The standard HPSG analysis of Germanic verb clusters can not explain the observed narrow-scope readings of adjuncts in such verb clusters.We present an extension of the HPSG analysis that accounts for the systematic ambiguity of the scope of adjuncts in verb cluster constructions, by treating adjuncts as members of the subcat list. The extension uses powerful recursive lexical rules, implemented as complex constraints. We show how 'delayed evaluation' techniques from constraint-logic programming can be used to process such lexical rules.

This study focuses on an essential precondition for reproducibility in computational linguistics: the willingness of authors to share relevant source code and data. Ten years after Ted Pedersen’s influential “Last Words” contribution in Computational Linguistics, we investigate to what extent researchers in computational linguistics are willing and able to share their data and code. We surveyed all 395 full papers presented at the 2011 and 2016 ACL Annual Meetings, and identified whether links to data and code were provided. If working links were not provided, authors were requested to provide this information. Although data were often available, code was shared less often. When working links to code or data were not provided in the paper, authors provided the code in about one third of cases. For a selection of ten papers, we attempted to reproduce the results using the provided data and code. We were able to reproduce the results approximately for six papers. For only a single paper did we obtain the exact same results. Our findings show that even though the situation appears to have improved comparing 2016 to 2011, empiricism in computational linguistics still largely remains a matter of faith. Nevertheless, we are somewhat optimistic about the future. Ensuring reproducibility is not only important for the field as a whole, but also seems worthwhile for individual researchers: The median citation count for studies with working links to the source code is higher.

In this paper, we explore the performance of a linear SVM trained on languageindependent character features for the NLI Shared Task 2017. Our basic system (GRONINGEN) achieves the best performance (87.56 F1-score) on the evaluation set using only 1-9 character n-grams as features. We compare this against several ensemble and meta-classifiers in order to examine how the linear system fares when combined with other, especially non-linear classifiers. Special emphasis is placed on the topic bias that exists by virtue of the assessment essay prompt distribution.

We present an approach to learning multi-sense word embeddings relying both on monolingual and bilingual information. Our model consists of an encoder, which uses monolingual and bilingual context (i.e. a parallel sentence) to choose a sense for a given word, and a decoder which predicts context words based on the chosen sense. The two components are estimated jointly. We observe that the word representations induced from bilingual data outperform the monolingual counterparts across a range of evaluation tasks, even though crosslingual information is not available at test time.

A generalization of the dictionary data structure is described, called tuple dictionary. A tuple dictionary represents the mapping of n-tuples of strings to some value. This data structure is motivated by practical applications in speech and language processing, in which very large instances of tuple dictionaries are used to represent language models. A technique for compact representation of tuple dictionaries is presented. The technique can be seen as an application and extension of perfect hashing by means of ÿnite-state automata. Preliminary practical experiments indicate that the technique yields considerable and important space savings of up to 90% in practice.