Home
Catalogue search
Refine your search:
Keyword
Creator / Publisher:
Besacier, L. (4)
Boito, M.Z. (4)
Villavicencio, A. (4)
Berard, A. (1)
Bérard, A. (1)
Godard, P. (1)
Kačič, Z. (1)
Kubin, G. (1)
Ondel, L. (1)
Yvon, F. (1)
Year:
2020 (1)
2019 (1)
2018 (2)
Medium:
Online (4)
Type
BLLDB-Access
Search in the Catalogues and Directories
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
Sort by
creator [A → Z]
'
creator [Z → A]
'
publishing year ↑ (asc)
'
publishing year ↓ (desc)
'
title [A → Z]
'
title [Z → A]
'
Simple Search
Hits 1 – 4 of 4
1
Investigating language impact in bilingual approaches for computational language documentation
Boito, M.Z.
;
Villavicencio, A.
;
Besacier, L.
. - : Special Interest Group: Under-resourced Languages (SIGUL), 2020
BASE
Show details
2
Empirical evaluation of sequence-to-sequence models for word discovery in low-resource settings
Boito, M.Z.
;
Villavicencio, A.
;
Besacier, L.
. - : International Speech Communication Association (ISCA), 2019
Abstract:
Since Bahdanau et al. [1] first introduced attention for neural machine translation, most sequence-to-sequence models made use of attention mechanisms [2, 3, 4]. While they produce soft-alignment matrices that could be interpreted as alignment between target and source languages, we lack metrics to quantify their quality, being unclear which approach produces the best alignments. This paper presents an empirical evaluation of 3 of the main sequence-to-sequence models for word discovery from unsegmented phoneme sequences: CNN, RNN and Transformer-based. This task consists in aligning word sequences in a source language with phoneme sequences in a target language, inferring from it word segmentation on the target side [5]. Evaluating word segmentation quality can be seen as an extrinsic evaluation of the soft-alignment matrices produced during training. Our experiments in a low-resource scenario on Mboshi and English languages (both aligned to French) show that RNNs surprisingly outperform CNNs and Transformer for this task. Our results are confirmed by an intrinsic evaluation of alignment quality through the use Average Normalized Entropy (ANE). Lastly, we improve our best word discovery model by using an alignment entropy confidence measure that accumulates ANE over all the occurrences of a given alignment pair in the collection.
URL:
http://eprints.whiterose.ac.uk/155716/
https://www.isca-speech.org/archive/Interspeech_2019/abstracts/2029.html
http://eprints.whiterose.ac.uk/155716/8/Boito%20et%20al%202019%20Empirical%20Evaluation%20of%20Sequence-to-Sequence%20Models%20for%20Word%20Discovery,%20ISCA.pdf
BASE
Hide details
3
Unsupervised word segmentation from speech with attention
Godard, P.
;
Boito, M.Z.
;
Ondel, L.
. - : ISCA, 2018
BASE
Show details
4
Unwritten languages demand attention too! Word discovery with encoder-decoder models
Boito, M.Z.
;
Bérard, A.
;
Villavicencio, A.
. - : IEEE, 2018
BASE
Show details
Mobile view
All
Catalogues
UB Frankfurt Linguistik
0
IDS Mannheim
0
OLC Linguistik
0
UB Frankfurt Retrokatalog
0
DNB Subject Category Language
0
Institut für Empirische Sprachwissenschaft
0
Leibniz-Centre General Linguistics (ZAS)
0
Bibliographies
BLLDB
0
BDSL
0
IDS Bibliografie zur deutschen Grammatik
0
IDS Bibliografie zur Gesprächsforschung
0
IDS Konnektoren im Deutschen
0
IDS Präpositionen im Deutschen
0
IDS OBELEX meta
0
MPI-SHH Linguistics Collection
0
MPI for Psycholinguistics
0
Linked Open Data catalogues
Annohub
0
Online resources
Link directory
0
Journal directory
0
Database directory
0
Dictionary directory
0
Open access documents
BASE
4
Linguistik-Repository
0
IDS Publikationsserver
0
Online dissertations
0
Language Description Heritage
0
© 2013 - 2024 Lin|gu|is|tik
|
Imprint
|
Privacy Policy
|
Datenschutzeinstellungen ändern