Learn More
We aim to shed light on the state-of-the-art in NP coreference resolution by teasing apart the differences in the MUC and ACE task definitions, the assumptions made in evaluation methodologies, and inherent differences in text corpora. First, we examine three subproblems that play a role in coreference resolution: named entity recognition, anaphoric-ity(More)
In this paper, we describe the 2015 iteration of the SemEval shared task on Sentiment Analysis in Twitter. This was the most popular sentiment analysis shared task to date with more than 40 teams participating in each of the last three years. This year's shared task competition consisted of five sentiment prediction sub-tasks. Two were reruns from previous(More)
Despite the existence of several noun phrase coref-erence resolution data sets as well as several formal evaluations on the task, it remains frustratingly difficult to compare results across different corefer-ence resolution systems. This is due to the high cost of implementing a complete end-to-end coreference resolution system, which often forces(More)
Fine-grained subjectivity analysis has been the subject of much recent research attention. As a result, the field has gained a number of working definitions, technical approaches and manually annotated corpora that cover many facets of subjectivity. Little work has been done, however, on one aspect of fine-grained opinions – the specification and(More)
We describe an approach to coreference resolution that relies on the intuition that easy decisions should be made early, while harder decisions should be left for later when more information is available. We are inspired by the recent success of the rule-based system of Raghunathan et al. (2010), which relies on the same intuition. Our system, however,(More)
We investigate techniques to support the answering of opinion-based questions. We first present the OpQA corpus of opinion questions and answers. Using the corpus , we compare and contrast the properties of fact and opinion questions and answers. Based on the disparate characteristics of opinion vs. fact answers, we argue that traditional fact-based QA(More)
Graphical models are often used " inappropriately , " with approximations in the topol-ogy, inference, and prediction. Yet it is still common to train their parameters to approximately maximize training likelihood. We argue that instead, one should seek the parameters that minimize the empirical risk of the entire imperfect system. We show how to locally(More)
Our team from the JHU HLTCOE participated in the Entity Linking and Cold Start Knowledge Base tasks in this year's Text Analysis Conference Knowledge Base Population evaluation. We have previously participated in TAC-KBP entity linking evaluations in 2009, 2010, and 2011. This year we developed two new systems: CALE (Context Aware Linker of Entities) and(More)
In this paper, we explore the utility of attitude types for improving question answering (QA) on both web-based discussions and news data. We present a set of attitude types developed with an eye toward QA and show that they can be reliably annotated. Using the attitude annotations, we develop automatic classifiers for recognizing two main types of(More)