Results 101 to 110 of about 46,318 (263)
An analysis of word embedding spaces and regularities [PDF]
Word embeddings are widely use in several applications due to their ability to capture semantic relationships between words as relations between vectors in high dimensional spaces.
Gijón Agudo, Manuel
core +1 more source
WordNet and wikipedia connection in Turkish WordNet KeNet
This paper aims to present WordNet and Wikipedia connection by linking synsets from Turkish WordNet KeNet with Wikipedia and thus, provide a better machine-readable dictionary to create an NLP model with rich data. For this purpose, manual mapping between two resources is realized and 11,478 synsets are linked to Wikipedia.
Doğan, M.+5 more
openaire +1 more source
Human activity recognition: A review of deep learning‐based methods
Human Activity Recognition (HAR) covers methods for automatically identifying human activities from a stream of data. End‐users of HAR methods cover a range of sectors, including health, self‐care, amusement, safety and monitoring. In this survey, the authors provide a thorough overview of deep learning based and detailed analysis of work that was ...
Sanjay Jyoti Dutta+2 more
wiley +1 more source
Enrichment of OntoSenseNet: Adding a Sense-annotated Telugu lexicon
The paper describes the enrichment of OntoSenseNet - a verb-centric lexical resource for Indian Languages. This resource contains a newly developed Telugu-Telugu dictionary. It is important because native speakers can better annotate the senses when both
Parupalli, Sreekavitha, Singh, Navjyoti
core +1 more source
Fast intensive crowd counting model of Internet of Things based on multi‐scale attention mechanism
Abstract Object detection based on deep learning plays an important role in the application of the Internet of Things (IoT). Traditional methods consume a lot of computing resources and cannot be well deployed in the IoT environment. A lightweight object detection method based on attention mechanism is proposed and applied to crowd counting. In view of
Dong Liu, Zhiyong Wang, Xiangjia Meng
wiley +1 more source
A Word Sense-Oriented User Interface for Interactive Multilingual Text Retrieval [PDF]
In this paper we present an interface for supporting a user in an interactive cross-language search process using semantic classes. In order to enable users to access multilingual information, different problems have to be solved: disambiguating and ...
DeLuca, Ernesto William+1 more
core
NGHIÊN CỨU VỀ UPPER ONTOLOGY TRỰC TUYẾN
Chúng tôi trình bày cách tiếp cận mới về ánh xạ giữa WordNet và SUMO (Suggested Upper Merged Ontology) cũng như công cụ trình duyệt SUMO trực tuyến có thể sử dụng để duyệt SUMO, và sự kết nối của nó với từ vựng WordNet.
Huỳnh Nhứt Phát+2 more
doaj
Synonymie et granularité dans les bases lexicales du type WordNet
In this paper we present a contribution to the transformation of PolNet, a Polish wordnet developed at the Adam Mickiewicz University in Pozna, into a Lexicon Grammar of Polish.
Zygmunt Vetulani, Grażyna Vetulani
doaj +1 more source
A study of query expansion methods for patent retrieval [PDF]
Patent retrieval is a recall-oriented search task where the objective is to find all possible relevant documents. Queries in patent retrieval are typically very long since they take the form of a patent claim or even a full patent application in the ...
Jones, Gareth J.F., Magdy, Walid
core
Ús de la Viquipèdia per al desenvolupament de recursos lingüístics: el WordNet 3.0 català i castellà
En aquest article presentem l'estat de la qüestió en l'ús de la Viquipèdia per a tasques relacionades amb el processament del llenguatge natural i tres aplicacions que hem creat per a l'enriquiment d'un recurs lingüí ...
Antoni Oliver, Salvador Climent
doaj +1 more source