Learn More
We present a new method, based on graph theory, for bilingual lexicon extraction without relying on resources with limited availability like parallel corpora. The graphs we use represent linguistic relations between words such as adjectival modification. We experiment with a number of ways of combining different linguistic relations and present a novel(More)
Increasing attention is being devoted to continuous word vector representations (predict vector spaces). Mikolov et al. (2013) reported that a predict vector space seemingly encodes syntactic and semantic properties: Baroni et al. (2014) presented experiments for English where predict vectors outperform count vectors ¢ But how reliable are they for other(More)
Supervised classification needs large amounts of annotated training data that is expensive to create. Two approaches that reduce the cost of annotation are active learning and crowd-sourcing. However, these two approaches have not been combined successfully to date. We evaluate the utility of active learning in crowdsourcing on two tasks, named entity(More)
This paper presents an innovative, complex approach to semantic verb classification that relies on selectional preferences as verb properties. The probabilistic verb class model underlying the semantic classes is trained by a combination of the EM algorithm and the MDL principle, providing soft clusters with two dimensions (verb senses and(More)
We present a novel graph-theoretic method for the initial annotation of high-confidence training data for bootstrapping sentiment classifiers. We estimate polarity using topic-specific PageRank. Sentiment information is propagated from an initial seed lexicon through a joint graph representation of words and documents. We report improved classification(More)
Business processes have tremendously changed the way large companies conduct their business: The integration of information systems into the workflows of their employees ensures a high service level and thus high customer satisfaction. One core aspect of business process engineering are events that steer the workflows and trigger internal processes. Strict(More)
This paper presents a graph-theoretic approach to the identification of yet-unknown word translations. The proposed algorithm is based on the recursive Sim-Rank algorithm and relies on the intuition that two words are similar if they establish similar grammatical relationships with similar other words. We also present a formulation of SimRank in matrix form(More)
Sentiment analysis systems can benefit from the translation of sentiment information. We present a novel, graph-based approach using SimRank, a well-established graph-theoretic algorithm, to transfer sentiment information from a source language to a target language. We evaluate this method in comparison with semantic orientation using pointwise mutual(More)