In this paper we propose a simple yet efficient method for constrained word deletion to compress sentences, based on top-down greedy local flipping from multiple random initializations. The algorithm naturally integrates various grammatical constraints in the compression process, without using time-consuming integer linear programming solvers. Our formulation suits for any objective function involving arbitrary local score definition. Experimental results show that the proposed method achieves nearly identical performance with explicit ILP formulation while being much more efficient.

Sequential data often possesses hierarchical structures with complex dependencies between sub-sequences, such as found between the utterances in a dialogue. To model these dependencies in a generative framework, we propose a neural network-based generative architecture, with stochastic latent variables that span a variable number of time steps. We apply the proposed model to the task of dialogue response generation and compare it with other recent neural-network architectures. We evaluate the model performance through a human evaluation study. The experiments demonstrate that our model improves upon recently proposed models and that the latent variables facilitate both the generation of meaningful, long and diverse responses and maintaining dialogue state.

In the Markov decision process model, policies are usually evaluated by expected cumulative rewards. As this decision criterion is not always suitable, we propose in this paper an algorithm for computing a policy optimal for the quantile criterion. Both finite and infinite horizons are considered. Finally we experimentally evaluate our approach on random MDPs and on a data center control problem.

Partially Observable Markov Decision Processes (POMDPs) are powerful models for planning under uncertainty in partially observable domains. However, computing optimal solutions for POMDPs is challenging because of the high computational requirements of POMDP solution algorithms. Several algorithms use a subroutine to prune dominated vectors in value functions, which requires a large number of linear programs (LPs) to be solved and it represents a large part of the total running time. In this paper we show how the LPs in POMDP pruning subroutines can be decomposed using a Benders decomposition. The resulting algorithm incrementally adds LP constraints and uses only a small fraction of the constraints. Our algorithm significantly improves the performance of existing pruning methods and the commonly used incremental pruning algorithm. Our new variant of incremental pruning is the fastest optimal pruning-based POMDP algorithm.

The management of uncertainty is crucial when harvesting structured content from unstructured and noisy sources. Knowledge Graphs ( KGs ) are a prominent example. KGs maintain both numerical and non-numerical facts, with the support of an underlying schema. These facts are usually accompanied by a confidence score that witnesses how likely is for them to hold. Despite their popularity, most of existing KGs focus on static data thus impeding the availabilityof timewise knowledge. What is missing is a comprehensive solution for the management of uncertain and temporal data in KGs . The goal of this paper is to fill this gap. We rely on two main ingredients. The first is a numerical extension of Markov Logic Networks (MLNs) that provide the necessary underpinning to formalize the syntax and semantics of uncertain temporal KGs . The second is a set of Datalog constraints with inequalities that extend the underlying schema of the KGs and help to detect inconsistencies. From a theoretical point of view, we discuss the complexity of two important classes of queries for uncertain temporal KGs: maximuma-posteriori and conditional probability inference. Due to the hardness of these problems and the fact that MLN solvers do not scale well, we also explore the usage of Probabilistic Soft Logics (PSL) as a practical tool to support our reasoning tasks. We report on an experimental evaluation comparing the MLN and PSL approaches.

Adaptive management is applied in conservation and natural resource management, and consists of making sequential decisions when the transition matrix is uncertain. Informally described as ’learning by doing’, this approach aims to trade off between decisions that help achieve the objective and decisions that will yield a better knowledge of the true transition matrix. When the true transition matrix is assumed to be an element of a finite set of possible matrices, solving a mixed observability Markov decision process (MOMDP) leads to an optimal trade-off but is very computationally demanding. Under the assumption (common in adaptive management) that the true transition matrix is stationary, we propose a polynomial-time algorithm to find a lower bound of the value function. In the corners of the domain of the value function (belief space), this lower bound is provably equal to the optimal value function. We also show that under further assumptions, it is a linear approximation of the optimal value function in a neighborhood around the corners. We evaluate the benefits of our approach by using it to initialize the solvers MO-SARSOP and Perseus on a novel computational sustainability problem and a recent adaptive management data challenge. Our approach leads to an improved initial value function and translates into significant computational gains for both solvers.

For non-expert users, a textual query is the most popular and simple means for communicating with a retrieval or question answering system.However, there is a risk of receiving queries which do not match with the background knowledge.Query expansion and query rewriting are solutions for this problem but they are in danger of potentially yielding a large number of irrelevant words, which in turn negatively influences runtime as well as accuracy.In this paper, we propose a new method for automatic rewriting input queries on graph-structured RDF knowledge bases.We employ a Hidden Markov Model to determine the most suitable derived words from linguistic resources.We introduce the concept of triple-based co-occurrence for recognizing co-occurred words in RDF data.This model was bootstrapped with three statistical distributions.Our experimental study demonstrates the superiority of the proposed approach to the traditional n-gram model.

Relational learning deals with data that are characterized by relational structures. An important task is collective classification, which is to jointly classify networked objects. While it holds a great promise to produce a better accuracy than non-collective classifiers, collective classification is computationally challenging and has not leveraged on the recent breakthroughs of deep learning. We present Column Network (CLN), a novel deep learning model for collective classification in multi-relational domains. CLN has many desirable theoretical properties: (i) it encodes multi-relations between any two instances; (ii) it is deep and compact, allowing complex functions to be approximated at the network level with a small set of free parameters; (iii) local and relational features are learned simultaneously; (iv) long-range, higher-order dependencies between instances are supported naturally; and (v) crucially, learning and inference are efficient with linear complexity in the size of the network and the number of relations. We evaluate CLN on multiple real-world applications: (a) delay prediction in software projects, (b) PubMed Diabetes publication classification and (c) film genre classification. In all of these applications, CLN demonstrates a higher accuracy than state-of-the-art rivals.

Monte Carlo tree search (MCTS) is extremely popular in computer Go which determines each action by enormous simulations in a broad and deep search tree. However, human experts select most actions by pattern analysis and careful evaluation rather than brute search of millions of future interactions. In this paper, we propose a computer Go system that follows experts’ way of thinking and playing. Our system consists of two parts. The first part is a novel deep alternative neural network (DANN) used to generate candidates of next move. Compared with existing deep convolutional neural network (DCNN), DANN inserts recurrent layer after each convolutional layer and stacks them in an alternative manner. We show such setting can preserve more contexts of local features and its evolutions which are beneficial for move prediction. The second part is a long-term evaluation (LTE) module used to provide a reliable evaluation of candidates rather than a single probability from move predictor. This is consistent with human experts’ nature of playing since they can foresee tens of steps to give an accurate estimation of candidates. In our system, for each candidate, LTE calculates a cumulative reward after several future interactions when local variations are settled. Combining criteria from the two parts, our system determines the optimal choice of next move. For more comprehensive experiments, we introduce a new professional Go dataset (PGD), consisting of $253,233$ professional records. Experiments on GoGoD and PGD datasets show the DANN can substantially improve performance of move prediction over pure DCNN. When combining LTE, our system outperforms most relevant approaches and open engines based on MCTS.

Belief Propagation (BP) is an iterative message-passing algorithm for performing inference in graphical models Convergent message-passing algorithms. There has (GMs), such as Markov Random Fields (MRFs). BP calculates been much research on finding variations to the update equations the marginal distribution for each unobserved node, of BP that guarantee convergence. These algorithms conditional on any observed nodes (Pearl 1988). It achieves are often similar in structure to the nonconvergent algorithms, this by propagating the information from a few observed yet it can be proven that the value of the variational nodes throughout the network by iteratively passing information problem (or its dual) improves at each iteration (Hazan and between neighboring nodes. It is known that when Shashua 2008; Heskes 2006; Meltzer, Globerson, and Weiss the graphical model has a tree structure, then BP converges 2009). Another body of recent papers have suggested to to the true marginals (according to exact probabilistic inference) solve the convergence problems of MMinference by linearizing after a finite number of iterations.