Mark Cieliebak

Distributed computing by mobile robots : gathering

Consider a set of

Leveraging Large Amounts of Weakly Supervised Data for Multi-Language Sentiment Classification

n>2

Swiss-Chocolate: Sentiment Detection using Sparse SVMs and Part-Of-Speech n-Grams

identical mobile computational entities in the plane, called robots, operating in Look-Compute-Move cycles, without any means of direct communication. The Gathering Problem is the primitive task of all entities gathering in finite time at a point not fixed in advance, without any external control. The problem has been extensively studied in the literature under a variety of strong assumptions (e.g., synchronicity of the cycles, instantaneous movements, complete memory of the past, common coordinate system, etc.). In this paper we consider the setting without those assumptions, that is, when the entities are oblivious (i.e., they do not remember results and observations from previous cycles), disoriented (i.e., have no common coordinate system), and fully asynchronous (i.e., no assumptions exist on timing of cycles and activities within a cycle). The existing algorithmic contributions for such robots are limited to solutions for

A Twitter corpus and benchmark resources for german sentiment analysis

n \leq 4

Sentiment Analysis using Convolutional Neural Networks with Multi-Task Training and Distant Supervision on Italian Tweets

or for restricted sets of initial configura...

Potential and limitations of cross-domain sentiment classification

This paper presents a novel approach for multi-lingual sentiment classification in short texts. This is a challenging task as the amount of training data in languages other than English is very limited. Previously proposed multi-lingual approaches typically require to establish a correspondence to English for which powerful classifiers are already available. In contrast, our method does not require such supervision. We leverage large amounts of weakly-supervised data in various languages to train a multi-layer convolutional network and demonstrate the importance of using pre-training of such networks. We thoroughly evaluate our approach on various multi-lingual datasets, including the recent SemEval-2016 sentiment prediction benchmark (Task 4), where we achieved state-of-the-art performance. We also compare the performance of our model trained individually for each language to a variant trained for all languages at once. We show that the latter model reaches slightly worse - but still acceptable - performance when compared to the single language model, while benefiting from better generalization properties across languages.

Influence of flipped classroom on technical skills and non-technical competences of IT students

We describe a classifier to predict the message-level sentiment of English microblog messages from Twitter. This paper describes the classifier submitted to the SemEval-2014 competition (Task 9B). Our approach was to build up on the system of the last year’s winning approach by NRC Canada 2013 (Mohammad et al., 2013), with some modifications and additions of features, and additional sentiment lexicons. Furthermore, we used a sparse (‘1-regularized) SVM, instead of the more commonly used ‘2-regularization, resulting in a very sparse linear classifier.

Swiss-Chocolate: Combining Flipout Regularization and Random Forests with Artificially Built Subsystems to Boost Text-Classification for Sentiment

In this paper we present SB10k, a new corpus for sentiment analysis with approx. 10,000 German tweets. We use this new corpus and two existing corpora to provide state-of-the-art benchmarks for sentiment analysis in German: we implemented a CNN (based on the winning system of SemEval-2016) and a feature-based SVM and compare their performance on all three corpora. For the CNN, we also created German word embeddings trained on 300M tweets. These word embeddings were then optimized for sentiment analysis using distant-supervised learning. The new corpus, the German word embeddings (plain and optimized), and source code to re-run the benchmarks are publicly available.

JOINT_FORCES: Unite Competing Sentiment Classifiers with Random Forest

English. In this paper, we propose a classifier for predicting sentiments of Italian Twitter messages. This work builds upon a deep learning approach where we leverage large amounts of weakly labelled data to train a 2-layer convolutional neural network. To train our network we apply a form of multi-task training. Our system participated in the EvalItalia-2016 competition and outperformed all other approaches on the sentiment analysis task. In questo articolo, presentiamo un sistema per la classificazione di soggettività e polarità di tweet in lingua italiana. L’approccio descritto si basa su reti neurali. In particolare, utilizziamo un dataset di 300M di tweet per addestrare una convolutional neural network. Il sistema è stato addestrato e valutato sui dati forniti dagli organizzatori di Sentipolc, task di sentiment analysis su Twitter organizzato nell’ambito di Evalita 2016..

Gathering autonomous mobile robots in non-totally symmetric configurations

In this paper we investigate the crossdomain performance of sentiment analysis systems. For this purpose we train a convolutional neural network (CNN) on data from different domains and evaluate its performance on other domains. Furthermore, we evaluate the usefulness of combining a large amount of different smaller annotated corpora to a large corpus. Our results show that more sophisticated approaches are required to train a system that works equally well on various domains.