Automated story generation is the problem of automatically selecting a sequence of events, actions, or words that can be told as a story. We seek to develop a system that can generate stories by learning everything it needs to know from textual story corpora. To date, recurrent neural networks that learn language models at character, word, or sentence levels have had little success generating coherent stories. We explore the question of event representations that provide a mid-level of abstraction between words and sentences in order to retain the semantic information of the original data while minimizing event sparsity. We present a technique for preprocessing textual story data into event sequences. We then present a technique for automated story generation whereby we decompose the problem into the generation of successive events (event2event) and the generation of natural language sentences from events (event2sentence). We give empirical results comparing different event representations and their effects on event successor generation and the translation of events to natural language.

We propose semi-random features for nonlinear function approximation. The flexibility of semi-random feature lies between the fully adjustable units in deep learning and the random features used in kernel methods. For one hidden layer models with semi-random features, we prove with no unrealistic assumptions that the model classes contain an arbitrarily good function as the width increases (universality), and despite non-convexity, we can find such a good function (optimization theory) that generalizes to unseen new data (generalization bound). For deep models, with no unrealistic assumptions, we prove universal approximation ability, a lower bound on approximation error, a partial optimization guarantee, and a generalization bound. Depending on the problems, the generalization bound of deep semi-random features can be exponentially better than the known bounds of deep ReLU nets; our generalization error bound can be independent of the depth, the number of trainable weights as well as the input dimensionality. In experiments, we show that semi-random features can match the performance of neural networks by using slightly more units, and it outperforms random features by using significantly fewer units. Moreover, we introduce a new implicit ensemble method by using semi-random features.

Co-clustering computes clusters of data items and the related features concurrently, and it has been used in many applications such as community detection, product recommendation, computer vision, and pricing optimization. In this paper, we propose a new co-clustering method, called CoDiNMF, which improves the clustering quality and finds directional patterns among co-clusters by using multiple directed and undirected graphs. We design the objective function of co-clustering by using min-cut criterion combined with an additional term which controls the sum of net directional flow between different co-clusters. In addition, we show that a variant of Nonnegative Matrix Factorization (NMF) can solve the proposed objective function effectively. We run experiments on the US patents and BlogCatalog data sets whose ground truth have been known, and show that CoDiNMF improves clustering results compared to other co-clustering methods in terms of average F1 score, Rand index, and adjusted Rand index (ARI). Finally, we compare CoDiNMF and other co-clustering methods on the Wikipedia data set of philosophers, and we can find meaningful directional flow of influence among co-clusters of philosophers.

Knowledge graph (KG) is known to be helpful for the task of question answering (QA), since it provides well-structured relational information between entities, and allows one to further infer indirect facts. However, it is challenging to build QA systems which can learn to reason over knowledge graphs based on question-answer pairs alone. First, when people ask questions, their expressions are noisy (for example, typos in texts, or variations in pronunciations), which is non-trivial for the QA system to match those mentioned entities to the knowledge graph. Second, many questions require multi-hop logic reasoning over the knowledge graph to retrieve the answers. To address these challenges, we propose a novel and unified deep learning architecture, and an end-to-end variational learning algorithm which can handle noise in questions, and learn multi-hop reasoning simultaneously. Our method achieves state-of-the-art performance on a recent benchmark dataset in the literature. We also derive a series of new benchmark datasets, including questions for multi-hop reasoning, questions paraphrased by neural translation model, and questions in human voice. Our method yields very promising results on all these challenging datasets.

Graphical models offer techniques for capturing the structure of many problems in real-world domains and provide means for representation, interpretation, and inference. The modeling framework provides tools for discovering rules for solving problems by exploring structural relationships. We present the Structural Affinity method that uses graphical models for first learning and subsequently recognizing the pattern for solving problems on the Raven's Progressive Matrices Test of general human intelligence. Recently there has been considerable work on computational models of addressing the Raven's test using various representations ranging from fractals to symbolic structures. In contrast, our method uses Markov Random Fields parameterized by affinity factors to discover the structure in the geometric analogy problems and induce the rules of Carpenter et al.'s cognitive model of problem-solving on the Raven's Progressive Matrices Test. We provide a computational account that first learns the structure of a Raven's problem and then predicts the solution by computing the probability of the correct answer by recognizing patterns corresponding to Carpenter et al.'s rules. We demonstrate that the performance of our model on the Standard Raven Progressive Matrices is comparable with existing state of the art models.

Reports on the 2017 AAAI Spring Symposium Series

The 2016 Computational Analogy Workshop at ICCBR

Computational analogy and case-based reasoning (CBR) are closely related research areas. Both employ prior cases to reason in complex situations with incomplete information. Analogy research often focuses on modeling human cognitive processes, the structural alignment between a base/source and target, and adaptation/abstraction of the analogical source content. While CBR research also deals with alignment and adaptation, the field tends to focus more on retrieval, case-base maintenance, and pragmatic solutions to real-world problems. However, despite their obvious overlap in research goals and approaches, cross communication and collaboration between these areas has been progressively diminishing. CBR and computational analogy researchers stand to benefit greatly from increased exposure to each other's work and greater cross-pollination of ideas. The objective of this workshop is to promote such communication by bringing together researchers from the two areas, to foster new collaborative endeavors, to stimulate new ideas and avoid reinventing old ones.

It is also important to remember that having a very sharp distinction of AI A rise in real-world applications of AI has stimulated for social good research is not always feasible, and significant interest from the public, media, and policy often unnecessary. While there has been significant makers. Along with this increasing attention has progress, there still exist many major challenges facing come a media-fueled concern about purported negative the design of effective AIbased approaches to deal consequences of AI, which often overlooks the with the difficulties in real-world domains. One of the societal benefits that AI is delivering and can deliver challenges is interpretability since most algorithms for in the near future. To address these concerns, the AI for social good problems need to be used by human symposium on Artificial Intelligence for the Social end users. Second, the lack of access to valuable data Good (AISOC-17) highlighted the benefits that AI can that could be crucial to the development of appropriate bring to society right now. It brought together AI algorithms is yet another challenge. Third, the researchers and researchers, practitioners, experts, data that we get from the real world is often noisy and and policy makers from a wide variety of domains.

Computational agents use knowledge representations to reason about the data world they occupy. A theory of consciousness, Integrated Information Theory, suggests beings that are conscious use experiences to reason about the world they occupy. Herein, the question is considered: Is an experience a knowledge representation?