We propose a sentence generation strategy that describes images by predicting the most likely nouns, verbs, scenes and prepositions that make up the core sentence structure. The input are initial noisy estimates of the objects and scenes detected in the image using state of the art trained detectors. As predicting actions from still images directly is unreliable, we use a language model trained...

Prepositions1—as well as prepositional phrases (PPs) and markers of various sorts— have a mixed history in computational linguistics (CL), as well as related fields such as artificial intelligence, information retrieval (IR), and computational psycholinguistics: On the one hand they have been championed as being vital to precise language understanding (e.g., in information extraction), and on t...

The present work is concerned with projective prepositions, which express the relation between two objects by referring to a direction in three-dimensional space. The projective prepositions have been regarded as expressing simple schematic relations of a geometric nature. A theory of the apprehension of projective relations can account for their meanings when they express strictly geometric re...

Prepositions in natural languages often appear to be governed by arbitrary conventionalized idiomatic uses (e.g., I was born in May, I will see you on Sunday). We present empirical evidence that such prepositional uses are not entirely arbitrary, as they activate image-schematic perceptual simulations during language processing. In Experiment 1, native speakers of English were prompted to think...

In recent years, we have witnessed the concomitant rise of communicative and contextualised approaches as well as the paradigmatic development of the Mobile Assisted Language Learning (MALL) framework in analyzing language learning. The focus of MALL research has gradually shifted from content-based (delivery of learning content through mobile devices) to design-oriented (authentic and/or socia...

We are developing a system in which a user can control virtual agents through natural language dialogue. We particularly focus on the semantic analysis of spatial expressions in natural language instructions. Spatial expressions are relative to the speaker’s viewpoint and the indicated positions can change dynamically. In this paper we propose a semantic representation using lambda structures. ...