Prepositions in Applications: A Survey and Introduction to the Special Issue

Baldwin, Timothy; Kordoni, Valia; Villavicencio, Aline

doi:10.1162/coli.2009.35.2.119

Cited by 29 publications

(16 citation statements)

References 88 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Baldwin et al [6] summarize linguistic issues in syntactic and semantic accounts of prepositions; such as PP attachment and the semantics of prepositional multi-word phrases. Spatial language and prepositions have been much discussed by cognitive linguists [7]- [11] and by image-schema theorists [12]- [14].…”

Section: Inferring Intended Referentsmentioning

confidence: 99%

A generative probabilistic framework for learning spatial language

Dawson

Wright

Rebguns

et al. 2013

2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL)

View full text Add to dashboard Cite

The language of space and spatial relations is a rich source of abstract semantic structure. We develop a probabilistic model that learns to understand utterances that describe spatial configurations of objects in a tabletop scene by seeking the meaning that best explains the sentence chosen. The inference problem is simplified by assuming that sentences express symbolic representations of (latent) semantic relations between referents and landmarks in space, and that given these symbolic representations, utterances and physical locations are conditionally independent. As such, the inference problem factors into a symbolgrounding component (linking propositions to physical locations) and a symbol-translation component (linking propositions to parse trees). We evaluate the model by eliciting production and comprehension data from human English speakers and find that our system recovers the referent of spatial utterances at a level of proficiency approaching human performance. I. INTRODUCTIONImagine that a friend asks you to "Bring me the thing toward the far corner of the table." This simple request requires fairly sophisticated cognitive processing. You must first identify that she is referring to something on a table, in particular, one with corners. Then, you must orient the table to distinguish "far" vs. "near" corners. Finally, if there is more than one object near a "far" corner, but one is also very near the edge, you might tend to favor the other one, reasoning that it would have been easy to ask for "the one near the edge".We model a version of this problem, with a particular focus on recovering the referent of spatial utterances like "the thing toward the far corner of the table", where the only information available about the intended object is its position relative to a landmark in the scene. Beginning with no knowledge about the meanings of words, but equipped with a small vocabulary of spatial relations (e.g., containment, proximity, ordering in cardinal directions) and abstract representations of objects and their parts (e.g., a table can be represented as a line with ends and a middle, or as a rectangle with corners, quadrants and edges), our model learns probabilistic correspondences between sentences and abstract spatial relations between referents and landmarks by "observing" a teacher repeatedly generating an utterance and pointing to a location in space.Clearly a method that involved supervised learning based on observed propositional semantics would not be developmentally plausible, as children do not get to observe symbolic meaning directly, and so crucially, the abstract relations are never made overt to our learner. Rather, the locations are probabilistically assigned to abstract landmark-relation pairs

show abstract

Section: Inferring Intended Referentsmentioning

confidence: 99%

A generative probabilistic framework for learning spatial language

Dawson

Wright

Rebguns

et al. 2013

2013 IEEE Third Joint International Conference on Development and Learning and Epigenetic Robotics (ICDL)

View full text Add to dashboard Cite

show abstract

“…Despite a steady trickle of papers over the years (see Baldwin et al, 2009 for a review), there is no apparent consensus approach to the treatment of preposition semantics in NLP. Studies have examined preposition semantics within multiword expressions (Cook and Stevenson, 2006), in spatial relations (Hying, 2007), across languages (Saint-Dizier, 2006b), in nonnative writing (Chodorow et al, 2007), in semantic role labeling (Dahlmeier et al, 2009), in vector space models (Zwarts and Winter, 2000), and in discourse (Denand and Rolbert, 2004).…”

Section: Prepositions In Nlpmentioning

confidence: 99%

Proceedings of The 9th Linguistic Annotation Workshop

2015

View full text Add to dashboard Cite

“…As such, prepositions have received relatively less attention compared to nouns, verbs or adjectives from computational linguists [1,23]. Those who have looked into prepositions often share the opinion that the spatial prepositions "at", "in" and "on" are a fundamental set of prepositions in English and the primary characteristic of their applicability in natural language is the proximity of the object they locate to the reference, or landmark, used in the PP [4,15].…”

Section: Related Workmentioning

confidence: 99%

Spatial interpretations of preposition "at"

Vasardani

Winter

Richter

et al. 2012

Proceedings of the 1st ACM SIGSPATIAL International Workshop on Crowdsourced and Volunteered Geographic Information

View full text Add to dashboard Cite

The current keyword-and substring matches-based retrieval methods most search engines rely on to answer spatial queries ignore the more specific interpretations of spatial relations. Moreover, the use of the general preposition "at" in natural language queries results in underspecified locations. This paper examines the use of "at" in a set of crowdsourced place descriptions and develops a methodology for interpreting "at" as one of the more location-specific, closely related spatial prepositions "in", "on", or "by". The application of suggested schemas in the paper enables the interpretation of "at" according to the granularity level and classification type of the spatial feature it refers to. The crowdsourced results show that most people use "at" to locate themselves either in relation to buildings, or to (naturally or artificially) bounded outdoor areas (at street level). When used with building level reference features, "at" is more likely to be interpreted as "in" the feature (mostly indoors) and less so "by" it. For reference features at street level, "at" is more likely to be interpreted as "in" the reference feature's region (within a bounded outdoor area) and less so "on" it (e.g., a water surface). The results indicate it is possible to use the proposed methodology for enabling search engines to better rank the results returned to natural language spatial queries by appropriately interpreting "at". The paper's research outcomes are an example of the use of crowdsourced information for improving the interaction between users and services.

show abstract

Prepositions in Applications: A Survey and Introduction to the Special Issue

Cited by 29 publications

References 88 publications

A generative probabilistic framework for learning spatial language

A generative probabilistic framework for learning spatial language

Proceedings of The 9th Linguistic Annotation Workshop

Spatial interpretations of preposition "at"

Contact Info

Product

Resources

About