57,750 Hits in 3.8 sec

Spotting automatically cross-language relations

Federico Tomassetti, Giuseppe Rizzo, Marco Torchiano
2014 2014 Software Evolution Week - IEEE Conference on Software Maintenance, Reengineering, and Reverse Engineering (CSMR-WCRE)  
In this work we present a language agnostic approach to automatically detect cross-language relations to ease re-factoring, validation and to allow navigation support to the developer.  ...  We apply such a procedure to an AngularJS application and we show that this approach spots cross-language relations at fine grained level with 93.2% of recall and a F-measure of 92.2%. 1  ...  Inspired by this preliminary consideration, we have started over an exhaustive investigation on the context in the field of spotting automatically cross-language relations.  ... 
doi:10.1109/csmr-wcre.2014.6747189 dblp:conf/csmr/TomassettiRT14 fatcat:tyiazji5dfgedodcrkvkkczw2u

Automatic Detection, Indexing, and Retrieval of Multiple Attributes from Cross-Lingual Multimedia Data [chapter]

Qian Hu, Fred J. Goodman, Stanley M. Boykin, Randall K. Fish, Warren R. Greiff, Stephen R. Jones, Stephen R. Moore
2012 Multimedia Information Extraction  
language ID and automatically identified non-lexical audio cues.  ...  multi-media and cross-lingual data collection, and refine query results.  ...  In our Audio Hot Spotting prototype, we experimented with query expansion to achieve two purposes, 1) to improve the retrieval rate of related passages when exact word match fails, and 2) to allow cross  ... 
doi:10.1002/9781118219546.ch14 fatcat:iz2khooigrgszf5sbwvwqpj74i

Sign Language Video Retrieval with Free-Form Textual Queries [article]

Amanda Duarte, Samuel Albanie, Xavier Giró-i-Nieto, Gül Varol
2022 arXiv   pre-print
We propose to tackle this task by learning cross-modal embeddings on the recently introduced large-scale How2Sign dataset of American Sign Language (ASL).  ...  We, therefore, propose SPOT-ALIGN, a framework for interleaving iterative rounds of sign spotting and feature alignment to expand the scope and scale of available training data.  ...  Related Work Our work relates primarily to existing research in textvideo embeddings for video retrieval, sign language video retrieval and automatic annotation of sign language videos with auxiliary cues  ... 
arXiv:2201.02495v1 fatcat:sqapj2bkvvdetktmhcmsylgq2m

Automatic learning of phonetic mappings for cross-language phonetic-search in keyword spotting

Yossi Bar-Yosef, Ruth Aloni-Lavi, Irit Opher, Noam Lotner, Ella Tetariy, Vered Silber-Varod, Vered Aharonson, Ami Moyal
2012 2012 IEEE 27th Convention of Electrical and Electronics Engineers in Israel  
Our cross-language PS experiments showed that learning a good cross-language mapping can alleviate acoustic mismatches between languages, to significantly improve cross-language phonetic-search.  ...  Phonetic-search (PS) is an extremely fast technique used for spoken keyword spotting over large amounts of audio data.  ...  INTRODUCTION These days there is a growing demand for supporting new languages in Keyword Spotting (KWS) and other Automatic Speech Recognition (ASR) based applications.  ... 
doi:10.1109/eeei.2012.6376955 fatcat:ckitfcxto5hh5ps7sg4rp6dmli

Automatic Compilation of Travel Information from Texts: A Survey [chapter]

Hidetsugu Nanba, Aya Ishino, Toshiyuki Takezaw
2012 Theory and Applications for Advanced Text Mining  
Evaluation Workshop GeoCLEF: Geographic Information Retrieval GeoCLEF ( was the cross-language geographic retrieval track run as part of the Cross-Language Evaluation Forum  ...  NTCIR GeoTime NTCIR GeoTime was another cross-language geographic retrieval track run as part of the NTCIR. It operated from 2008 to 2011 [8, 9] .  ... 
doi:10.5772/51290 fatcat:cmfu5trrlveo3pepvclnv33feq

Visually grounded cross-lingual keyword spotting in speech [article]

Herman Kamper, Michael Roth
2018 arXiv   pre-print
We ask whether visual grounding can be used for cross-lingual keyword spotting: given a text keyword in one language, the task is to retrieve spoken utterances containing that keyword in another language  ...  This could enable searching through speech in a low-resource language using text queries in a high-resource language.  ...  In cross-lingual keyword spotting, utterances in one language should be retrieved in response to user text queries in a different language.  ... 
arXiv:1806.05030v1 fatcat:w4cx5ceswbbx3l42vmh5gvmtoa

The Intonation System of Tajik: Is it Identical to Persian?

Marina Agafonova
2018 The 6th Intl. Workshop on Spoken Language Technologies for Under-Resourced Languages  
We ask whether visual grounding can be used for cross-lingual keyword spotting: given a text keyword in one language, the task is to retrieve spoken utterances containing that keyword in another language  ...  This could enable searching through speech in a low-resource language using text queries in a high-resource language.  ...  In cross-lingual keyword spotting, utterances in one language should be retrieved in response to user text queries in a different language.  ... 
doi:10.21437/sltu.2018-53 dblp:conf/sltu/KamperR18 fatcat:tpy6o46sizb5xjjip5yg3ni42a

An automatic word-spotting framework for medieval manuscripts

Ruggero Pintus, Ying Yang, Enrico Gobbetti, Holly Rushmeier
2015 2015 Digital Heritage  
We present a completely automatic and scalable framework to perform query-by-example word-spotting on medieval manuscripts.  ...  languages, image resolutions, levels of conservation, noise and amount of illumination and ornamentation.  ...  CONCLUSIONS We have presented a completely automatic and scalable framework to perform word-spotting in medieval handwritten books, in a single or cross-manuscript setup.  ... 
doi:10.1109/digitalheritage.2015.7419446 dblp:conf/dh/PintusYGR15 fatcat:vd3scxm2rrhr3mp34iojg4pkhi


Federico Tomassetti, Giuseppe Rizzo, Raphael Troncy
2014 Proceedings of the 23rd International Conference on World Wide Web - WWW '14 Companion  
This paper describes a library for detecting cross-language relations in polyglot frameworks. The library has been developed to be modular and to be easily integrated in existing IDEs.  ...  These cross-language relations are normally not captured by tools which require the developer to learn and to remember those associations in order to understand and maintain the application.  ...  OUTLOOK In this paper, we present a prototype library for detecting automatically cross-language relations.  ... 
doi:10.1145/2567948.2578036 dblp:conf/www/TomassettiRT14 fatcat:b6n2cc7rnjhjldgcwwhyzgxtjy

Audio based soccer game summarization

Helenca Duxans, Xavier Anguera, David Conejero
2009 2009 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting  
-Without using any language dependent cue, the way the commentators speak is related to what is happening in the game.  ...  There are multiple industrial applications of soccer game analysis, such as automatic summarization services for TV broadcasters, Internet users or instantaneously notification of hot spot events to specific  ... 
doi:10.1109/isbmsb.2009.5133759 fatcat:drwisuwzpfgwhcfkdcydfkqm4u

Corpus-Based Contrastive Study of Verbal Tenses [chapter]

Cristina Grisot
2018 Yearbook of Corpus Linguistics and Pragmatics  
Automatic spotting results have errors, and the aim of researchers working in Natural Language Processing is to reduce the number of errors as much as possible.  ...  Translational relations can be identified using the translation spotting technique.  ... 
doi:10.1007/978-3-319-96752-3_3 fatcat:23w7yzc4b5hgnm3gpwfalr23em

Galene: Online Prediction Of Sea State And Risk Assessment For Small Boats As An Open Lightweight Web Saas

Petros Petrou, John Kontoulis, Harris Georgiou
2017 Zenodo  
The main input is the user's GPS position and the average wind measurement around that spot, as well as the local coast line and sea depth profile that the platform retrieves automatically from open sources  ...  On the other hand, if such wind data are available and current in real time for a specific spot, it would be extremely useful if the predictions could be updated accordingly on demand.  ...  Turkey-Greece crossings: 5-10 n.m. /  1.5m waves (max) Libya-Italy crossings: 200-300 n.m. /  4.5m waves (max)  Even with the same weather intensity, risk factor for small/medium boats becomes at  ... 
doi:10.5281/zenodo.1045421 fatcat:cuesiyi4zfcgxglchrbuciljjy

Automated Speech and Audio Analysis for Semantic Access to Multimedia [chapter]

Franciska de Jong, Roeland Ordelman, Marijn Huijbregts
2006 Lecture Notes in Computer Science  
The applicability of techniques will be discussed from a media crossing perspective.  ...  This paper overviews the various ways in which automatic speech and audio analysis can contribute to increased granularity of automatically extracted metadata.  ...  We introduce the concept of cross-media mining in section 4. Automatic audio indexing techniques are overviewed in section 5.  ... 
doi:10.1007/11930334_18 fatcat:gfextjrehbe27n4zz4utygzgny

Annotating the meaning of discourse connectives by looking at their translation: The translation-spotting technique

Bruno Cartoni, Sandrine Zufferey, Thomas Meyer
2013 Dialogue and Discourse  
This problem is all the more important since connectives are salient textual markers of cohesion and need to be correctly interpreted for many Natural Language Processing applications.  ...  This technique also opens new avenues for further cross-linguistic research on discourse relations and connectives.  ...  automatically.  ... 
doi:10.5087/dad.2013.204 fatcat:pzjcvbdptjht3poo2f7he7toai

Cross-language Semantic Matching for Discovering Links to e-gov Services in the LOD Cloud

Fedelucio Narducci, Matteo Palmonari, Giovanni Semeraro
2013 Extended Semantic Web Conference  
In this paper we present CroSeR (Cross-language Service Retriever), a tool able to match and retrieve cross-language e-gov services stored in the LOD cloud.  ...  We adopted a Wikipedia-based semantic representation in order to overcome the problems related to match really short textual descriptions associated to the services.  ...  The goal of that paper is to investigate how to automatically generate cross-language links between resources in large document collections.  ... 
dblp:conf/esws/NarducciPS13 fatcat:ml6prz7yyrggxgzmeihvbarxai
« Previous Showing results 1 — 15 out of 57,750 results