This paper presents experimental work on the relative naturalness of subject-oriented reflexives (herself) and pronouns (her) in English locative prepositional phrases (e.g., Michele set a glass next to her/herself). Syntactic approaches anaphor licensing have tended focus lack complementarity such constructions; however, it has long been observed that preferences between forms may depend verb ...

PP-attachments are an important source of errors in parsing natural language. We propose in this article to use data coming from a multimodal corpus, combining textual, visual and conceptual information, as well as a correction strategy, to propose alternative attachments in the output of a parser.

This article focuses on the use of prepositional genitive instead dative for prepositions entsprechend, gemäß and nahe. The aim this study is to evaluate frequency genitives with these in current newspaper texts determine requirements further research. selected are described lexicographically, their usage evaluated a corpus developed by author paper within DeReKo.

Abstract German in Austria is claimed to be shaped by wide-spread dialect use and historical language contact. In this context, variation prepositional phrases (PPs) frequently cited, but still underresearched. Three linguistic variables are particularly interesting: (1) preposition choice (p-choice), (2) case marking PPs (3) preposition–determiner contractions. The present study aims at identi...

The term ‘meaning’, as it is presently employed in Linguistics, a polysemous concept, covering broad range of operational definitions. Focussing on two these definitions, meaning ‘concept’ and ‘context’ (also known ‘distributional semantics’), this paper explores to what extent definitions lead converging conclusions regarding the number nature distinct senses form covers. More specifically, in...

We present a low-rank multi-linear model for the task of solving prepositional phrase attachment ambiguity (PP task). Our model exploits tensor products of word embeddings, capturing all possible conjunctions of latent embeddings. Our results on a wide range of datasets and task settings show that tensor products are the best compositional operation and that a relatively simple multi-linear mod...