The translation of prepositions is often considered one of the more difficult tasks within the field of machine translation. We describe an experiment using transformationbased learning to induce rules to select the appropriate target language preposition from aligned bilingual data. Results show an accuracy of 84.9%, to be compared with a baseline of 75.5%, where the most frequent translation ...

The paper presents the work in progress for a PhD thesis about preposition incorporation Bulgarian BulTreeBank WordNet. Being one of most polysemous parts speech, prepositions are still relatively challenging NLP and usually missing wordnets. A semantic classification, model synsets synset relations proposed. planned applications directions future processing introduced.

knowledge of marble bag composition has been triggered by many individual examples of marble bags. More interestingly, this learner was able to have certain expectations about a marble bag containing a novel marble color by learning from bags containing only black or white marbles. Translating this to a linguistic example, suppose the marble bags are individual sentences. Some sentences contain...

This paper explores from a neuropsychological perspective the relation between the meanings of English locative prepositions (e.g., in, on, above, below) and the kinds of representations that are used for many visuospatial processes such as recognising, drawing, and constructing spatially complex objects. One possibility that has been proposed by some psycholinguists is that the meanings of pre...

Abstract Non-finite complementation strategies found in American Norwegian (AmNo) (made available by the Corpus of Nordic Speech (CANS)) reveal unique and diverging patterns when compared to both standard dialectal English. We argue this paper that majority these divergent structures are result overextension (Rinke & Flores, 2014; Rinke et al., 2018; Putnam Hoffman, 2021; Kupisch, 2014), wh...

In creating an English grammar checking software product, we implemented a large-coverage grammar based on the dependency grammar formalism. This implementat ion required some adaptation of current linguistic description to prevent serious overgeneration of parse trees. Here, • we present one particular example, that of preposition stranding and dangling prepositions, where implementing an alte...

This paper describes the submission of the National University of Singapore (NUS) to the HOO 2012 shared task. Our system uses a pipeline of confidence-weighted linear classifiers to correct determiner and preposition errors. Our system achieves the highest correction F1 score on the official test set among all 14 participating teams, based on gold-standard edits both before and after revision.

This paper describes ongoing work, aimed at producing a lexicon of prepositions, i.e. relations denoted by prepositions, to be used for information retrieval purposes. The work is ontology based, which for this project means that the ontological types of the arguments of the preposition are considered, rather than the word forms. Thus, sense distinctions are made based on ontological constraint...