Filters








120,845 Hits in 5.7 sec

Learning Semantic Maps from Natural Language Descriptions

Matt Walter, Sachithra Hemachandra, Bianca Homberg, Stefanie Tellex, Seth Teller
2013 Robotics: Science and Systems IX  
This paper proposes an algorithm that enables robots to efficiently learn human-centric models of their environment from natural language descriptions.  ...  This semantic graph provides a common framework in which we integrate concepts from natural language descriptions (e.g., labels and spatial relations) with metric observations from low-level sensors.  ...  CONCLUSION We described a semantic mapping algorithm enabling robots to efficiently learn metrically accurate semantic maps from natural language descriptions.  ... 
doi:10.15607/rss.2013.ix.004 dblp:conf/rss/WalterHHTT13 fatcat:zcaa34ydgbhh3h7vpl3ubmcmnm

A framework for learning semantic maps from grounded natural language descriptions

Matthew R. Walter, Sachithra Hemachandra, Bianca Homberg, Stefanie Tellex, Seth Teller
2014 The international journal of robotics research  
This paper describes a framework that enables robots to efficiently learn human-centric models of their environment from natural language descriptions.  ...  We evaluate the algorithm's ability to learn human-centric maps of several different environments and analyze the knowledge inferred from language and the utility of the learned maps.  ...  Semantic Accuracy Discussion Learning from Allocentric, Anticipatory Language A contribution of our work is the use of natural language descriptions to produce consistent semantic maps from spatial  ... 
doi:10.1177/0278364914537359 fatcat:2g5u2mda4nctjjtwrjdtiyicke

DeepAM: Migrate APIs with Multi-modal Sequence to Sequence Learning [article]

Xiaodong Gu, Hongyu Zhang, Dongmei Zhang, Sunghun Kim
2017 arXiv   pre-print
The key component of DeepAM is based on the multimodal sequence to sequence learning architecture that aims to learn joint semantic representations of bilingual API sequences from big source code data.  ...  Existing approaches mine API mappings from projects that have corresponding versions in two languages.  ...  natural language description.  ... 
arXiv:1704.07734v1 fatcat:4d5y4lnhwjbq5pzi477r6ngk5i

DeepAM: Migrate APIs with Multi-modal Sequence to Sequence Learning

Xiaodong Gu, Hongyu Zhang, Dongmei Zhang, Sunghun Kim
2017 Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence  
The key component of DeepAM is based on the multi-modal sequence to sequence learning architecture that aims to learn joint semantic representations of bilingual API sequences from big source code data  ...  Existing approaches mine API mappings from projects that have corresponding versions in two languages.  ...  translate from the semantic representations V to corresponding natural language descriptions D.  ... 
doi:10.24963/ijcai.2017/514 dblp:conf/ijcai/GuZZ017 fatcat:awd6oa4atnaoziu3ezz6nwrodu

E-Learning resource reuse, based on bilingual ontology annotation and ontology mapping

Tatyana Ivanova
2019 International Journal of Advanced Computer Research  
standards, etc.), used for semantic description of e-Learning courses.  ...  natural language [16] .  ... 
doi:10.19101/ijacr.2019.940101 fatcat:nzumk4kc4bfzhdhoq2wgjeixdu

Rich Semantics Improve Few-shot Learning [article]

Mohamed Afham, Salman Khan, Muhammad Haris Khan, Muzammal Naseer, Fahad Shahbaz Khan
2021 arXiv   pre-print
Human learning benefits from multi-modal inputs that often appear as rich semantics (e.g., description of an object's attributes while learning about it).  ...  This enables us to learn generalizable concepts from very limited visual examples.  ...  [1] use the language descriptions during the pertaining stage in FSL to learn natural task structure.  ... 
arXiv:2104.12709v2 fatcat:ttqiek7zgbfsbjulzqpgzatrze

Hybrid Attention Network for Language-Based Person Search

Yang Li, Huahu Xu, Junsheng Xiao
2020 Sensors  
Language-based person search retrieves images of a target person using natural language description and is a challenging fine-grained cross-modal retrieval task.  ...  It can better learn the bidirectional semantic dependency and capture the key words of sentences, so as to extract the context information and key semantic features of the language description more effectively  ...  Context Information Extraction Using BiLSTM The descriptions of persons from different witnesses are in the form of natural language.  ... 
doi:10.3390/s20185279 pmid:32942720 pmcid:PMC7570628 fatcat:hrqu7lz4frg4vdvoicory4vm6e

Language is Power: Representing States Using Natural Language in Reinforcement Learning [article]

Erez Schwartz, Guy Tennenholtz, Chen Tessler, Shie Mannor
2020 arXiv   pre-print
natural language representations for reinforcement learning.  ...  ., raw visual input), we propose to represent the state using natural language. Language can represent complex scenarios and concepts, making it a favorable candidate for representation.  ...  ViZDoom's semantic segmentation maps were used as the core element for generating our natural language descriptions.  ... 
arXiv:1910.02789v2 fatcat:nsoh4gxudzczrcyeblalirtqui

PDDL Planning with Natural Language-Based Scene Understanding for UAV-UGV Cooperation

Jiyoun Moon, Beom-Hee Lee
2019 Applied Sciences  
Further, recent developments in deep learning methods show outstanding performance for semantic scene understanding using natural language.  ...  We employ neural networks for natural-language-based scene understanding to share environmental information among robots.  ...  On language description part, a GCN extracts features from the graph map. The extracted graph feature is concatenated with a word and feed into the RNN as input.  ... 
doi:10.3390/app9183789 fatcat:lsfmciw4rvaxvlpwmznuodrqte

Robots That Use Language

Stefanie Tellex, Nakul Gopalan, Hadas Kress-Gazit, Cynthia Matuszek
2020 Annual Review of Control Robotics and Autonomous Systems  
This article surveys the use of natural language in robotics from a robotics point of view.  ...  This problem differs from other natural language processing domains due to the need to ground the language to noisy percepts and physical actions.  ...  (158) incorporates information from language into a semantic map of the environment.  ... 
doi:10.1146/annurev-control-101119-071628 fatcat:gljaeee7pvhb3ohuur3agdvvyq

Learning to interpret spatial natural language in terms of qualitative spatial relations* [chapter]

Parisa Kordjamshidi, Joana Hois, Marie-Francine Moens
2013 Representing Space in Cognition  
In this chapter, we apply formal models and machine learning techniques to map spatial semantics in natural language to qualitative spatial representations.  ...  , and (ii) we map the extracted parts that result from the first task to qualitative spatial representations.  ...  4 Machine Learning: From Spatial Language to RCC In this section, we present the machine learning task for mapping linguistic spatial features extracted from natural language to spatial calculi (see again  ... 
doi:10.1093/acprof:oso/9780199679911.003.0007 fatcat:37yp4icujjgm3eypqywb2qruei

Learning Deep Semantic Model for Code Search using CodeSearchNet Corpus [article]

Chen Wu, Ming Yan
2022 arXiv   pre-print
Different from typical information retrieval tasks, code search requires to bridge the semantic gap between the programming language and natural language, for better describing intrinsic concepts and semantics  ...  Semantic code search is the task of retrieving relevant code snippet given a natural language query.  ...  In our work, code token vectors are learnt independently for each language, and we learn a linear map W lang for each language and use it to project the code token vectors to a same semantic space, as  ... 
arXiv:2201.11313v1 fatcat:er5p53ejsbenjaywdppdrhtcyu

Zero-shot Learning of Classifiers from Natural Language Quantification

Shashank Srivastava, Igor Labutov, Tom Mitchell
2018 Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
Humans can efficiently learn new concepts using language.  ...  We use semantic parsing to map explanations to probabilistic assertions grounded in latent class labels and observed attributes of unlabeled data, and leverage the differential semantics of linguistic  ...  First, we map the set of natural language explanations of a concept to logical forms Figure 2: Our approach to Zero-shot learning from Language.  ... 
doi:10.18653/v1/p18-1029 dblp:conf/acl/MitchellSL18 fatcat:fuhmnmaqzbghnjdat3w4ofz3jm

An Open Vocabulary Semantic Parser for End-User Programming Using Natural Language

Juliano Efson Sales, Andr� Freitas, Siegfried Handschuh
2018 2018 IEEE 12th International Conference on Semantic Computing (ICSC)  
In this paper, we propose a semantic parsing approach to map natural language commands to actions from a large and heterogeneous frame set trained under a small set of annotated data.  ...  The ability to automatically interpret natural language commands and actions has the potential of freeing up endusers to interact with software artefacts without the syntactic, vocabulary and formal constraints  ...  MAPPING NATURAL LANGUAGE COMMANDS TO ACTION FRAMES The semantic parsing of natural language commands consists of mapping a natural language command to a formal function representation from a knowledge  ... 
doi:10.1109/icsc.2018.00020 dblp:conf/semco/SalesFH18 fatcat:tf3eo5qfkvc3hp5y6tmg5gzmpe

Imitation learning for natural language direction following through unknown environments

Felix Duvallet, Thomas Kollar, Anthony Stentz
2013 2013 IEEE International Conference on Robotics and Automation  
However, natural language direction following through unknown environments requires understanding the meaning of language, using a partial semantic world model to generate actions in the world, and reasoning  ...  We address the problem of robots following natural language directions through complex unknown environments.  ...  We have appreciated valuable discussions with Stéphane Ross and Drew Bagnell, as well as the comments from the anonymous reviewers.  ... 
doi:10.1109/icra.2013.6630702 dblp:conf/icra/DuvalletKS13 fatcat:b7olkax2tnd6jbdanc4lbx6dpq
« Previous Showing results 1 — 15 out of 120,845 results