We discuss methodological choices in contrastive and diagnostic evaluation in meaning representation parsing, i.e. mapping from natural language utterances to graph-based encodings of its semantic structure. Drawing inspiration from earlier work in syntactic dependency parsing, we transfer and refine several quantitative diagnosis techniques for use in the context of the 2019 shared task on Meaning Representation Parsing (MRP). As in parsing proper, moving evaluation from simple rooted trees to general graphs brings along its own range of challenges. Specifically, we seek to begin to shed light on relative strenghts and weaknesses in different broad families of parsing techniques. In addition to these theoretical reflections, we conduct a pilot experiment on a selection of top-performing MRP systems and one of the five meaning representation frameworks in the shared task. Empirical results suggest that the proposed methodology can be meaningfully applied to parsing into graph-structured target representations, uncovering hitherto unknown properties of the different systems that can inform future development and cross-fertilization across approaches.

Automatic Term Extraction (ATE) extracts terminology from domain-specific corpora. ATE is used in many NLP tasks, including Computer Assisted Translation, where it is typically applied to individual documents rather than the entire corpus. While corpus-level ATE has been extensively evaluated, it is not obvious how the results transfer to document-level ATE. To fill this gap, we evaluate 16 state-of-the-art ATE methods on full-length documents from three different domains, on both corpus and document levels. Unlike existing studies, our evaluation is more realistic as we take into account all gold terms. We show that no single method is best in corpus-level ATE, but C-Value and KeyConceptRelatendess surpass others in document-level ATE.

In this paper, we demonstrate the system built to solve the SemEval-2019 task 4: Hyperpartisan News Detection (Kiesel et al., 2019), the task of automatically determining whether an article is heavily biased towards one side of the political spectrum. Our system receives an article in its raw, textual form, analyzes it, and predicts with moderate accuracy whether the article is hyperpartisan. The learning model used was primarily trained on a manually prelabeled dataset containing news articles. The system relies on the previously constructed SVM model, available in the Python Scikit-Learn library. We ranked 6th in the competition of 42 teams with an accuracy of 79.1% (the winning team had 82.2%).

Compositional Distributional Semantic Models (CDSMs) model the meaning of phrases and sentences in vector space. They have been predominantly evaluated on limited, artificial tasks such as semantic sentence similarity on hand-constructed datasets. This paper argues for lexical substitution (LexSub) as a means to evaluate CDSMs. LexSub is a more natural task, enables us to evaluate meaning composition at the level of individual words, and provides a common ground to compare CDSMs with dedicated LexSub models. We create a LexSub dataset for CDSM evaluation from a corpus with manual “all-words” LexSub annotation. Our experiments indicate that the Practical Lexical Function CDSM outperforms simple component-wise CDSMs and performs on par with the context2vec LexSub model using the same context.

This paper describes the PARSEME Shared Task 1.1 on automatic identification of verbal multiword expressions. We present the annotation methodology, focusing on changes from last year’s shared task. Novel aspects include enhanced annotation guidelines, additional annotated data for most languages, corpora for some new languages, and new evaluation settings. Corpora were created for 20 languages, which are also briefly discussed. We report organizational principles behind the shared task and the evaluation metrics employed for ranking. The 17 participating systems, their methods and obtained results are also presented and analysed.

As multiword expressions (MWEs) exhibit a range of idiosyncrasies, their automatic detection warrants the use of many different features. Tsvetkov and Wintner (2014) proposed a Bayesian network model that combines linguistically motivated features and also models their interactions. In this paper, we extend their model with new features and apply it to Croatian, a morphologically complex and a relatively free word order language, achieving a satisfactory performance of 0.823 F1-score. Furthermore, by comparing against (semi)naive Bayes models, we demonstrate that manually modeling feature interactions is indeed important. We make our annotated dataset of Croatian MWEs freely available.