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.

Prior studies in multilingual language modeling (e.g., Cotterell et al., 2018; Mielke et al., 2019) disagree on whether or not inflectional morphology makes languages harder to model. We attempt to resolve the disagreement and extend those studies. We compile a larger corpus of 145 Bible translations in 92 languages and a larger number of typological features.1 We fill in missing typological data for several languages and consider corpus-based measures of morphological complexity in addition to expert-produced typological features. We find that several morphological measures are significantly associated with higher surprisal when LSTM models are trained with BPE-segmented data. We also investigate linguistically motivated subword segmentation strategies like Morfessor and Finite-State Transducers (FSTs) and find that these segmentation strategies yield better performance and reduce the impact of a language’s morphology on language modeling.

No abstract

The Free Linguistic Environment (FLE) project focuses on the development of an open and free library of natural language processing functions and a grammar engineering platform for Lexical Functional Grammar (LFG) and related grammar frameworks. In its present state the code-base of FLE contains basic essential elements for LFG-parsing. It uses finite-state-based morphological analyzers and syntactic unification parsers to generate parse-trees and related functional representations for input sentences based on a grammar. It can process a variety of grammar formalisms, which can be used independently or serve as backbones for the LFG parser. Among the supported formalisms are Context-free Grammars (CFG), Probabilistic Contextfree Grammars (PCFG), and all formal grammar components of the XLEgrammar formalism. The current implementation of the LFG-parser includes the possibility to use a PCFG backbone to model probabilistic c-structures. It also includes f-structure representations that allow for the specification or calculation of probabilities for complete f-structure representations, as well as for sub-paths in f-structure trees. Given these design features, FLE enables various forms of probabilistic modeling of c-structures and f-structures for input or output sentences that go beyond the capabilities of other technologies based on the LFG framework.