Héctor Llorens

Mark Collier, Hector Urdiales Llorens

Contextual multi-armed bandit problems arise frequently in important industrial applications. Existing solutions model the context either linearly, which enables uncertainty driven (principled) exploration, or non-linearly, by using epsilon-greedy exploration policies. Here we present a deep learning framework for contextual multi-armed bandits that is both non-linear and enables principled exploration at the same time. We tackle the exploration vs. exploitation trade-off through Thompson sampling by exploiting the connection between inference time dropout and sampling from the posterior over the weights of a Bayesian neural network. In order to adjust the level of exploration automatically as more data is made available to the model, the dropout rate is learned rather than considered a hyperparameter. We demonstrate that our approach substantially reduces regret on two tasks (the UCI Mushroom task and the Casino Parity task) when compared to 1) non-contextual bandits, 2) epsilon-greedy deep contextual bandits, and 3) fixed dropout rate deep contextual bandits. Our approach is currently being applied to marketing optimization problems at HubSpot.

Estela Saquete, Jose Luis Vicedo, Patricio Martínez-Barco et al.

This paper presents a multilayered architecture that enhances the capabilities of current QA systems and allows different types of complex questions or queries to be processed. The answers to these questions need to be gathered from factual information scattered throughout different documents. Specifically, we designed a specialized layer to process the different types of temporal questions. Complex temporal questions are first decomposed into simple questions, according to the temporal relations expressed in the original question. In the same way, the answers to the resulting simple questions are recomposed, fulfilling the temporal restrictions of the original complex question. A novel aspect of this approach resides in the decomposition which uses a minimal quantity of resources, with the final aim of obtaining a portable platform that is easily extensible to other languages. In this paper we also present a methodology for evaluation of the decomposition of the questions as well as the ability of the implemented temporal layer to perform at a multilingual level. The temporal layer was first performed for English, then evaluated and compared with: a) a general purpose QA system (F-measure 65.47% for QA plus English temporal layer vs. 38.01% for the general QA system), and b) a well-known QA system. Much better results were obtained for temporal questions with the multilayered system. This system was therefore extended to Spanish and very good results were again obtained in the evaluation (F-measure 40.36% for QA plus Spanish temporal layer vs. 22.94% for the general QA system).

Leon Derczynski, Hector Llorens, Naushad UzZaman

TimeML is an XML-based schema for annotating temporal information over discourse. The standard has been used to annotate a variety of resources and is followed by a number of tools, the creation of which constitute hundreds of thousands of man-hours of research work. However, the current state of resources is such that many are not valid, or do not produce valid output, or contain ambiguous or custom additions and removals. Difficulties arising from these variances were highlighted in the TempEval-3 exercise, which included its own extra stipulations over conventional TimeML as a response. To unify the state of current resources, and to make progress toward easy adoption of its current incarnation ISO-TimeML, this paper introduces TimeML-strict: a valid, unambiguous, and easy-to-process subset of TimeML. We also introduce three resources -- a schema for TimeML-strict; a validator tool for TimeML-strict, so that one may ensure documents are in the correct form; and a repair tool that corrects common invalidating errors and adds disambiguating markup in order to convert documents from the laxer TimeML standard to TimeML-strict.

Naushad UzZaman, Hector Llorens, James Allen et al.

We describe the TempEval-3 task which is currently in preparation for the SemEval-2013 evaluation exercise. The aim of TempEval is to advance research on temporal information processing. TempEval-3 follows on from previous TempEval events, incorporating: a three-part task structure covering event, temporal expression and temporal relation extraction; a larger dataset; and single overall task quality scores.

Leon Derczynski, Héctor Llorens, Estela Saquete

Automatic annotation of temporal expressions is a research challenge of great interest in the field of information extraction. Gold standard temporally-annotated resources are limited in size, which makes research using them difficult. Standards have also evolved over the past decade, so not all temporally annotated data is in the same format. We vastly increase available human-annotated temporal expression resources by converting older format resources to TimeML/TIMEX3. This task is difficult due to differing annotation methods. We present a robust conversion tool and a new, large temporal expression resource. Using this, we evaluate our conversion process by using it as training data for an existing TimeML annotation tool, achieving a 0.87 F1 measure -- better than any system in the TempEval-2 timex recognition exercise.