Artificial Intelligence

---

Hierarchical Attentional Hybrid Neural Networks for Document Classification (1901.06610v2)

Jader Abreu, Luis Fred, David Macêdo, Cleber Zanchettin

2019-01-20

Document classification is a challenging task with important applications. The deep learning approaches to the problem have gained much attention recently. Despite the progress, the proposed models do not incorporate the knowledge of the document structure in the architecture efficiently and not take into account the contexting importance of words and sentences. In this paper, we propose a new approach based on a combination of convolutional neural networks, gated recurrent units, and attention mechanisms for document classification tasks. The main contribution of this work is the use of convolution layers to extract more meaningful, generalizable and abstract features by the hierarchical representation. The proposed method in this paper improves the results of the current attention-based approaches for document classification.

The Winnability of Klondike and Many Other Single-Player Card Games (1906.12314v1)

Charlie Blake, Ian P. Gent

2019-06-28

The most famous single-player card game is 'Klondike', but our ignorance of its winnability percentage has been called "one of the embarrassments of applied mathematics". Klondike is just one of many single-player card games, generically called 'patience' or 'solitaire' games, for which players have long wanted to know how likely a particular game is to be winnable for a random deal. A number of different games have been studied empirically in the academic literature and by non-academic enthusiasts. Here we show that a single general purpose Artificial Intelligence program, called "Solvitaire", can be used to determine the winnability percentage of approximately 30 different single-player card games with a 95% confidence interval of +/- 0.1% or better. For example, we report the winnability of Klondike as 81.956% +/- 0.096% (in the 'thoughtful' variant where the player knows the location of all cards), a 30-fold reduction in confidence interval over the best previous result. Almost all our results are either entirely new or represent significant improvements on previous knowledge.

Growing Action Spaces (1906.12266v1)

Gregory Farquhar, Laura Gustafson, Zeming Lin, Shimon Whiteson, Nicolas Usunier, Gabriel Synnaeve

2019-06-28

In complex tasks, such as those with large combinatorial action spaces, random exploration may be too inefficient to achieve meaningful learning progress. In this work, we use a curriculum of progressively growing action spaces to accelerate learning. We assume the environment is out of our control, but that the agent may set an internal curriculum by initially restricting its action space. Our approach uses off-policy reinforcement learning to estimate optimal value functions for multiple action spaces simultaneously and efficiently transfers data, value estimates, and state representations from restricted action spaces to the full task. We show the efficacy of our approach in proof-of-concept control tasks and on challenging large-scale StarCraft micromanagement tasks with large, multi-agent action spaces.

Anticipatory Thinking: A Metacognitive Capability (1906.12249v1)

Adam Amos-Binks, Dustin Dannenhauer

2019-06-28

Anticipatory thinking is a complex cognitive process for assessing and managing risk in many contexts. Humans use anticipatory thinking to identify potential future issues and proactively take actions to manage their risks. In this paper we define a cognitive systems approach to anticipatory thinking as a metacognitive goal reasoning mechanism. The contributions of this paper include (1) defining anticipatory thinking in the MIDCA cognitive architecture, (2) operationalizing anticipatory thinking as a three step process for managing risk in plans, and (3) a numeric risk assessment calculating an expected cost-benefit ratio for modifying a plan with anticipatory actions.

Reinforcement Learning with Policy Mixture Model for Temporal Point Processes Clustering (1905.12345v3)

Weichang Wu, Junchi Yan, Xiaokang Yang, Hongyuan Zha

2019-05-29

Temporal point process is an expressive tool for modeling event sequences over time. In this paper, we take a reinforcement learning view whereby the observed sequences are assumed to be generated from a mixture of latent policies. The purpose is to cluster the sequences with different temporal patterns into the underlying policies while learning each of the policy model. The flexibility of our model lies in: i) all the components are networks including the policy network for modeling the intensity function of temporal point process; ii) to handle varying-length event sequences, we resort to inverse reinforcement learning by decomposing the observed sequence into states (RNN hidden embedding of history) and actions (time interval to next event) in order to learn the reward function, thus achieving better performance or increasing efficiency compared to existing methods using rewards over the entire sequence such as log-likelihood or Wasserstein distance. We adopt an expectation-maximization framework with the E-step estimating the cluster labels for each sequence, and the M-step aiming to learn the respective policy. Extensive experiments show the efficacy of our method against state-of-the-arts.

Uncovering the Semantics of Wikipedia Categories (1906.12089v1)

Nicolas Heist, Heiko Paulheim

2019-06-28

The Wikipedia category graph serves as the taxonomic backbone for large-scale knowledge graphs like YAGO or Probase, and has been used extensively for tasks like entity disambiguation or semantic similarity estimation. Wikipedia's categories are a rich source of taxonomic as well as non-taxonomic information. The category 'German science fiction writers', for example, encodes the type of its resources (Writer), as well as their nationality (German) and genre (Science Fiction). Several approaches in the literature make use of fractions of this encoded information without exploiting its full potential. In this paper, we introduce an approach for the discovery of category axioms that uses information from the category network, category instances, and their lexicalisations. With DBpedia as background knowledge, we discover 703k axioms covering 502k of Wikipedia's categories and populate the DBpedia knowledge graph with additional 4.4M relation assertions and 3.3M type assertions at more than 87% and 90% precision, respectively.

Label Efficient Semi-Supervised Learning via Graph Filtering (1901.09993v3)

Qimai Li, Xiao-Ming Wu, Han Liu, Xiaotong Zhang, Zhichao Guan

2019-01-28

Graph-based methods have been demonstrated as one of the most effective approaches for semi-supervised learning, as they can exploit the connectivity patterns between labeled and unlabeled data samples to improve learning performance. However, existing graph-based methods either are limited in their ability to jointly model graph structures and data features, such as the classical label propagation methods, or require a considerable amount of labeled data for training and validation due to high model complexity, such as the recent neural-network-based methods. In this paper, we address label efficient semi-supervised learning from a graph filtering perspective. Specifically, we propose a graph filtering framework that injects graph similarity into data features by taking them as signals on the graph and applying a low-pass graph filter to extract useful data representations for classification, where label efficiency can be achieved by conveniently adjusting the strength of the graph filter. Interestingly, this framework unifies two seemingly very different methods -- label propagation and graph convolutional networks. Revisiting them under the graph filtering framework leads to new insights that improve their modeling capabilities and reduce model complexity. Experiments on various semi-supervised classification tasks on four citation networks and one knowledge graph and one semi-supervised regression task for zero-shot image recognition validate our findings and proposals.

On Learning to Prove (1904.11099v3)

Daniel Huang

2019-04-24

In this paper, we consider the problem of learning a first-order theorem prover that uses a representation of beliefs in mathematical claims to construct proofs. The inspiration for doing so comes from the practices of human mathematicians where "plausible reasoning" is applied in addition to deductive reasoning to find proofs. Towards this end, we introduce a representation of beliefs that assigns probabilities to the exhaustive and mutually exclusive first-order possibilities found in Hintikka's theory of distributive normal forms. The representation supports Bayesian update, induces a distribution on statements that does not enforce that logically equivalent statements are assigned the same probability, and suggests an embedding of statements into an associated Hilbert space. We then examine conjecturing as model selection and an alternating-turn game of determining consistency. The game is amenable (in principle) to self-play training to learn beliefs and derive a prover that is complete when logical omniscience is attained and sound when beliefs are reasonable. The representation has super-exponential space requirements as a function of quantifier depth so the ideas in this paper should be taken as theoretical. We will comment on how abstractions can be used to control the space requirements at the cost of completeness.

Multi-Criteria Chinese Word Segmentation with Transformer (1906.12035v1)

Xipeng Qiu, Hengzhi Pei, Hang Yan, Xuanjing Huang

2019-06-28

Different linguistic perspectives cause many diverse segmentation criteria for Chinese word segmentation (CWS). Most existing methods focus on improving the performance of single-criterion CWS. However, it is interesting to exploit these heterogeneous segmentation criteria and mine their common underlying knowledge. In this paper, we propose a concise and effective model for multi-criteria CWS, which utilizes a shared fully-connected self-attention model to segment the sentence according to a criterion indicator. Experiments on eight datasets with heterogeneous segmentation criteria show that the performance of each corpus obtains a significant improvement, compared to single-criterion learning.

Probabilistic Neural-symbolic Models for Interpretable Visual Question Answering (1902.07864v2)

Ramakrishna Vedantam, Karan Desai, Stefan Lee, Marcus Rohrbach, Dhruv Batra, Devi Parikh

2019-02-21

We propose a new class of probabilistic neural-symbolic models, that have symbolic functional programs as a latent, stochastic variable. Instantiated in the context of visual question answering, our probabilistic formulation offers two key conceptual advantages over prior neural-symbolic models for VQA. Firstly, the programs generated by our model are more understandable while requiring lesser number of teaching examples. Secondly, we show that one can pose counterfactual scenarios to the model, to probe its beliefs on the programs that could lead to a specified answer given an image. Our results on the CLEVR and SHAPES datasets verify our hypotheses, showing that the model gets better program (and answer) prediction accuracy even in the low data regime, and allows one to probe the coherence and consistency of reasoning performed.

---