argue that what we usually call thinking in the process of language understanding almost always involves discovering the missing text - text is rarely explicitly stated but is implicitly assumed as shared background knowledge. We therefore suggest extending the WS challenge to include tests beyond those involving reference resolution, including examples that require discovering the missing text in situations that are usually treated in computational linguistics under different labels, such as metonymy, quantifier scope ambiguity, lexical disambiguation, and co-predication, to name a few.

Abstract--Commonsense knowledge is paramount to enable intelligent systems. Typically, it is characterized as being implicit and ambiguous, hindering thereby the automation of its acquisition. To address these challenges, this paper presents semantically enhanced models to enable reasoning through resolving part of commonsense ambiguity. The proposed models enhance in a knowledge graph embedding framework for knowledge base completion. Experimental results show the effectiveness of the new semantic models in commonsense reasoning. Intelligent systems need to acquire humanlike knowledge in order to perform smart decision making. This type of knowledge which is often termed commonsense knowledge refers to the agreed-upon facts and information about everyday world that is assumed to be shared by everyone.

Reading comprehension QA tasks have seen a recent surge in popularity, yet most works have focused on fact-finding extractive QA. We instead focus on a more challenging multi-hop generative task (NarrativeQA), which requires the model to reason, gather, and synthesize disjoint pieces of information within the context to generate an answer. This type of multi-step reasoning also often requires understanding implicit relations, which humans resolve via external, background commonsense knowledge. We first present a strong generative baseline that uses a multi-attention mechanism to perform multiple hops of reasoning and a pointer-generator decoder to synthesize the answer. This model performs substantially better than previous generative models, and is competitive with current state-of-the-art span prediction models. We next introduce a novel system for selecting grounded multi-hop relational commonsense information from ConceptNet via a pointwise mutual information and term-frequency based scoring function. Finally, we effectively use this extracted commonsense information to fill in gaps of reasoning between context hops, using a selectively-gated attention mechanism. This boosts the model's performance significantly (also verified via human evaluation), establishing a new state-of-the-art for the task. We also show that our background knowledge enhancements are generalizable and improve performance on QAngaroo-WikiHop, another multi-hop reasoning dataset.

Comprehending procedural text, e.g., a paragraph describing photosynthesis, requires modeling actions and the state changes they produce, so that questions about entities at different timepoints can be answered. Although several recent systems have shown impressive progress in this task, their predictions can be globally inconsistent or highly improbable. In this paper, we show how the predicted effects of actions in the context of a paragraph can be improved in two ways: (1) by incorporating global, commonsense constraints (e.g., a non-existent entity cannot be destroyed), and (2) by biasing reading with preferences from large-scale corpora (e.g., trees rarely move). Unlike earlier methods, we treat the problem as a neural structured prediction task, allowing hard and soft constraints to steer the model away from unlikely predictions. We show that the new model significantly outperforms earlier systems on a benchmark dataset for procedural text comprehension (+8% relative gain), and that it also avoids some of the nonsensical predictions that earlier systems make.

The AI revolution is taking place right now. In contrast to what the scary headlines and stories suggest, the revolution is not about robots or computers taking over humanity. The real revolution does have and will have a continuing impact on all facets of society, but in a more subtle way. This blog will keep you informed about the developments in AI by emphasising the actual practical implications for society and business rather than stating futuristic claims about what may happen. Let us start with the concept of artificial intelligence, AI, for short.

We argue that logical semantics might have faltered due to its failure in distinguishing between two fundamentally very different types of concepts: ontological concepts, that should be types in a strongly-typed ontology, and logical concepts, that are predicates corresponding to properties of and relations between objects of various ontological types. We will then show that accounting for these differences amounts to the integration of lexical and compositional semantics in one coherent framework, and to an embedding in our logical semantics of a strongly-typed ontology that reflects our commonsense view of the world and the way we talk about it in ordinary language. We will show that in such a framework a number of challenges in natural language semantics can be adequately and systematically treated.

This paper describes how the "SP Theory of Intelligence" with the "SP Computer Model", outlined in an Appendix, may throw light on aspects of commonsense reasoning (CSR) and commonsense knowledge (CSK), as discussed in another paper by Ernest Davis and Gary Marcus (DM). In four main sections, the paper describes: 1) The main problems to be solved; 2) Other research on CSR and CSK; 3) Why the SP system may prove useful with CSR and CSK 4) How examples described by DM may be modelled in the SP system. With regard to successes in the automation of CSR described by DM, the SP system's strengths in simplification and integration may promote seamless integration across these areas, and seamless integration of those area with other aspects of intelligence. In considering challenges in the automation of CSR described by DM, the paper describes in detail, with examples of SP-multiple-alignments. how the SP system may model processes of interpretation and reasoning arising from the horse's head scene in "The Godfather" film. A solution is presented to the 'long tail' problem described by DM. The SP system has some potentially useful things to say about several of DM's objectives for research in CSR and CSK.

We present Web-STAR, an online platform for story understanding built on top of the STAR reasoning engine for STory comprehension through ARgumentation. The platform includes a web-based IDE, integration with the STAR system, and a web service infrastructure to support integration with other systems that rely on story understanding functionality to complete their tasks. The platform also delivers a number of "social" features, including a community repository for public story sharing with a built-in commenting system, and tools for collaborative story editing that can be used for team development projects and for educational purposes.

Facebook on Tuesday officially announced that it's hired some of academia's top AI researchers, defending its practice of drawing talent from universities around the globe. Facebook AI Research (FAIR) "relies on open partnerships to help drive AI forward, where researchers have the freedom to control their own agenda," Facebook Chief AI Scientist Yann LeCun wrote in a blog post. "Ours frequently collaborate with academics from other institutions, and we often provide financial and hardware resources to specific universities. The latest hires include Carnegie Mellon Prof. Jessica Hodgins, who will lead a new FAIR lab in Pittsburgh focused on robotics, large-scale and lifelong learning, common sense reasoning, and AI in support of creativity. She'll be joined by Carnegie Mellon Prof. Abhinav Gupta, another robotics expert.

Commonsense reasoning is a longstanding challenge for deep learning. For example, it is difficult to use neural networks to tackle the Winograd Schema dataset [1]. In this paper, we present a simple method for commonsense reasoning with neural networks, using unsupervised learning. Key to our method is the use of language models, trained on a massive amount of unlabled data, to score multiple choice questions posed by commonsense reasoning tests. On both Pronoun Disambiguation and Winograd Schema challenges, our models outperform previous state-of-the-art methods by a large margin, without using expensive annotated knowledge bases or hand-engineered features. We train an array of large RNN language models that operate at word or character level on LM-1-Billion, CommonCrawl, SQuAD, Gutenberg Books, and a customized corpus for this task and show that diversity of training data plays an important role in test performance. Further analysis also shows that our system successfully discovers important features of the context that decide the correct answer, indicating a good grasp of commonsense knowledge.