Institut des Technologies Multilingues & Multimédias de l’Information
Institute for Multilingual & Multimedia Information
Institut für Multilinguale & Multimediale Informationsverarbeitung


Montag 1. September 2014

Alle Fassungen dieses Artikels: [Deutsch] [français] [français]

Day 1, Session 1: Modelisation of Errors by machine

(Chair: Yannick Estève)

PDF - 417.5 kB
Keynote: Julia Hirschberg

Identifying and Responding to Errors in Spoken Dialogue Systems


PDF - 620.3 kB
Maja Popovic

Automatic error analysis of machine translations


PDF - 176 kB
Martin Sundermeyer

Direct Observation of Pruning Errors - A Search Analysis Tool


PDF - 2.9 MB
Atsunori Ogawa

Recognition rate estimation based on error type classification and its applications



Day 1, Session 2: Complex errors, errors from multiple sources

(Chair: Chris Cieri)

PDF - 3.2 MB
Keynote: Josef Kittler

To fuse or not to fuse


PDF - 730.4 kB
Juliette Kahn

Evaluation is not just a score


PDF - 965.8 kB
Hervé Bredin

Visualizing multimodal person recognition errors: a REPERE use case of the Camomile project


PDF - 401 kB
Mirjam Ernestus

Errors induced by pronunciation variants typical of casual speech


Day 1, Session 3: Impact of errors

(Chair: Laurent Besacier)

PDF - 1013.5 kB
Keynote: Lucia Specia

Is this translation fit for purpose? Predicting quality versus predicting errors


PDF - 288 kB
Sophie Rosset

Human annotation of ASR error regions: Is ’gravity’ a sharable concept for human annotators?


PDF - 776.7 kB
Catherine Kobus

Machine translation error categorization by post-editions automatic analysis


PDF - 1.2 MB
Benoît Favre

Automatic Human Utility Evaluation of ASR Systems: Does WER Really Predict Performance?


Day 2, Session 4: Errors by machines and humans

(Chair: Ioana Vasilescu)

PDF - 1.6 MB
Keynote: Sarah Hawkins

Illusions, contexts and domains of analysis in assessing errors in speech processing


PDF - 433.3 kB
Michel Simard

Error Analysis of Error Corrections in Machine Translation


PDF - 570.6 kB
Martin Cooke

Noise-induced slips of the ear


PDF - 499.5 kB
Odette Scharenborg

Comparing human and automatic speech recognition


PDF - 822.8 kB
Bernd Meyer

What’s the difference? Quantifying errors in human and automatic speech recognition


Day 2, Session 5: Error Analysis

(Chair: Liz Shriberg)


PDF - 510.1 kB
Keynote: Mark Liberman

Machine learning from machine learning errors : Work in progress on parsing and phonetic alignment


PDF - 1.2 MB
Sebastian Stüker

The Influence of Topic and Domain Specific Words on WER - And Can We Get the User in to Correct Them?


PDF - 990.4 kB
Natalie Kübler & François Yvon

Human Errors and Automatic Errors in Machine Translations. What are the Differences?


PDF - 934.4 kB
Tim Schlippe

Error blaming based on Decoding Output


PDF - 985.5 kB
Martine Adda-Decker & Barbara Schuppler

What we can learn from ASR errors about low-resourced languages : a case-study of Luxembourgish and Austrian


JPEG - 21.7 kB
Ilya Oparin

Summary of the workshop

Skelett | | Sitemap |