Program

Tuesday, November 23

09:00 - 09:30 Registration

09:30 - 09:40 Opening

09:40 - 10:55

  • Rajarshi Biswas, Michael Barz, Mareike Hartmann, and Daniel Sonntag. Improving German Image Captions Using Machine Translation and Transfer Learning
  • Stéphane d’Ascoli, Alice Coucke, Francesco Caltagirone, Alexandre Caulier, and Marc Lelarge. Conditioned Text Generation with Transfer for Closed-domain Dialogue Systems
  • Bilal Ghanem, Simone Paolo Ponzetto, and Paolo Rosso. FacTweet: Profiling Fake News Twitter Accounts

10:55 - 11:15 Break

11:15 - 12:30

  • Svanhvít L. Ingólfsdóttir, Ásmundur A. Guðjónsson, and Hrafn Loftsson. Named Entity Recognition for Icelandic: Annotated Corpus and Models
  • Anastasiia Klimashevskaia, Richa Gadgil, Thomas Gerrity, Foaad Khosmood, Christian Gütl, and Patrick Howe. Automatic News Article Generation from Legislative Proceedings: A Phenom-based Approach
  • Jan Lehecka, Jan Švec, Pavel Ircing, and Luboš Šmídl. BERT-Based Sentiment Analysis Using Distillation

12:30 - 14:00 Lunch

14:00 - 14:50

  • Vigneshwaran Muralidaran, Irena Spasic, and Dawn Knight. A Cognitive Approach to Parsing with Neural Networks
  • Emma O’Neill, Robert Young, Elsa Thiaville, Muireann MacCarthy, Julie Carson-Berndsen, and Anthony Ventresque. S-Capade: Spelling Correction Aimed at Particularly Deviant Errors

14:50 - 15:10 Break

15:10 - 16:00 John H.L. Hansen. Challenges and Advancements in Speaker Diarization & Recognition for Naturalistic Data Streams - Invited lecture

16:00 - 16:20 Break

16:20 - 16:50 Poster session I


Wednesday, November 24

09:30 - 10:45

  • Matúš Pikuliak and Marián Šimko. Exploring Parameter Sharing Techniques for Cross-lingual and Cross-task Supervision
  • Lukáš Radoský and Miroslav Blšták. Constructing Sentiment Lexicon with Game for Annotation Collection
  • Marta Vicente and Elena Lloret. A Discourse-informed Approach for Cost-effective Extractive Summarization

10:45 - 11:05 Break

11:05 - 12:20

  • Rinalds Viksna and Inguna Skadina. Robustness of Named Entity Recognition: Case of Latvian
  • Andreas Waldis, Luca Mazzola, and Alexander Denzler. Towards eXplainable AI in Text Features Engineering
  • Jan Lehecka and Jan Švec. Comparison of Czech Transformers on Text Classification Tasks

12:20 - 13:50 Lunch

13:50 - 14:40

  • Juan M. Coria, Hervé Bredin, Sahar Ghannay, and Sophie Rosset. A Comparison of Metric Learning Loss Functions for End-To-End Speaker Verification
  • Ghania Droua-Hamdani. *ANN-MLP Classifier of Native and Nonnative Speakers Using Speech Rhythm Cues

Thursday, November 25

09:30 - 10:45

  • Ajinkya Kulkarni, Vincent Colotte, and Denis Jouvet. Deep Variational Metric Learning for Transfer of Expressivity in Multispeaker Text to Speech
  • Jose Antonio Lopez Saenz and Thomas Hain. Use of Speaker Metadata for Improving Automatic Pronunciation Assessment
  • Yasufumi Moriya and Gareth Jones. Augmenting ASR for User-generated Videos with Semi-supervised Training and Acoustic Model Adaptation for Spoken Content Retrieval

10:45 - 11:05 Break

11:05 - 12:20

  • Josef V. Psutka, Jan Vanek, and Aleš Pražák. Various DNN-HMM Architectures Used in Acoustic Modeling with Single-speaker and Single-channel
  • Aviad Shtrosberg, Jesus Villalba, Najim Dehak, Azaria Cohen, and Bar Ben-Yair. Invariant Representation Learning for Robust Far-field Speaker Recognition
  • Nam H. Trinh and Darragh O’Brien. Generative Adversarial Network-based Semi-supervised Learning for Pathological Speech Classification

12:20 - 13:50 Lunch

13:50 - 14:40 Mark A. Hasegawa-Johnson. Automatic Discovery of Phoneme Inventories for Speech Technology in Under-resourced Languages - Invited lecture

14:40 - 15:00 Break

15:00 - 15:30 Poster session II

15:30 - 15:40 Closing