A discourse typically involves numerous entities, but few are mentioned more than once. Distinguishing those that die out after just one mention (singleton) from those that lead longer lives (coreferent) would dramatically simplify the hypothesis space for coreference resolution models, leading to increased performance. To realize these gains, we build a classifier for predicting the singleton/coreferent distinction. The models feature representations synthesize linguistic insights about the factors affecting discourse entity lifespans (especially negation, modality, and attitude predication) with existing results about the benefits of surface (part-of-speech and n-gram-based) features for coreference resolution. The model is effective in its own right, and the feature representations help to identify the anchor phrases in bridging anaphora as well. Furthermore, incorporating the model into two very different state-of-the-art coreference resolution systems, one rule-based and the other learning-based, yields significant performance improvements.

The AIIDE-14 Workshop program was held Friday and Saturday, October 3–4, 2014 at North Carolina State University in Raleigh, North Carolina. The workshop program included five workshops covering a wide range of topics. The titles of the workshops held Friday were Games and Natural Language Processing, and Artificial Intelligence in Adversarial Real-Time Games. The titles of the workshops held Saturday were Diversity in Games Research, Experimental Artificial Intelligence in Games, and Musical Metacreation. This article presents short summaries of those events.

The AAAI-14 Workshop program was held Sunday and Monday, July 27–28, 2012, at the Québec City Convention Centre in Québec, Canada. Canada. The AAAI-14 workshop program included fifteen workshops covering a wide range of topics in artificial intelligence. The titles of the workshops were AI and Robotics; Artificial Intelligence Applied to Assistive Technologies and Smart Environments; Cognitive Computing for Augmented Human Intelligence; Computer Poker and Imperfect Information; Discovery Informatics; Incentives and Trust in Electronic Communities; Intelligent Cinematography and Editing; Machine Learning for Interactive Systems: Bridging the Gap between Perception, Action and Communication; Modern Artificial Intelligence for Health Analytics; Multiagent Interaction without Prior Coordination; Multidisciplinary Workshop on Advances in Preference Handling; Semantic Cities — Beyond Open Data to Models, Standards and Reasoning; Sequential Decision Making with Big Data; Statistical Relational AI; and The World Wide Web and Public Health Intelligence. This article presents short summaries of those events.

Information extraction (IE) is the technique for transforming unstructured textual data into structured representation that can be understood by machines. The exponential growth of the Web generates an exceptional quantity of data for which automatic knowledge capture is essential. This work describes the methodology for web scale information extraction in the LODIE project (linked open data information extraction) and highlights results from the early experiments carried out in the initial phase of the project. LODIE aims to develop information extraction techniques able to scale at web level and adapt to user information needs. The core idea behind LODIE is the usage of linked open data, a very large-scale information resource, as a ground-breaking solution for IE, which provides invaluable annotated data on a growing number of domains. This article has two objectives. First, describing the LODIE project as a whole and depicting its general challenges and directions. Second, describing some initial steps taken towards the general solution, focusing on a specific IE subtask, wrapper induction.

We describe TickTock, a conversational agent designed to engage humans on topics of its choosing and to carry on an interaction for as long as possible. Our prototype uses a database of talk show transcripts featuring guests from the film industry. To be an interesting companion Tick Tock uses immediate context from the last two turns to formulate queries into a database of utterances. The process is automatic. TickTock monitors user engagement and performs certain moves, such as topic shifts, based on its assessment of user state. Initially we used utterance content for monitoring and subsequently we begun to investigate non-language cues, such as prosody and visual cues to create a more robust engagement model based on multiple human communication channels.

A method for determining whether given text is a rumor or disinformation is proposed, based on web mining and linguistic technology comparing two paragraphs of text. We hypothesize about a family of content generation algorithms which are capable of producing disinformation from a portion of genuine, original text. We then propose a disinformation detection algorithm which finds a candidate source of text on the web and compares it with the given text, applying parse thicket technology. Parse thicket is graph combined from a sequence of parse trees augmented with inter-sentence relations for anaphora and rhetoric structures. We evaluate our algorithm in the domain of customer reviews, considering a product review as an instance of possible disinformation. It is confirmed as a plausible way to detect rumor and disinformation in a web document. Linguistic approach presented here complements social network structure-based described on a corpus of research on disinformation detection.

We propose a graphical model for representing networks of stochastic processes, the minimal generative model graph. It is based on reduced factorizations of the joint distribution over time. We show that under appropriate conditions, it is unique and consistent with another type of graphical model, the directed information graph, which is based on a generalization of Granger causality. We demonstrate how directed information quantifies Granger causality in a particular sequential prediction setting. We also develop efficient methods to estimate the topological structure from data that obviate estimating the joint statistics. One algorithm assumes upper-bounds on the degrees and uses the minimal dimension statistics necessary. In the event that the upper-bounds are not valid, the resulting graph is nonetheless an optimal approximation. Another algorithm uses near-minimal dimension statistics when no bounds are known but the distribution satisfies a certain criterion. Analogous to how structure learning algorithms for undirected graphical models use mutual information estimates, these algorithms use directed information estimates. We characterize the sample-complexity of two plug-in directed information estimators and obtain confidence intervals. For the setting when point estimates are unreliable, we propose an algorithm that uses confidence intervals to identify the best approximation that is robust to estimation error. Lastly, we demonstrate the effectiveness of the proposed algorithms through analysis of both synthetic data and real data from the Twitter network. In the latter case, we identify which news sources influence users in the network by merely analyzing tweet times.

Despite having various attractive qualities such as high prediction accuracy and the ability to quantify uncertainty and avoid over-fitting, Bayesian Matrix Factorization has not been widely adopted because of the prohibitive cost of inference. In this paper, we propose a scalable distributed Bayesian matrix factorization algorithm using stochastic gradient MCMC. Our algorithm, based on Distributed Stochastic Gradient Langevin Dynamics, can not only match the prediction accuracy of standard MCMC methods like Gibbs sampling, but at the same time is as fast and simple as stochastic gradient descent. In our experiments, we show that our algorithm can achieve the same level of prediction accuracy as Gibbs sampling an order of magnitude faster. We also show that our method reduces the prediction error as fast as distributed stochastic gradient descent, achieving a 4.1% improvement in RMSE for the Netflix dataset and an 1.8% for the Yahoo music dataset.

Knowledge bases have the potential to advance artificial intelligence, but often suffer from recall problems, i.e., lack of knowledge of new entities and relations. On the contrary, social media such as Twitter provide abundance of data, in a timely manner: information spreads at an incredible pace and is posted long before it makes it into more commonly used resources for knowledge extraction. In this paper we address the question whether we can exploit social media to extract new facts, which may at first seem like finding needles in haystacks. We collect tweets about 60 entities in Freebase and compare four methods to extract binary relation candidates, based on syntactic and semantic parsing and simple mechanism for factuality scoring. The extracted facts are manually evaluated in terms of their correctness and relevance for search. We show that moving from bottom-up syntactic or semantic dependency parsing formalisms to top-down frame-semantic processing improves the robustness of knowledge extraction, producing more intelligible fact candidates of better quality. In order to evaluate the quality of frame semantic parsing on Twitter intrinsically, we make a multiply frame-annotated dataset of tweets publicly available.

Tag recommendation has become one of the most important ways of organizing and indexing online resources like articles, movies, and music. Since tagging information is usually very sparse, effective learning of the content representation for these resources is crucial to accurate tag recommendation. Recently, models proposed for tag recommendation, such as collaborative topic regression and its variants, have demonstrated promising accuracy. However, a limitation of these models is that, by using topic models like latent Dirichlet allocation as the key component, the learned representation may not be compact and effective enough. Moreover, since relational data exist as an auxiliary data source in many applications, it is desirable to incorporate such data into tag recommendation models. In this paper, we start with a deep learning model called stacked denoising autoencoder (SDAE) in an attempt to learn more effective content representation. We propose a probabilistic formulation for SDAE and then extend it to a relational SDAE (RSDAE) model. RSDAE jointly performs deep representation learning and relational learning in a principled way under a probabilistic framework. Experiments conducted on three real datasets show that both learning more effective representation and learning from relational data are beneficial steps to take to advance the state of the art.