Filters








80 Hits in 2.4 sec

A Hierarchy with, of, and for Preposition Supersenses

Nathan Schneider, Vivek Srikumar, Jena D. Hwang, Martha Palmer
2015 Proceedings of The 9th Linguistic Annotation Workshop  
To facilitate automatic disambiguation, we propose a general-purpose, broadcoverage taxonomy of preposition functions that we call supersenses: these are coarse and unlexicalized so as to be tractable  ...  Our resource, including extensive documentation of the supersenses, many example sentences, and mappings to other lexical resources, will be publicly released. 2 Supersense inventories have also been described  ...  Acknowledgments Improved coarse semantic categories for prepositions are the result of ongoing collaborations; they reflect the efforts of ourselves and others including Tim O'Gorman, Katie Conger, Meredith  ... 
doi:10.3115/v1/w15-1612 dblp:conf/acllaw/SchneiderSHP15 fatcat:hsfux3mruveblogkiklajrmvqa

A corpus of preposition supersenses in English web reviews [article]

Nathan Schneider, Jena D. Hwang, Vivek Srikumar, Meredith Green, Kathryn Conger, Tim O'Gorman, Martha Palmer
2016 arXiv   pre-print
We present the first corpus annotated with preposition supersenses, unlexicalized categories for semantic functions that can be marked by English prepositions (Schneider et al., 2015).  ...  Moreover, unlike the previous schemes, the preposition supersenses are organized hierarchically. Our data will be publicly released on the web upon publication.  ...  and Susan Brown for helpful discussions.  ... 
arXiv:1605.02257v1 fatcat:jff3wqbu5zdcfoe2jhzy5pdia4

A Corpus of Preposition Supersenses

Nathan Schneider, Jena D. Hwang, Vivek Srikumar, Meredith Green, Abhijit Suresh, Kathryn Conger, Tim O'Gorman, Martha Palmer
2016 Proceedings of the 10th Linguistic Annotation Workshop held in conjunction with ACL 2016 (LAW-X 2016)  
We present the first corpus annotated with preposition supersenses, unlexicalized categories for semantic functions that can be marked by English prepositions .  ...  The preposition supersenses are organized hierarchically and designed to facilitate comprehensive manual annotation. Our dataset is publicly released on the web. 1  ...  and Susan Brown for helpful discussions.  ... 
doi:10.18653/v1/w16-1712 dblp:conf/acllaw/SchneiderHSGSCO16 fatcat:6l6azltkpfebjfvxmbd2s64gui

Comprehensive Supersense Disambiguation of English Prepositions and Possessives

Nathan Schneider, Jena D. Hwang, Vivek Srikumar, Jakob Prange, Austin Blodgett, Sarah R. Moeller, Aviram Stern, Adi Bitan, Omri Abend
2018 Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
We introduce a new annotation scheme, corpus, and task for the disambiguation of prepositions and possessives in English.  ...  ; unite prepositions and possessives under the same class inventory; and distinguish between a marker's lexical contribution and the role it marks in the context of a predicate or scene.  ...  support; and anonymous reviewers for useful feedback.  ... 
doi:10.18653/v1/p18-1018 dblp:conf/acl/AbendSSHPBMSB18 fatcat:nqy5xw6le5ckbe2bgx7cu7bjaa

Comprehensive Supersense Disambiguation of English Prepositions and Possessives [article]

Nathan Schneider, Jena D. Hwang, Vivek Srikumar, Jakob Prange, Austin Blodgett, Sarah R. Moeller, Aviram Stern, Adi Bitan, Omri Abend
2018 arXiv   pre-print
We introduce a new annotation scheme, corpus, and task for the disambiguation of prepositions and possessives in English.  ...  ; unite prepositions and possessives under the same class inventory; and distinguish between a marker's lexical contribution and the role it marks in the context of a predicate or scene.  ...  support; and anonymous reviewers for useful feedback.  ... 
arXiv:1805.04905v1 fatcat:yrdehe3x7nc55eytibgftxkoqi

Double Trouble: The Problem of Construal in Semantic Annotation of Adpositions

Jena D. Hwang, Archna Bhatia, Na-Rae Han, Tim O'Gorman, Vivek Srikumar, Nathan Schneider
2017 Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017)  
We consider the semantics of prepositions, revisiting a broad-coverage annotation scheme used for annotating all 4,250 preposition tokens in a 55,000 word corpus of English.  ...  discuss how this representation would allow for a simpler inventory of labels.  ...  Ellsworth for an insightful perspective on construal, Paul Portner for a helpful clarification regarding approaches to conceptualization in the literature, and anonymous reviewers for their thoughtful  ... 
doi:10.18653/v1/s17-1022 dblp:conf/starsem/HwangBHOSS17 fatcat:iovwoki32rhxbggmyywnutal6y

Coping with Construals in Broad-Coverage Semantic Annotation of Adpositions [article]

Jena D. Hwang, Archna Bhatia, Na-Rae Han, Tim O'Gorman, Vivek Srikumar, Nathan Schneider
2017 arXiv   pre-print
We consider the semantics of prepositions, revisiting a broad-coverage annotation scheme used for annotating all 4,250 preposition tokens in a 55,000 word corpus of English.  ...  We suggest a framework to represent both the scene role and the adposition's lexical function so they can be annotated at scale---supporting automatic, statistical processing of domain-general language  ...  Acknowledgments We thank the rest of our CARMLS team-Martha Palmer, Ken Litkowski, Katie Conger, and Meredith Green-for participating in weekly discussions of adposition semantics; Michael Ellsworth for  ... 
arXiv:1703.03771v1 fatcat:bwkwsdmlrjht7g7lhu5zqmkpg4

Supersense tagging of unknown nouns using semantic similarity

James R. Curran
2005 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics - ACL '05  
The limited coverage of lexical-semantic resources is a significant problem for NLP systems which can be alleviated by automatically classifying the unknown words.  ...  Ciaramita and Johnson (2003) present a tagger which uses synonym set glosses as annotated training examples.  ...  Acknowledgements We would like to thank Massi Ciaramita for supplying his original data for these experiments and answering our queries, and to Stephen Clark and the anonymous reviewers for their helpful  ... 
doi:10.3115/1219840.1219844 dblp:conf/acl/Curran05 fatcat:on23dwal5ngtzdekyhptzjiiae

A Corpus of Adpositional Supersenses for Mandarin Chinese [article]

Siyao Peng, Yang Liu, Yilun Zhu, Austin Blodgett, Yushi Zhao, Nathan Schneider
2020 arXiv   pre-print
Our approach adapts a framework that defined a general set of supersenses according to ostensibly language-independent semantic criteria, though its development focused primarily on English prepositions  ...  Moreover, there is a dearth of annotated corpora for investigating the cross-linguistic variation of adposition semantics, or for building multilingual disambiguation systems.  ...  Acknowledgements We thank anonymous reviewers for their feedback.  ... 
arXiv:2003.08437v1 fatcat:ou364g2z2rbyfonxgb6kf4g3r4

Adpositional Supersenses for Mandarin Chinese [article]

Yilun Zhu, Yang Liu, Siyao Peng, Austin Blodgett, Yushi Zhao, Nathan Schneider
2018 arXiv   pre-print
This study adapts Semantic Network of Adposition and Case Supersenses (SNACS) annotation to Mandarin Chinese and demonstrates that the same supersense categories are appropriate for Chinese adposition  ...  We annotated 15 chapters of The Little Prince, with high interannotator agreement.  ...  Acknowledgments We would like to thank Nathan's Excellent Research Team (NERT), Case and Adposition Representation for Multi-Lingual Semantics (CARMLS) group, and two anonymous reviewers for valuable comments  ... 
arXiv:1812.02317v1 fatcat:rwkaoud2w5dhbea5iy54t2iskq

Knowledge Graph Construction and Its Application in Automatic Radiology Report Generation from Radiologist's Dictation [article]

Kaveri Kale, Pushpak Bhattacharyya, Aditya Shetty, Milind Gune, Kush Shrivastava, Rustom Lawyer, Spriha Biswas
2022 arXiv   pre-print
Furthermore, we include a manual qualitative analysis from radiologists, which shows that 80-85% of the generated reports are correctly written, and the remaining are partially correct.  ...  This paper focuses on KG construction for each organ by extracting information from an existing large corpus of free-text radiology reports.  ...  Also, we plan to combine all KGs of different organs in a single KG in the future. That would be a single knowledge base for all organs.  ... 
arXiv:2206.06308v2 fatcat:a5ifhm277rh25a2wdwa3a2arly

Adposition and Case Supersenses v2.6: Guidelines for English [article]

Nathan Schneider, Jena D. Hwang, Vivek Srikumar, Archna Bhatia, Na-Rae Han, Tim O'Gorman, Sarah R. Moeller, Omri Abend, Adi Shalev, Austin Blodgett, Jakob Prange
2022 arXiv   pre-print
This document offers a detailed linguistic description of SNACS (Semantic Network of Adposition and Case Supersenses; Schneider et al., 2018), an inventory of 52 semantic labels ("supersenses") that characterize  ...  Version 2 is a revision of the supersense inventory proposed for English by Schneider et al. (2015, 2016) (henceforth "v1"), which in turn was based on previous schemes.  ...  Inventory The v2.6 hierarchy is a tree with 52 supersense labels.  ... 
arXiv:1704.02134v8 fatcat:tqyi2vm3o5dxfhcnypmf2443za

Digraph analysis of dictionary preposition definitions

Kenneth C. Litkowski
2002 Proceedings of the ACL-02 workshop on Word sense disambiguation recent successes and future directions -  
We characterize these primitives and show how they can be used to develop an inheritance hierarchy for prepositions, representing the definitions by a type and slots for its arguments.  ...  We develop a model of preposition definitions in a machine-readable dictionary using the theory of labeled directed graphs and analyze the resulting digraphs to determine a primitive set of preposition  ...  The large number of senses that have verb hypernymic roots indicates a close kinship between prepositions and verbs, suggesting that a verb hierarchy may provide an organizing principle for prepositions  ... 
doi:10.3115/1118675.1118677 dblp:conf/semeval/Litkowski02 fatcat:g7yyhcirufelflceu7dlwc7dxi

Modelling the Polysemy of Spatial Prepositions in Referring Expressions

Adam Richard-Bollans, Lucía Gómez Álvarez, Anthony G. Cohn
2020 Proceedings of the Seventeenth International Conference on Principles of Knowledge Representation and Reasoning  
In order to compare polysemes and aid typicality judgements we then introduce a notion of 'polyseme hierarchy'.  ...  In previous work exploring how to automatically generate typicality measures for spatial prepositions in grounded settings, we considered a semantic model based on Prototype Theory and introduced a method  ...  The partial support of the EU under the Horizon 2020 research and innovation programme grant agreement 825619 is also gratefully acknowledged.  ... 
doi:10.24963/kr.2020/72 dblp:conf/kr/Richard-Bollans20 fatcat:mqowyzblrngh5gayyjprsihpiy

Semi Supervised Preposition-Sense Disambiguation using Multilingual Data [article]

Hila Gonen, Yoav Goldberg
2016 arXiv   pre-print
Our approach pre-trains an LSTM encoder for predicting the translation of a preposition, and then incorporates the pre-trained encoder as a component in a supervised classification system, and fine-tunes  ...  Prepositions are very common and very ambiguous, and understanding their sense is critical for understanding the meaning of the sentence.  ...  Each preposition has a different set of possible senses, with a range of 2 to 25 possible senses for a given preposition. We use the original split to train and test sets.  ... 
arXiv:1611.08813v1 fatcat:wkjpkoyfbvfrtjhlkitn33xwge
« Previous Showing results 1 — 15 out of 80 results