81 |
Emergence of attention in a neural model of visually grounded speech
|
|
|
|
In: Learning Language in Humans and in Machines 2018 conference ; https://hal.archives-ouvertes.fr/hal-01970514 ; Learning Language in Humans and in Machines 2018 conference, Jul 2018, Paris, France (2018)
|
|
BASE
|
|
Show details
|
|
84 |
Linguistic unit discovery from multi-modal inputs in unwritten languages: Summary of the "Speaking Rosetta" JSALT 2017 Workshop ...
|
|
|
|
BASE
|
|
Show details
|
|
85 |
Unsupervised Word Segmentation from Speech with Attention ...
|
|
|
|
BASE
|
|
Show details
|
|
86 |
Unwritten Languages Demand Attention Too! Word Discovery with Encoder-Decoder Models
|
|
|
|
In: IEEE Automatic Speech Recognition and Understanding (ASRU) ; https://hal.archives-ouvertes.fr/hal-01592091 ; IEEE Automatic Speech Recognition and Understanding (ASRU), Dec 2017, Okinawa, Japan (2017)
|
|
BASE
|
|
Show details
|
|
87 |
Unsupervised Word Discovery Using Attentional Encoder-Decoder Models
|
|
|
|
In: WiNLP workshop, ACL 2017 ; https://hal.archives-ouvertes.fr/hal-02895851 ; WiNLP workshop, ACL 2017, Jul 2017, Vancouver, Canada (2017)
|
|
BASE
|
|
Show details
|
|
88 |
The Zero Resource Speech Challenge 2017
|
|
|
|
In: ASRU 2017 ; https://hal.inria.fr/hal-01687504 ; ASRU 2017, Dec 2017, Okinawa, Japan (2017)
|
|
BASE
|
|
Show details
|
|
91 |
Machine Assisted Analysis of Vowel Length Contrasts in Wolof ...
|
|
|
|
BASE
|
|
Show details
|
|
92 |
Unwritten Languages Demand Attention Too! Word Discovery with Encoder-Decoder Models ...
|
|
|
|
BASE
|
|
Show details
|
|
93 |
SPEECH-COCO: 600k Visually Grounded Spoken Captions Aligned to MSCOCO Data Set ...
|
|
|
|
BASE
|
|
Show details
|
|
95 |
LIG-AIKUMA: a Mobile App to Collect Parallel Speech for Under-Resourced Language Studies
|
|
|
|
In: Interspeech 2016 proceedings ; Interspeech 2016 (short demo paper) ; https://hal.archives-ouvertes.fr/hal-01350062 ; Interspeech 2016 (short demo paper), Sep 2016, San-Francisco, France (2016)
|
|
BASE
|
|
Show details
|
|
96 |
Word2Vec vs DBnary: Augmenting METEOR using Vector Representations or Lexical Resources?
|
|
|
|
In: 26th International Conference on Computational Linguistics (COLING 2016) ; COLING 2016 ; https://hal.archives-ouvertes.fr/hal-01376948 ; COLING 2016, ANLP & ICCL, Dec 2016, Osaka, Japan (2016)
|
|
BASE
|
|
Show details
|
|
97 |
Projection Interlingue d'Étiquettes pour l'Annotation Sémantique Non Supervisée
|
|
|
|
In: Actes de la conférence conjointe JEP-TALN-RECITAL ; TALN 2016 ; https://hal.archives-ouvertes.fr/hal-01350117 ; TALN 2016, Jul 2016, Paris, France (2016)
|
|
BASE
|
|
Show details
|
|
98 |
Inducing Multilingual Text Analysis Tools Using Bidirectional Recurrent Neural Networks
|
|
|
|
In: COLING 2016 ; https://hal.archives-ouvertes.fr/hal-01374205 ; COLING 2016, ANLP, Dec 2016, Osaka, Japan ; http://coling2016.anlp.jp (2016)
|
|
BASE
|
|
Show details
|
|
99 |
The CAMOMILE Collaborative Annotation Platform for Multi-modal, Multi-lingual and Multi-media Documents
|
|
Poignant, Johann; Budnik, Mateusz; Bredin, Hervé; Barras, Claude; Stefas, Mickael; Bruneau, Pierrick; Adda, Gilles; Besacier, Laurent; Ekenel, Hazim; Francopoulo, Gil; Hernando, Javier; Mariani, Joseph; Morros, Ramon; Quénot, Georges; Rosset, Sophie; Tamisier, Thomas
|
|
In: Proceedings of LREC 2016 ; LREC 2016 Conference ; https://hal.archives-ouvertes.fr/hal-01350096 ; LREC 2016 Conference, May 2016, Portoroz, Slovenia (2016)
|
|
Abstract:
International audience ; In this paper, we describe the organization and the implementation of the CAMOMILE collaborative annotation framework for multimodal, multimedia, multilingual (3M) data. Given the versatile nature of the analysis which can be performed on 3M data, the structure of the server was kept intentionally simple in order to preserve its genericity, relying on standard Web technologies. Layers of annotations, defined as data associated to a media fragment from the corpus, are stored in a database and can be managed through standard interfaces with authentication. Interfaces tailored specifically to the needed task can then be developed in an agile way, relying on simple but reliable services for the management of the centralized annotations. We then present our implementation of an active learning scenario for person annotation in video, relying on the CAMOMILE server; during a dry run experiment, the manual annotation of 716 speech segments was thus propagated to 3504 labeled tracks. The code of the CAMOMILE framework is distributed in open source.
|
|
Keyword:
[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; active learning; Annotation tool; collaborative annotation; multimedia; person annotation
|
|
URL: https://hal.archives-ouvertes.fr/hal-01350096/document https://hal.archives-ouvertes.fr/hal-01350096 https://hal.archives-ouvertes.fr/hal-01350096/file/456_Paper.pdf
|
|
BASE
|
|
Hide details
|
|
100 |
MultiVec: a Multilingual and Multilevel Representation Learning Toolkit for NLP
|
|
|
|
In: The 10th edition of the Language Resources and Evaluation Conference (LREC) ; https://hal.archives-ouvertes.fr/hal-01335930 ; The 10th edition of the Language Resources and Evaluation Conference (LREC), May 2016, Portoroz, Slovenia ; http://lrec2016.lrec-conf.org/en/ (2016)
|
|
BASE
|
|
Show details
|
|
|
|