We present the IUCL system, based on supervised learning, for the shared task on stance detection. Our official submission, the random forest model, reaches a score of 63.60, and is ranked 6th out of 19 teams. We also use gradient boosting decision trees and SVM and merge all classifiers into an ensemble method. Our analysis shows that random forest is good at retrieving minority classes and gradient boosting majority classes. The strengths of different classifiers wrt. precision and recall complement each other in the ensemble.

Abusive language detection has received much attention in the last years, and recent approaches perform the task in a number of different languages. We investigate which factors have an effect on multilingual settings, focusing on the compatibility of data and annotations. In the current paper, we focus on English and German. Our findings show large differences in performance between the two languages.We find that the best performance is achieved by different classification algorithms. Sampling to address class imbalance issues is detrimental for German and beneficial for English. The only similarity that we find is that neither data set shows clear topics when we compare the results of topic modeling to the gold standard. Based on our findings, we can conclude that a multilingual optimization of classifiers is not possible even in settings where comparable data sets are used.

In this paper, we develop an approach to automatically predict user ratings for recipes at Epicurious.com, based on the recipes' reviews. We investigate two distributional methods for feature selection, Information Gain and Bi-Normal Separation; we also compare distributionally selected features to linguistically motivated features and two types of frameworks: a one-layer system where we aggregate all reviews and predict the rating vs. a two-layer system where ratings of individual reviews are predicted and then aggregated. We obtain our best results by using the two-layer architecture, in combination with 5 000 features selected by Information Gain. This setup reaches an overall accuracy of 65.60%, given an upper bound of 82.57%.

We investigate parsing replicability across 7 languages (and 8 treebanks), showing that choices concerning the use of grammatical functions in parsing or evaluation and the influence of the rare word threshold, as well as choices in test sentences and evaluation script options have considerable and often unexpected effects on parsing accuracies. All of those choices need to be carefully documented if we want to ensure replicability.

Parsing Chinese critically depends on correct word segmentation for the parser since incorrect segmentation inevitably causes incorrect parses. We investigate a pipeline approach to segmentation and parsing using word lattices as parser input. We compare CRF-based and lexicon-based approaches to word segmentation. Our results show that the lattice parser is capable of selecting the correction segmentation from thousands of options, thus drastically reducing the number of unparsed sentence. Lexicon-based parsing models have a better coverage than the CRFbased approach, but the many options are more difficult to handle. We reach our best result by using a lexicon from the nbest CRF analyses, combined with highly probable words.