Understanding verbs is essential for many natural language tasks. Tothis end, large-scale lexical resources such as FrameNet have beenmanually constructed to annotate the semantics of verbs (frames) andtheir arguments (frame elements or FEs) in example sentences.Our goal is to "semantically conceptualize" example sentences by connectingFEs to knowledge base (KB) concepts.For example, connecting Employer FE to company concept in the KB enables the understanding thatany (unseen) company can also be FE examples.However, a naive adoption of existing KB conceptualization technique, focusingon scenarios of conceptualizing a few terms,cannot 1) scale to many FE instances (average of 29.7 instances for all FEs) and 2) leverage interdependence betweeninstances and concepts.We thus propose a scalable k-truss clusteringand a Markov Random Field (MRF) model leveraging interdependence betweenconcept-instance, concept-concept, and instance-instance pairs. Our extensive analysis with real-life data validates that our approachimproves not only the quality of the identified concepts for FrameNet, but alsothat of applications such as selectional preference.

Neural language models are a powerful tool to embed words into semantic vector spaces. However, learning such models generally relies on the availability of abundant and diverse training examples. In highly specialised domains this requirement may not be met due to difficulties in obtaining a large corpus, or the limited range of expression in average use. Such domains may encode prior knowledge about entities in a knowledge base or ontology. We propose a generative model which integrates evidence from diverse data sources, enabling the sharing of semantic information. We achieve this by generalising the concept of co-occurrence from distributional semantics to include other relationships between entities or words, which we model as affine transformations on the embedding space. We demonstrate the effectiveness of this approach by outperforming recent models on a link prediction task and demonstrating its ability to profit from partially or fully unobserved data training labels. We further demonstrate the usefulness of learning from different data sources with overlapping vocabularies.

We present the first probabilistic model to capture all levels of the Minsky Frame structure, with the goal of corpus-based induction of scenario definitions. Our model unifies prior efforts in discourse-level modeling with that of Fillmore's related notion of frame, as captured in sentence-level, FrameNet semantic parses; as part of this, we resurrect the coupling among Minsky's frames, Schank's scripts and Fillmore's frames, as originally laid out by those authors. Empirically, our approach yields improved scenario representations, reflected quantitatively in lower surprisal and more coherent latent scenarios.

We introduce ExTaSem!, a novel approach for the automatic learning of lexical taxonomies from domain terminologies. First, we exploit a very large semantic network to collect housands of in-domain textual definitions. Second, we extract (hyponym, hypernym) pairs from each definition with a CRF-based algorithm trained on manually-validated data. Finally, we introduce a graph induction procedure which constructs a full-fledged taxonomy where each edge is weighted according to its domain pertinence. ExTaSem! achieves state-of-the-art results in the following taxonomy evaluation experiments: (1) Hypernym discovery, (2) Reconstructing gold standard taxonomies, and (3) Taxonomy quality according to structural measures. We release weighted taxonomies for six domains for the use and scrutiny of the community.

Verbs are important in semantic understanding of natural language. Traditional verb representations, such as FrameNet, PropBank, VerbNet, focus on verbs' roles. These roles are too coarse to represent verbs' semantics. In this paper, we introduce verb patterns to represent verbs' semantics, such that each pattern corresponds to a single semantic of the verb. First we analyze the principles for verb patterns: generality and specificity. Then we propose a nonparametric model based on description length. Experimental results prove the high effectiveness of verb patterns. We further apply verb patterns to context-aware conceptualization, to show that verb patterns are helpful in semantic-related tasks.

What capabilities are required for an AI system to pass standard 4th Grade Science Tests? Previous work has examined the use of Markov Logic Networks (MLNs) to represent the requisite background knowledge and interpret test questions, but did not improve upon an information retrieval (IR) baseline. In this paper, we describe an alternative approach that operates at three levels of representation and reasoning: information retrieval, corpus statistics, and simple inference over a semi-automatically constructed knowledge base, to achieve substantially improved results. We evaluate the methods on six years of unseen, unedited exam questions from the NY Regents Science Exam (using only non-diagram, multiple choice questions), and show that our overall system’s score is 71.3%, an improvement of 23.8% (absolute) over the MLN-based method described in previous work. We conclude with a detailed analysis, illustrating the complementary strengths of each method in the ensemble. Our datasets are being released to enable further research.

Churn happens when a customer leaves a brand or stop using its services. Brands reduce their churn rates by identifying and retaining potential churners through customer retention campaigns. In this paper, we consider the problem of classifying micro-posts as churny or non-churny with respect to a given brand. Motivated by the recent success of recurrent neural networks (RNNs) in word representation, we propose to utilize RNNs to learn micro-post and churn indicator representations. We show that such representations improve the performance of churn detection in microblogs and lead to more accurate ranking of churny contents. Furthermore, in this researchwe show that state-of-the-art sentiment analysis approaches fail to identify churny contents. Experiments on Twitter data about three telco brands show the utility of our approach for this task.

A key advantage the reactive planning approach adopted by BDI-based agents is the ability to recover from plan execution failures, and almost all BDI agent programming languages and platforms provide some form of failure handling mechanism. In general, these consist of simply choosing an alternative plan for the failed subgoal (e.g., JACK, Jadex). In this paper, we propose an alternative approach to recovering from execution failures that relies on exploiting positive interactions between an agent's intentions. A positive interaction occurs when the execution of an action in one intention assists the execution of actions in other intentions (e.g., by (re)establishing their preconditions). We have implemented our approach in a scheduling algorithm for BDI agents which we call SP. The results of a preliminary empirical evaluation of SP suggest our approach out-performs existing failure handling mechanisms used by state-of-the-art BDI languages. Moreover, the computational overhead of SP is modest.

Communication between agents has the potential to improve team performance of collaborative tasks. However, communication is not free in most domains, requiring agents to reason about the costs and benefits of sharing information. In this work, we develop an online, decentralized communication policy, ConTaCT, that enables agents to decide whether or not to communicate during time-critical collaborative tasks in unknown, deterministic environments. Our approach is motivated by real-world applications, including the coordination of disaster response and search and rescue teams. These settings motivate a model structure that explicitly represents the world model as initially unknown but deterministic in nature, and that de-emphasizes uncertainty about action outcomes. Simulated experiments are conducted in which ConTaCT is compared to other multi-agent communication policies, and results indicate that ConTaCT achieves comparable task performance while substantially reducing communication overhead.

Many solution methods for Markov Decision Processes (MDPs) exploit structure in the problem and are based on value function factorization. Especially multiagent settings, however, are known to suffer from an exponential increase in value component sizes as interactions become denser, restricting problem sizes and types that can be handled. We present an approach to mitigate this limitation for certain types of multiagent systems, exploiting a property that can be thought of as "anonymous influence" in the factored MDP. We show how representational benefits from anonymity translate into computational efficiencies, both for variable elimination in a factor graph and for the approximate linear programming solution to factored MDPs. Our methods scale to factored MDPs that were previously unsolvable, such as the control of a stochastic disease process over densely connected graphs with 50 nodes and 25 agents.