This work addresses the task of identifying thematic correspondences across subcorpora focused on different topics. We introduce an unsupervised algorithmic framework based on distributional data clustering, which generalizes previous initial works on this task. The empirical results reveal interesting commonalities of different religions. We evaluate the results through measuring the overlap o...

This paper describes our contribution to the social event detection (SED) task of the MediaEval Benchmark 2013. We present a robust unsupervised approach for the clustering of tagged photos and videos into social events. Results on the SED datasets show that the proposed approach yields an excellent generalization ability and state-of-the-art clustering performance.

We present a comparison of different selectional preference models and evaluate them on an automatic verb classification task in German. We find that all the models we compare are effective for verb clustering; the best-performing model uses syntactic information to induce nouns classes from unlabelled data in an unsupervised manner. A very simple model based on lexical preferences is also foun...

A truly personal and reactive computer system should have access to the same information as its user, including the ambient sights and sounds. To this end, we have developed a system for extracting events and scenes from natural audio/visual input. We nd our system can (without any prior labeling of data) cluster the audio/visual data into events, such as passing through doors and crossing the ...

This paper presents our participation in SemEval-2015 task 12 (Aspect Based Sentiment Analysis). We participated employing only unsupervised or weakly-supervised approaches. Our attempt is based on requiring the minimum annotated or hand-crafted content, and avoids training a model using the provided training set. We use a continuous word representations (Word2Vec) to leverage in-domain semanti...

Novel neural network models that can handle complex tasks with fewer examples than before are being developed for a wide range of applications. In some fields, even the creation few labels is laborious task and impractical, especially data require more seconds to generate each label. biotechnological domain, cell cultivation experiments usually done by varying circumstances experiments, seldom ...