Search

Dialogue response generation (DRG) is a critical component of task-oriented dialogue systems (TDSs). Its purpose is to generate proper natural language responses given some context, e.g., historical utterances, system states, etc. State-of-the-art work focuses on how to better tackle DRG in an end-to-end way. Typically, such studies assume that each token is drawn from a single distribution over the output vocabulary, which may not always be optimal. Responses vary greatly with different intents, e.g., domains, system actions. We propose a novel mixture-of-generators network (MoGNet) for DRG, where we assume that each token of a response is drawn from a mixture of distributions. MoGNet consists of a chair generator and several expert generators. Each expert is specialized for DRG w.r.t. a particular intent. The chair coordinates multiple experts and combines the output they have generated to produce more appropriate responses. We propose two strategies to help the chair make better decisions, namely, a retrospective mixture-of-generators (RMoG) and a prospective mixture-of-generators (PMoG). The former only considers the historical expert-generated responses until the current time step while the latter also considers possible expert-generated responses in the future by encouraging exploration. In order to differentiate experts, we also devise a global-and-local (GL) learning scheme that forces each expert to be specialized towards a particular intent using a local loss and trains the chair and all experts to coordinate using a global loss. We carry out extensive experiments on the MultiWOZ benchmark dataset. MoGNet significantly outperforms state-of-the-art methods in terms of both automatic and human evaluations, demonstrating its effectiveness for DRG.

Suppose you want to design a voting rule that can be used to elect a committee or parliament by asking each voter to approve of a subset of the candidates standing. There are several properties you may want that rule to satisfy. First, voters should enjoy some form of proportional representation. Second, voters should not have an incentive to misrepresent their preferences. Third, outcomes should be Pareto efficient. We show that it is impossible to design a voting rule that satisfies all three properties. We also explore what possibilities there are when we weaken our requirements. Of special interest is the methodology we use, as a significant part of the proof is outsourced to a SAT solver. While prior work has considered similar questions for the special case of resolute voting rules, which do not allow for ties between outcomes, we focus on the fact that, in practice, most voting rules allow for the possibility of such ties.

A key aspect of foraging in robot swarms is optimizing the search efficiency when both the environment and target density are unknown. Hence, designing optimal exploration strategies is desirable. This paper proposes a novel approach that extends the individual Lévy walk to a collective one. To achieve this, we adjust the individual motion through applying an artificial potential field method originating from local communication. We demonstrate the effectiveness of the enhanced foraging by confirming that the collective trajectory follows a heavy-tailed distribution over a wide range of swarm sizes. Additionally, we study target search efficiency of the proposed algorithm in comparison with the individual Lévy walk for two different types of target distributions: Homogeneous and heterogeneous. Our results highlight the advantages of the proposed approach for both target distributions, while increasing the scalability to large swarm sizes. Finally, we further extend the individual exploration algorithm by adapting the Lévy walk parameter α, altering the motion pattern based on a local estimation of the target density. This adaptive behavior is particularly useful when targets are distributed in patches.

In data mining, finding interesting patterns is a challenging task. Constraint-based mining is a well-known approach to this, and one for which constraint programming has been shown to be a well-suited and generic framework. Constraint dominance programming (CDP) has been proposed as an extension that can capture an even wider class of constraint-based mining problems, by allowing us to compare relations between patterns. In this paper we improve CDP with the ability to specify an incomparability condition. This allows us to overcome two major shortcomings of CDP: finding dominated solutions that must then be filtered out after search, and unnecessarily adding dominance blocking constraints between incomparable solutions. We demonstrate the efficacy of our approach by extending the problem specification language ESSENCE and implementing it in a solver-independent manner on top of the constraint modelling tool CONJURE. Our experiments on pattern mining tasks with both a CP solver and a SAT solver show that using the incomparability condition during search significantly improves the efficiency of dominance programming and reduces (and often eliminates entirely) the need for post-processing to filter dominated solutions. Publisher PDF

While it is well known that arithmetic circuits can be used for efficient probabilistic inference, arithmetic circuits can also be used for other tasks. In this paper, we show how arithmetic circuits in a semiring setting (i.e., algebraic circuits) can solve decision theoretic inference tasks and a utility learning task under partial observability. The former involves finding the set of decisions that maximises the expected utility. We introduce two approaches for this, both applying algebraic circuits. The learning task involves learning unknown utility values from partially observed interpretations of which the total utility is given. We provide the necessary theory and also perform an experimental evaluation of the approaches. ispartof: pages:2569-2576 ispartof: Proceedings of the 24th European Conference on Artificial Intelligence vol:325 pages:2569-2576 ispartof: 24th European Conference on Artificial Intelligence location:Santiago de Compostela, Spain date:29 Aug - 8 Sep 2020 status: Published online