Idioms present many challenges to semantic annotation in a lexicalized framework, which leads to them being underrepresented or inadequately annotated in sembanks. In this work, we address this problem with respect to verbal idioms in the Parallel Meaning Bank (PMB), specifically in its German part, where only some idiomatic expressions have been annotated correctly. We first select candidate idiomatic expressions, then determine their idiomaticity status and whether they are decomposable or not, and then we annotate their semantics using WordNet senses and VerbNet semantic roles. Overall, inter-annotator agreement is very encouraging. A difficulty, however, is to choose the correct word sense. This is not surprising, given that English synsets are many and there is often no unique mapping from German idioms and words to them. Besides this, there are many subtle differences and interesting challenging cases. We discuss some of them in this paper.

In this paper we examine a BiLSTM architecture for disambiguating verbal potentially idiomatic expressions (PIEs) as to whether they are used in a literal or an idiomatic reading with respect to explainability of its decisions. Concretely, we extend the BiLSTM with an additional attention mechanism and track the elements that get the highest attention. The goal is to better understand which parts of an input sentence are particularly discriminative for the classifier’s decision, based on the assumption that these elements receive a higher attention than others. In particular, we investigate POS tags and dependency relations to PIE verbs for the tokens with the maximal attention. It turns out that the elements with maximal attention are oftentimes nouns that are the subjects of the PIE verb. For longer sentences however (i.e., sentences containing, among others, more modifiers), the highest attention word often stands in a modifying relation to the PIE components. This is particularly frequent for PIEs classified as literal. Our study shows that an attention mechanism can contribute to the explainability of classification decisions that depend on specific cues in the sentential context, as it is the case for PIE disambiguation.

Supervised disambiguation of verbal idioms (VID) poses special demands on the quality and quantity of the annotated data used for learning and evaluation. In this paper, we present a new VID corpus for German and perform a series of VID disambiguation experiments on it. Our best classifier, based on a neural architecture, yields an error reduction across VIDs of 57% in terms of accuracy compared to a simple majority baseline.

We propose to tackle the problem of verbal multiword expression (VMWE) identification using a neural graph parsing-based approach. Our solution involves encoding VMWE annotations as labellings of dependency trees and, subsequently, applying a neural network to model the probabilities of different labellings. This strategy can be particularly effective when applied to discontinuous VMWEs and, thanks to dense, pre-trained word vector representations, VMWEs unseen during training. Evaluation of our approach on three PARSEME datasets (German, French, and Polish) shows that it allows to achieve performance on par with the previous state-of-the-art (Al Saied et al., 2018).

In this paper, we describe Mumpitz, the system we submitted to the PARSEME Shared task on automatic identification of verbal multiword expressions (VMWEs). Mumpitz consists of a Bidirectional Recurrent Neural Network (BRNN) with Long Short-Term Memory (LSTM) units and a heuristic that leverages the dependency information provided in the PARSEME corpus data to differentiate VMWEs in a sentence. We submitted results for seven languages in the closed track of the task and for one language in the open track. For the open track we used the same system, but with pretrained instead of randomly initialized word embeddings to improve the system performance.

Non-compositional multiword expressions (MWEs) still pose serious issues for a variety of natural language processing tasks and their ubiquity makes it impossible to get around methods which automatically identify these kind of MWEs. The method presented in this paper was inspired by Sporleder and Li (2009) and is able to discriminate between the literal and non-literal use of an MWE in an unsupervised way. It is based on the assumption that words in a text form cohesive units. If the cohesion of these units is weakened by an expression, it is classified as literal, and otherwise as idiomatic. While Sporleder an Li used Normalized Google Distance to modell semantic similarity, the present work examines the use of a variety of different word embeddings.