Search

Convolutional sequence to sequence (CNN seq2seq) models have met success in abstractive summarization. However, their outputs often contain repetitive word sequences and logical inconsistencies, limiting the practicality of their application. In this paper, we find the reasons behind the repetition problem in CNN-based abstractive summarization through observing the attention map between the summaries with repetition and their corresponding source documents and mitigate the repetition problem. We propose to reduce the repetition in summaries by attention filter mechanism (ATTF) and sentence-level backtracking decoder (SBD), which dynamically redistributes attention over the input sequence as the output sentences are generated. The ATTF can record previously attended locations in the source document directly and prevent the decoder from attending to these locations. The SBD prevents the decoder from generating similar sentences more than once via backtracking at test. The proposed model outperforms the baselines in terms of ROUGE score, repeatedness, and readability. The results show that this approach generates high-quality summaries with minimal repetition and makes the reading experience better.

The majority of existing linear temporal logic (LTL) planning methods rely on the construction of a discrete product automaton, which combines a discrete abstraction of robot mobility and a Buchi automaton that captures the LTL specification. Representing this product automaton as a graph and using graph search techniques, optimal plans that satisfy the LTL task can be synthesized. However, constructing expressive discrete abstractions makes the synthesis problem computationally intractable. In this article, we propose a new sampling-based LTL planning algorithm that does not require any discrete abstraction of robot mobility. Instead, it incrementally builds trees that explore the product state-space, until a maximum number of iterations is reached or a feasible plan is found. The use of trees makes data storage and graph search tractable, which significantly increases the scalability of our algorithm. To accelerate the construction of feasible plans, we introduce bias in the sampling process, which is guided by transitions in the Buchi automaton that belong to the shortest path to the accepting states. We show that our planning algorithm, with and without bias, is probabilistically complete and asymptotically optimal. Finally, we present numerical experiments showing that our method outperforms relevant temporal logic planning methods.

Commonsense knowledge used by humans while doing online shopping is valuable but difficult to be captured by existing systems running on e-commerce platforms. While construction of common- sense knowledge graphs in e-commerce is non-trivial, representation learning upon such graphs poses unique challenge compared to well-studied open-domain knowledge graphs (e.g., Freebase). By leveraging the commonsense knowledge and representation techniques, various applications in e-commerce can be benefited. Based on AliCoCo, the large-scale e-commerce concept net assisting a series of core businesses in Alibaba, we further enrich it with more commonsense relations and present AliCoCo2, the first commonsense knowledge graph constructed for e-commerce use. We propose a multi-task encoder-decoder framework to provide effective representations for nodes and edges from AliCoCo2. To explore the possibility of improving e-commerce businesses with commonsense knowledge, we apply newly mined commonsense relations and learned embeddings to e-commerce search engine and recommendation system in different ways. Experimental results demonstrate that our proposed representation learning method achieves state-of-the-art performance on the task of knowledge graph completion (KGC), and applications on search and recommendation indicate great potential value of the construction and use of commonsense knowledge graph in e-commerce. Besides, we propose an e-commerce QA task with a new benchmark during the construction of AliCoCo2, for testing machine common sense in e-commerce, which can benefit research community in exploring commonsense reasoning.

Slot filling is a critical task in natural language understanding (NLU) for dialog systems. State-of-the-art approaches treat it as a sequence labeling problem and adopt such models as BiLSTM-CRF. While these models work relatively well on standard benchmark datasets, they face challenges in the context of E-commerce where the slot labels are more informative and carry richer expressions. In this work, inspired by the unique structure of E-commerce knowledge base, we propose a novel multi-task model with cascade and residual connections, which jointly learns segment tagging, named entity tagging and slot filling. Experiments show the effectiveness of the proposed cascade and residual structures. Our model has a 14.6% advantage in F1 score over the strong baseline methods on a new Chinese E-commerce shopping assistant dataset, while achieving competitive accuracies on a standard dataset. Furthermore, online test deployed on such dominant E-commerce platform shows 130% improvement on accuracy of understanding user utterances. Our model has already gone into production in the E-commerce platform., AAAI 2019

Cell behaviors are dictated by epigenetic and transcriptional programs. Little is known about how extracellular stimuli modulate these programs to reshape gene expression and control cell behavioral responses. Here, we interrogated the epigenetic and transcriptional response of endothelial cells to VEGFA treatment and found rapid chromatin changes that mediate broad transcriptomic alterations. VEGFA-responsive genes were associated with active promoters, but changes in promoter histone marks were not tightly linked to gene expression changes. VEGFA altered transcription factor occupancy and the distal epigenetic landscape, which profoundly contributed to VEGFA-dependent changes in gene expression. Integration of gene expression, dynamic enhancer, and transcription factor occupancy changes induced by VEGFA yielded a VEGFA-regulated transcriptional regulatory network, which revealed that the small MAF transcription factors are master regulators of the VEGFA transcriptional program and angiogenesis. Collectively these results revealed that extracellular stimuli rapidly reconfigure the chromatin landscape to coordinately regulate biological responses.

In this paper, we consider a robot navigation problem in environments populated by humans. The goal is to determine collision-free and dynamically feasible trajectories that also maximize human satisfaction. This is because they may drive the robot close to humans that need help with their work or because they may keep the robot away from humans when it can interfere with human sight or work. In practice, human satisfaction is subjective and hard to describe mathematically. As a result, the planning problem we consider in this paper may lack important contextual information. To address this challenge, we propose a semi-supervised Bayesian Optimization (BO) method to design globally optimal robot trajectories using non-contextual bandit human feedback in the form of complaints or satisfaction ratings that express how satisfactory a trajectory is, without revealing the reason. Since trajectory planning is typically a high-dimensional optimization problem in the space of waypoints that define a trajectory, BO may require prohibitively many queries for human feedback to return a good solution. To this end, we use an autoencoder to reduce the high-dimensional problem space into a low dimensional latent space, which we update using human feedback. Moreover, we improve the exploration efficiency of BO by biasing the search for new trajectories towards dynamically feasible and collision-free trajectories obtained using off-the-shelf motion planners. We demonstrate the efficiency of our proposed trajectory planning method in a scenario with humans that have diversified and unknown demands.

In this paper, we consider the problem of designing collision-free, dynamically feasible, and socially-aware trajectories for robots operating in environments populated by humans. We define trajectories to be social-aware if they do not interfere with humans in any way that causes discomfort. In this paper, discomfort is defined broadly and, depending on specific individuals, it can result from the robot being too close to a human or from interfering with human sight or tasks. Moreover, we assume that human feedback is a bandit feedback indicating a complaint or no complaint on the part of the robot trajectory that interferes with the humans, and it does not reveal any contextual information about the locations of the humans or the reason for a complaint. Finally, we assume that humans can move in the obstacle-free space and, as a result, human utility can change. We formulate this planning problem as an online optimization problem that minimizes the social value of the time-varying robot trajectory, defined by the total number of incurred human complaints. As the human utility is unknown, we employ zeroth order, or derivative-free, optimization methods to solve this problem, which we combine with off-the-shelf motion planners to satisfy the dynamic feasibility and collision-free specifications of the resulting trajectories. To the best of our knowledge, this is a new framework for socially-aware robot planning that is not restricted to avoiding collisions with humans but, instead, focuses on increasing the social value of the robot trajectories using only bandit human feedback., Comment: 10 pages, 3 figures

This paper proposes an optimal control synthesis algorithm for Linear Temporal Logic (LTL) tasks that exploits experience from solving similar LTL tasks before. The key idea is to appropriately decompose complex LTL tasks into simpler subtasks and define sets of skills, or plans, needed to solve these subtasks. These skills can be stored in a library of reusable skills and can be used to quickly synthesize plans for new tasks that have not been encountered before. Our proposed method is inspired by literature on multi-task learning and can be used to transfer experience between different LTL tasks. It amounts to a new paradigm in model-checking and optimal control synthesis methods that to this date do not use prior experience to solve planning problems. We present numerical experiments that show that our approach generally outperforms these methods in terms of time to generate feasible plans. We also show that our proposed algorithm is probabilistically complete and asymptotically optimal.

Understanding latent user needs beneath shopping behaviors is critical to e-commercial applications. Without a proper definition of user needs in e-commerce, most industry solutions are not driven directly by user needs at current stage, which prevents them from further improving user satisfaction. Representing implicit user needs explicitly as nodes like "outdoor barbecue" or "keep warm for kids" in a knowledge graph, provides new imagination for various e- commerce applications. Backed by such an e-commerce knowledge graph, we propose a supervised learning algorithm to conceptualize user needs from their transaction history as "concept" nodes in the graph and infer those concepts for each user through a deep attentive model. Offline experiments demonstrate the effectiveness and stability of our model, and online industry strength tests show substantial advantages of such user needs understanding., Comment: 9 pages, 6 figures. Accepted by CIKM 2019 Applied Research Track

The role of visible light on longevity is incompletely understood. Here we show the effect of visible light in Drosophila melanogaster is wavelength specific. Life span was significantly extended by green light, whereas blue light reduced longevity dramatically, and minor impact was observed with red light. While oxidative stress, heat stress, or caloric restriction does not contribute to the beneficial effect of green light, our study found that the life span extension effect of green light might be mediated by microbiota or photosensitive micronutrients in food medium. In conclusion, we report that green light can extend longevity and present the potential of light as a noninvasive therapy for aging-related diseases.

The growing complexity of modern Cyber-Physical Systems (CPS) and the frequent communication between their components make them vulnerable to malicious attacks. As a result, secure state estimation is a critical requirement for the control of these systems. Many existing secure state estimation methods suffer from combinatorial complexity which grows with the number of states and sensors in the system. This complexity can be mitigated using optimization-based methods that relax the original state estimation problem, although at the cost of optimality as these methods often identify attack-free sensors as attacked. In this paper, we propose a new optimal graph-search algorithm to correctly identify malicious attacks and to securely estimate the states even in large-scale CPS modeled as linear time-invariant systems. The graph consists of layers, each one containing two nodes capturing a truth assignment of any given sensor, and directed edges connecting adjacent layers only. Then, our algorithm searches the layers of this graph incrementally, favoring directions at higher layers with more attack-free assignments, while actively managing a repository of nodes to be expanded at later iterations. The proposed search bias and the ability to revisit nodes in the repository and self-correct, allow our graph-search algorithm to reach the optimal assignment faster and tackle larger problems. We show that our algorithm is complete and optimal provided that process and measurement noises do not dominate the attack signal. Moreover, we provide numerical simulations that demonstrate the ability of our algorithm to correctly identify attacked sensors and securely reconstruct the state. Our simulations show that our method outperforms existing algorithms both in terms of optimality and execution time., Comment: 16 pages, 10 figures

Answering complex questions that involve multiple entities and multiple relations using a standard knowledge base is an open and challenging task. Most existing KBQA approaches focus on simpler questions and do not work very well on complex questions because they were not able to simultaneously represent the question and the corresponding complex query structure. In this work, we encode such complex query structure into a uniform vector representation, and thus successfully capture the interactions between individual semantic components within a complex question. This approach consistently outperforms existing methods on complex questions while staying competitive on simple questions.

This paper studies the problem of discovering the structured knowledge representation of binary natural language relations.The representation, known as the schema, generalizes the traditional path of predicates to support more complex semantics.We present a search algorithm to generate schemas over a knowledge base, and propose a data-driven learning approach to discover the most suitable representations to one relation. Evaluation results show that inferred schemas are able to represent precise semantics, and can be used to enrich manually crafted knowledge bases.

This paper presents a framework to model the semantic representation of binary relations produced by open information extraction systems. For each binary relation, we infer a set of preferred types on the two arguments simultaneously, and generate a ranked list of type pairs which we call schemas. All inferred types are drawn from the Freebase type taxonomy, which are human readable. Our system collects 171,168 binary relations from ReVerb, and is able to produce top-ranking relation schemas with a mean reciprocal rank of 0.337.