Next-Generation Natural Language Generation

Información del proyecto

NG-NLG

Identificador del acuerdo de subvención: 101039303

DOI

10.3030/101039303

Fecha de la firma de la CE 31 Marzo 2022

Fecha de inicio 1 Abril 2022

Fecha de finalización 31 Marzo 2027

Financiado con arreglo a

• European Research Council (ERC)

Coste total

€ 1 420 375,00

Aportación de la UE

€ 1 420 375,00

Coordinado por

UNIVERZITA KARLOVA
Czechia

CORDIS proporciona enlaces a los documentos públicos y las publicaciones de los proyectos de los programas marco HORIZONTE.

Los enlaces a los documentos y las publicaciones de los proyectos del Séptimo Programa Marco, así como los enlaces a algunos tipos de resultados específicos, como conjuntos de datos y «software», se obtienen dinámicamente de OpenAIRE .

Publicaciones

Conference proceedings (34)

With a Little Help from the Authors: Reproducing Human Evaluation of an MT Error Detector

Autores: Ondřej Plátek, Mateusz Lango, Ondřej Dušek
Publicado en: Workshop on Human Evaluation of NLP Systems, Edición 3, 2023, ISBN 978-954-452-088-5
Editor: INCOMA Ltd.
DOI: 10.48550/ARXIV.2308.06527

Two Reproductions of a Human-Assessed Comparative Evaluation of a Semantic Error Detection System

Autores: Huidrom, Rudali; Dušek, Ondřej; Kasner, Zdenek; Castro Ferreira, Thiago; Belz, Anya
Publicado en: International Conference on Natural Language Generation: Generation Challenges, Edición 15, 2022, ISBN 978-1-955917-60-5
Editor: Association for Computational Linguistics
DOI: 10.5281/ZENODO.11373776

Tackling Hallucinations in Neural Chart Summarization

Autores: Saad Obaid ul Islam, Iza Škrjanec, Ondřej Dušek, Vera Demberg
Publicado en: International Natural Language Generation Conference, Edición 16, 2023, ISBN 979-8-89176-001-1
Editor: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2308.00399

AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog

Autores: Tomáš Nekvinda, Ondřej Dušek
Publicado en: Annual Meeting of the Special Interest Group on Discourse and Dialogue, Edición 23, 2022, ISBN 978-1-955917-66-7
Editor: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2209.03632

Polite Chatbot: A Text Style Transfer Application

Autores: Sourabrata Mukherjee, Vojtěch Hudeček, Ondřej Dušek
Publicado en: Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop, Edición 17, 2023, ISBN 978-1-959429-48-7
Editor: Association for Computational Linguistics
DOI: 10.5281/ZENODO.11373712

Frontiers in Artificial Intelligence and Applications

Autores: Jakub Raczyński, Mateusz Lango, Jerzy Stefanowski
Publicado en: European Conference on Artificial Intelligence, Edición 26, 2023, ISSN 0922-6389
Editor: IOS Press
DOI: 10.48550/ARXIV.2312.11356

Multilingual Text Style Transfer: Datasets Models for Indian Languages

Autores: Sourabrata Mukherjee, Atul Kr. Ojha, Akanksha Bansal, Deepak Alok, John P. McCrae, Ondřej Dušek
Publicado en: International Natural Language Generation Conference, Edición 17, 2024
Editor: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2405.20805

Critic-Driven Decoding for Mitigating Hallucinations in Data-to-text Generation

Autores: Mateusz Lango, Ondřej Dušek
Publicado en: Conference on Empirical Methods in Natural Language Processing, 2023, ISBN 979-8-89176-060-8
Editor: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2310.16964

Semantic Accuracy in Natural Language Generation: A Thesis Proposal

Autores: Patrícia Schmidtová
Publicado en: Annual Meeting of the Association for Computational Linguistics, Edición 61, vol. 4, 2023, ISBN 978-1-959429-69-2
Editor: Association for Computational Linguistics
DOI: 10.5281/ZENODO.11373677

MooseNet: A Trainable Metric for Synthesized Speech with a PLDA Module

Autores: Ondřej Plátek; Ondrej Dusek
Publicado en: ISCA Speech Synthesis Workshop, Edición 12, 2023
Editor: ISCA
DOI: 10.48550/arxiv.2301.07087

Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation

Autores: Zdeněk Kasner, Ondřej Dušek
Publicado en: Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Edición 62, 2024
Editor: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2401.10186

Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs

Autores: Simone Balloccu, Patrícia Schmidtová, Mateusz Lango, and Ondrej Dusek
Publicado en: Conference of the European Chapter of the Association for Computational Linguistics, Edición 18, 2024, ISBN 979-8-89176-088-2
Editor: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2402.03927

Are LLMs All You Need for Task-Oriented Dialogue?

Autores: Vojtěch Hudeček, Ondřej Dušek
Publicado en: Annual Meeting of the Special Interest Group on Discourse and Dialogue, Edición 24, 2023, ISBN 979-8-89176-028-8
Editor: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2304.06556

Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models

Autores: Zdeněk Kasner, Ioannis Konstas, Ondřej Dušek
Publicado en: Conference of the European Chapter of the Association for Computational Linguistics, Edición 17, 2023, ISBN 978-1-959429-44-9
Editor: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2210.07373

Are Experts Needed? On Human Evaluation of Counselling Reflection Generation

Autores: Zixiu Wu, Simone Balloccu, Ehud Reiter, Rim Helaoui, Diego Reforgiato Recupero, Daniele Riboni
Publicado en: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023, ISBN 978-1-959429-72-2
Editor: Association for Computational Linguistics
DOI: 10.18653/V1/2023.ACL-LONG.382

Learning Interpretable Latent Dialogue Actions With Less Supervision

Autores: Vojtěch Hudeček, Ondřej Dušek
Publicado en: Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing, Edición 2, 2022, ISBN 978-1-955917-65-0
Editor: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2209.11128

WebLINX: Real-World Website Navigation with Multi-Turn Dialogue

Autores: Xing Han Lu, Zdeněk Kasner, Siva Reddy
Publicado en: International Conference on Machine Learning, Edición 41, 2024
Editor: PMLR
DOI: 10.48550/ARXIV.2402.05930

LEEETs-Dial: Linguistic Entrainment in End-to-End Task-oriented Dialogue systems

Autores: Nalin Kumar, Ondrej Dusek
Publicado en: Findings of the Association for Computational Linguistics: NAACL 2024, 2024
Editor: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2311.09390

Low-Resource Text Style Transfer for Bangla: Data & Models

Autores: Sourabrata Mukherjee, Akanksha Bansal, Pritha Majumdar, Atul Kr. Ojha, Ondřej Dušek
Publicado en: Workshop on Bangla Language Processing, Edición 1, 2023, ISBN 979-8-89176-058-5
Editor: Association for Computational Linguistics
DOI: 10.5281/ZENODO.11372105

"ReproHum #0043-4: Evaluating Summarization Models: Investigating the Impact of Education and Language Proficiency on Reproducibility"

Autores: Mateusz Lango, Patricia Schmidtová, Simone Balloccu, Ondřej Dušek
Publicado en: Workshop on Human Evaluation of NLP Systems, Edición 4, 2024, ISSN 2951-2093
Editor: ELRA and ICCL
DOI: 10.5281/ZENODO.11371369

Ask the experts: sourcing high-quality datasets for nutritional counselling through Human-AI collaboration

Autores: Balloccu, Simone; Reiter, Ehud; Kumar, Vivek; Recupero, Diego Reforgiato; Riboni, Daniele
Publicado en: Findings of the Association for Computational Linguistics: EMNLP 2024, 2024
Editor: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2401.08420

Leveraging Large Language Models for Building Interpretable Rule-Based Data-to-Text Systems

Autores: Jędrzej Warczyński, Mateusz Lango, Ondřej Dušek
Publicado en: International Natural Language Generation Conference, Edición 17, 2024
Editor: Association for Computational Linguistics
DOI: 10.5281/ZENODO.14236701

VisuaLLM: Easy Web-based Visualization for Neural Language Generation

Autores: František Trebuňa, Ondřej Dušek
Publicado en: International Natural Language Generation Conference: System Demonstrations, Edición 16, 2023, ISBN 979-8-89176-002-8
Editor: Association for Computational Linguistics
DOI: 10.5281/ZENODO.11372124

Generating clickbait spoilers with an ensemble of large language models

Autores: Mateusz Woźny, Mateusz Lango
Publicado en: International Natural Language Generation Conference, Edición 16, 2023, ISBN 979-8-89176-001-1
Editor: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2404.15758

Neural Pipeline for Zero-Shot Data-to-Text Generation

Autores: Zdeněk Kasner, Ondřej Dušek
Publicado en: Annual Meeting of the Association for Computational Linguistics, Edición 60, 2022, ISBN 978-1-955917-21-6
Editor: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2203.16279

Are Large Language Models Actually Good at Text Style Transfer?

Autores: Sourabrata Mukherjee, Atul Kr. Ojha, Ondřej Dušek
Publicado en: International Natural Language Generation Conference, Edición 17, 2024
Editor: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2406.05885

Balancing the Style-Content Trade-Off in Sentiment Transfer Using Polarity-Aware Denoising

Autores: Sourabrata Mukherjee, Zdeněk Kasner, Ondřej Dušek
Publicado en: Text, Speech, and Dialogue, 2022, ISBN 9783031162695
Editor: Springer International Publishing
DOI: 10.48550/ARXIV.2312.14708

Leveraging Low-resource Parallel Data for Text Style Transfer

Autores: Sourabrata Mukherjee, Ondřej Dušek
Publicado en: International Natural Language Generation Conference, Edición 16, 2023, ISBN 979-8-89176-001-1
Editor: Association for Computational Linguistics
DOI: 10.5281/ZENODO.11373566

Automatic Metrics in Natural Language Generation: A survey of Current Evaluation Practices

Autores: Patrícia Schmidtová, Saad Mahamood, Simone Balloccu, Ondřej Dušek, Albert Gatt, Dimitra Gkatzia, David M. Howcroft, Ondřej Plátek, Adarsa Sivaprasad
Publicado en: International Natural Language Generation Conference, Edición 17, 2024
Editor: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2408.09169

Three Ways of Using Large Language Models to Evaluate Chat

Autores: Ondřej Plátek, Vojtěch Hudeček, Patricia Schmidtová, Mateusz Lango, Ondřej Dušek
Publicado en: Dialog System Technology Challenge, Edición 11, 2023
Editor: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2308.06502

Faithful and Plausible Natural Language Explanations for Image Classification: A Pipeline Approach

Autores: Adam Wojciechowski, Mateusz Lango, Ondrej Dušek
Publicado en: Findings of the Association for Computational Linguistics: EMNLP 2024, 2024
Editor: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2407.20899

TabGenie: A Toolkit for Table-to-Text Generation

Autores: Zdeněk Kasner, Ekaterina Garanina, Ondřej Plátek, Ondřej Dušek
Publicado en: Annual Meeting of the Association for Computational Linguistics, Edición 61, 2023
Editor: 978-1-959429-70-8
DOI: 10.48550/ARXIV.2302.14169

Better Translation + Split and Generate for Multilingual RDF-to-Text (WebNLG 2023)

Autores: Nalin Kumar, Saad Obaid Ul Islam, Ondřej Dušek
Publicado en: Workshop on Multimodal, Multilingual Natural Language Generation and Multilingual WebNLG Challenge, 2023
Editor: Association for Computational Linguistics
DOI: 10.5281/ZENODO.11373606

factgenie: A Framework for Span-based Evaluation of Generated Texts

Autores: Zdeněk Kasner, Ondřej Plátek, Patrícia Schmidtová, Simone Balloccu, Ondřej Dušek
Publicado en: International Natural Language Generation Conference: System Demonstrations, Edición 17, 2024
Editor: Association for Computational Linguistics
DOI: 10.48550/ARXIV.2407.17863

Peer reviewed articles (1)

Barriers and enabling factors for error analysis in NLG research

Autores: Emiel Van Miltenburg; Miruna Clinciu; Ondřej Dušek; Dimitra Gkatzia; Stephanie Inglis; Leo Leppänen; Saad Mahamood; Stephanie Schoch; Craig Thomson; Luou Wen
Publicado en: Northern European Journal of Language Technology, 2023, ISSN 2000-1533
Editor: Northern European Association of Language Technology
DOI: 10.3384/nejlt.2000-1533.2023.4529