scispace - formally typeset
Open accessJournal ArticleDOI: 10.1088/1757-899X/263/4/042042

Search optimization of named entities from twitter streams

01 Nov 2017-Vol. 263, Iss: 4, pp 042042
Abstract: With Enormous number of tweets, People often face difficulty to get exact information about those tweets. One of the approach followed for getting information about those tweets via Google. There is not any accuracy tool developed for search optimization and as well as getting information about those tweets. So, this system contains the search optimization and functionalities for getting information about those tweets. Another problem faced here are the tweets that contains grammatical errors, misspellings, non-standard abbreviations, and meaningless capitalization. So, these problems can be eliminated by the use of this tool. Lot of time can be saved and as well as by the use of efficient search optimization each information about those particular tweets can be obtained. more


Proceedings ArticleDOI: 10.3115/1599081.1599137
18 Aug 2008-
Abstract: Electronic written texts used in computermediated interactions (e-mails, blogs, chats, etc) present major deviations from the norm of the language This paper presents an comparative study of systems aiming at normalizing the orthography of French SMS messages: after discussing the linguistic peculiarities of these messages, and possible approaches to their automatic normalization, we present, evaluate and contrast two systems, one drawing inspiration from the Machine Translation task; the other using techniques that are commonly used in automatic speech recognition devices Combining both approaches, our best normalization system achieves about 11% Word Error Rate on a test set of about 3000 unseen messages more

Topics: Machine translation (53%), Word error rate (52%), Orthography (50%)

166 Citations

Open accessProceedings Article
Giuseppe Rizzo1, Raphaël Troncy1Institutions (1)
01 Jan 2011-
Abstract: In this paper, we present NERD, an evaluation framework we have developed that records and analyzes ratings of Named Entity (NE) extraction and disambiguation tools working on English plain text articles performed by human beings. NERD enables the comparison of different popular Linked Data entity extractors which expose APIs such as AlchemyAPI, DBPedia Spotlight, Extractiv, OpenCalais and Zemanta. Given an article and a particular tool, a user can assess the precision of the named entities extracted, their typing and linked data URI provided for disambiguation and their subjective relevance for the text. All user interactions are stored in a database. We propose the NERD ontology that defines mappings between the types detected by the different NE extractors. The NERD framework enables then to visualize the comparative performance of these tools with respect to human assessment. more

Topics: Named-entity recognition (52%), Linked data (51%)

43 Citations

Network Information
Related Papers (5)
01 Jan 2018

Huyen Trang Phan, Dinh Tuyen Hoang +2 more

10 Jul 2012

Xiaohua Liu, Furu Wei +1 more