Veselin Stoyanov

Learn More
This paper describes the fifth year of the Sentiment Analysis in Twitter task. SemEval-2017 Task 4 continues with a rerun of the subtasks of SemEval-2016 Task 4, which include identifying the overall sentiment of the tweet, sentiment towards a topic with classification on a twopoint and on a five-point ordinal scale, and quantification of the distribution(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, anaphoricity(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 subtasks. Two were reruns from previous(More)
Despite the existence of several noun phrase coreference resolution data sets as well as several formal evaluations on the task, it remains frustratingly difficult to compare results across different coreference 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 have created a software infrastructure called Reconcile that is a platform for the development of learning-based noun phrase (NP) coreference resolution systems. Reconcile’s architecture was designed to facilitate the rapid creation of coreference resolutions systems, easy implementation of new feature sets and approaches to coreference resolution, and(More)
Graphical models are often used “inappropriately,” with approximations in the topology, 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)
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)