9,558 Hits in 5.0 sec

Learning Semantically Rich Event Inference Rules Using Definition of Verbs [chapter]

Nasrin Mostafazadeh, James F. Allen
2015 Lecture Notes in Computer Science  
We learn semantically rich inference rules which can be actively chained together in order to provide deeper understanding of conceptual events.  ...  We present a novel attempt to automatically acquire conceptual knowledge about events in the form of inference rules by reading verb definitions.  ...  This work is funded by The Office of Naval Research under grant number N000141110417 and Nuance Foundation.  ... 
doi:10.1007/978-3-319-18111-0_30 fatcat:qowji37bbzgufif3e4pm5k56n4

A Broad-Coverage Deep Semantic Lexicon for Verbs [article]

James Allen, Hannah An, Ritwik Bose, Will de Beaumont, Choh Man Teng
2020 arXiv   pre-print
We have developed COLLIE-V, a deep lexical resource for verbs, with the coverage of WordNet and syntactic and semantic details that meet or exceed existing resources.  ...  multiple constraints from parsing dictionary definitions and examples.  ...  Acknowledgements This research has been supported by DARPA ARO contract W911NF-15-1-0542 and the Office of Naval Research N00014-19-1-2308.  ... 
arXiv:2007.02670v1 fatcat:6xuv7r3sznfnhecajk6n3wvoty

How could a child use verb syntax to learn verb semantics?

Steven Pinker
1994 Lingua  
This kind of inference depends on a good deal of prior learning of verbs' meanings in a particular language, and thus is most definitely not a case of 'bootstrapping' performed by a child to acquire the  ...  a learning mechanism that can construct and modify semantic representations over a set of uses of the verb, and a greater understanding of how children interpret events, actions, mental states, and other  ... 
doi:10.1016/0024-3841(94)90347-6 fatcat:l3iln2bs6vetrnvspaux5tayve

Unsupervised Learning of Narrative Event Chains

Nathanael Chambers, Daniel Jurafsky
2008 Annual Meeting of the Association for Computational Linguistics  
Hand-coded scripts were used in the 1970-80s as knowledge backbones that enabled inference and other NLP tasks requiring deep semantic knowledge.  ...  The first uses unsupervised distributional methods to learn narrative relations between events sharing coreferring arguments.  ...  Learning these prototypical schematic sequences of events is important for rich understanding of text.  ... 
dblp:conf/acl/ChambersJ08 fatcat:cj4gni3swvec7hsotqxucjdg3u

Semantic interpretation and knowledge extraction

Fernando Gomez, Carlos Segami
2007 Knowledge-Based Systems  
The knowledge acquisition component is grounded on a semantic interpreter of English based on an enhanced WordNet. An evaluation of the system performance is included.  ...  It is also indicated how the inferences necessary for the extraction of knowledge can be acquired by the system from sentences entered by users.  ...  The system acquires some inference rules because it already knows a lot in the form of a general noun ontology that has been reorganized for semantic interpretation and a rich set of predicates linked  ... 
doi:10.1016/j.knosys.2006.07.002 fatcat:26szna74nrg2hoh44ewwryowkm

"What Are You Trying to Do?" Semantic Typing of Event Processes [article]

Muhao Chen, Hongming Zhang, Haoyu Wang, Dan Roth
2020 arXiv   pre-print
This paper studies a new cognitively motivated semantic typing task, multi-axis event process typing, that, given an event process, attempts to infer free-form type labels describing (i) the type of action  ...  As our experiments indicate, P2GT supports identifying the intent of processes, as well as the fine semantic type of the affected object.  ...  Also, we would like thank Jennifer Sheffield and other members of the UPenn Cognitive Computation Group for giving suggestions that improved the manuscript.  ... 
arXiv:2010.06724v1 fatcat:lalkges7ejfktbf4h4wrs4ajqq

Semantic Modeling with SUMO [article]

Robert B. Allen
2021 arXiv   pre-print
We explore using the Suggested Upper Merged Ontology (SUMO) to develop a semantic simulation.  ...  We provide two proof-of-concept demonstrations modeling transitions in a simulated gasoline engine using a general-purpose programming language.  ...  [17] has proposed a "generative semantics" based on semantic primitives. All of these are part of the Event Structure of the verbs.  ... 
arXiv:2012.15835v3 fatcat:mffu5kilmvbddffnsziuexl5wi

Towards a self-extending parser

Jaime G. Carbonell
1979 Proceedings of the 17th annual meeting on Association for Computational Linguistics -  
The technique of projecting and integrating semantic constraints to learn word definitions is analyzed as Implemented in the POLITICS system.  ...  The problem of generalizing existing word meanings and understanding metaphorical uses of words Is addressed In terms of semantic constraint Integration.  ...  Learning From Script Expectations Learning word definitions In semantically-rich contexts Is perhaps one of the simpler tasks of incremental learning.  ... 
doi:10.3115/982163.982166 dblp:conf/acl/Garbonell79 fatcat:j5kdzbhhpvashoouici6avlbq4

A Revisit to the Incorporation of Context - Awareness in Affective Computing Systems

Aggeliki Vlachostergiou, Stefanos Kollia
2015 International and Interdisciplinary Conference on Modeling and Using Context  
In this paper, we revisit the definition of contexts in AC systems and propose a context incorporation framework based on semantic concept detection, extraction enrichment and representation in cognitive  ...  The research field of Human Computer Interaction (HCI) is moving towards more natural, sensitive and intelligent paradigms.  ...  Acknowledgements This research has been co-financed by the European Union (European Social Fund -EFS) and Greek national funds through the Operational Program "Education and Lifelong Learning" of the National  ... 
dblp:conf/context/VlachostergiouK15 fatcat:hqribplehbaypksiljf3oxokra

Event analysis for information extraction from business-based technical documents

Bell Manrique-Losada, Carlos Mario Zapata Jaramillo
2015 Proceedings of the The 3rd Workshop on EVENTS: Definition, Detection, Coreference, and Representation  
In order to infer such mentions, we analyze the subject-verbobject structure for semi-automatically extracting several lexical, syntactic, and semantic features for each event mention from the corpus.  ...  Extracting event mentions allows us to cast grouping together the mentions with same features and propose properties leading to the differences of the specific genre.  ...  Then, we use the types of verb in order to identify patterns. Such patterns will be the basis of rules for inferring and extracting organizational relationships from business-based information.  ... 
doi:10.3115/v1/w15-0808 dblp:conf/aclevents/LosadaJ15 fatcat:jw7yz6e37rf6xebsxnbsenvhvq

Learning Verb Inference Rules from Linguistically-Motivated Evidence

Hila Weisman, Jonathan Berant, Idan Szpektor, Ido Dagan
2012 Conference on Empirical Methods in Natural Language Processing  
Learning inference relations between verbs is at the heart of many semantic applications.  ...  However, most prior work on learning such rules focused on a rather narrow set of information sources: mainly distributional similarity, and to a lesser extent manually constructed verb co-occurrence patterns  ...  Inference rules specify a directional inference relation between two text fragments, and we follow the Textual Entailment modeling of inference , which refers to such rules as entailment rules.  ... 
dblp:conf/emnlp/WeismanBSD12 fatcat:bbgcd4lzwvgj7pxp2qbso66u44

Naming motion events in Spanish and English

Paula Cifuentes-Férez, Dedre Gentner
2006 Cognitive Linguistics  
We used the novel word mapping technique (Nagy and Gentner 1990) to test whether English and Spanish speakers would show effects of their differing semantic systems in inferring the meanings of novel motion  ...  The passages provided information about both the path and the manner of a novel motion event.  ...  They investigated the role of semantic and linguistic knowledge in the way adult speakers of English infer the meanings of novel nouns and verbs from a rich context.  ... 
doi:10.1515/cog.2006.014 fatcat:wqx4wmfjrraafnxvt6nore2bme

Building a Knowledge Graph from Natural Language Definitions for Interpretable Text Entailment Recognition [article]

Vivian S. Silva, André Freitas, Siegfried Handschuh
2018 arXiv   pre-print
Natural language definitions of terms can serve as a rich source of knowledge, but structuring them into a comprehensible semantic model is essential to enable them to be used in semantic interpretation  ...  WordNetGraph, a knowledge graph built out of noun and verb WordNet definitions according to this methodology, was successfully used in an interpretable text entailment recognition approach which uses paths  ...  in order to use a supervised machine learning model to classify the data, we needed a initial set of annotated definitions.  ... 
arXiv:1806.07731v1 fatcat:5526pcnozfh7dk5omik5d4lhvm

CaTeRS: Causal and Temporal Relation Scheme for Semantic Annotation of Event Structures

Nasrin Mostafazadeh, Alyson Grealish, Nathanael Chambers, James Allen, Lucy Vanderwende
2016 Proceedings of the Fourth Workshop on Events  
This is even more crucial for understanding stories and script learning. A prerequisite for learning scripts is a semantic framework which enables capturing rich event structures.  ...  Learning commonsense causal and temporal relation between events is one of the major steps towards deeper language understanding.  ...  This work was supported in part by Grant W911NF-15-1-0542 with the US Defense Advanced Research Projects Agency (DARPA), the Army Research Office (ARO) and Office of Naval Research (ONR).  ... 
doi:10.18653/v1/w16-1007 dblp:conf/aclevents/MostafazadehGCA16 fatcat:ggg3q4joo5d7hdyjwudhlwlffm

Automatic Discovery of Manner Relations and its Applications

Eduardo Blanco, Dan I. Moldovan
2010 Conference on Empirical Methods in Natural Language Processing  
Combinations of MANNER with other semantic relations are also discussed.  ...  An extended definition of MANNER is proposed, including restrictions on the sorts of concepts that can be part of its domain and range.  ...  The mapping also uses an automatically built list of verbs and nouns that encode events (verb events and noun events).  ... 
dblp:conf/emnlp/BlancoM10 fatcat:3typus7fzre4zfsboi3qepeqiy
« Previous Showing results 1 — 15 out of 9,558 results