Search Results - "Dušek, Ondřej"

Evaluating the state-of-the-art of End-to-End Natural Language Generation: The E2E NLG challenge by Dušek, Ondřej, Novikova, Jekaterina, Rieser, Verena

“…•Evaluation of 21 NLG systems of a wide variety of architectures: seq2seq and other data-driven, template- or rule-based.•Detailed evaluation with novel…”
Get full text

AI Technologies for Machine Supervision and Help in a Rehabilitation Scenario by Baranyi, Gábor, Dos Santos Melício, Bruno Carlos, Gaál, Zsófia, Hajder, Levente, Simonyi, András, Sindely, Dániel, Skaf, Joul, Dušek, Ondřej, Nekvinda, Tomáš, Lőrincz, András

“…We consider, evaluate, and develop methods for home rehabilitation scenarios. We show the required modules for this scenario. Due to the large number of…”
Get full text

HamleDT: Harmonized multi-language dependency treebank by Zeman, Daniel, Dušek, Ondřej, Mareček, David, Popel, Martin, Ramasamy, Loganathan, Štěpánek, Jan, Žabokrtský, Zdeněk, Hajič, Jan

“…We present HamleDT—a HArmonized Multi-LanguagE Dependency Treebank. HamleDT is a compilation of existing dependency treebanks (or dependency conversions of…”
Get full text

Adaptation of machine translation for multilingual information retrieval in the medical domain by Pecina, Pavel, Dušek, Ondřej, Goeuriot, Lorraine, Hajič, Jan, Hlaváčová, Jaroslava, Jones, Gareth J.F, Kelly, Liadh, Leveling, Johannes, Mareček, David, Novák, Michal, Popel, Martin, Rosa, Rudolf, Tamchyna, Aleš, Urešová, Zdeňka

“…Abstract Objective We investigate machine translation (MT) of user search queries in the context of cross-lingual information retrieval (IR) in the medical…”
Get full text

Beyond Traditional Benchmarks: Analyzing Behaviors of Open LLMs on Data-to-Text Generation by Kasner, Zdeněk, Dušek, Ondřej

“…We analyze the behaviors of open large language models (LLMs) on the task of data-to-text (D2T) generation, i.e., generating coherent and relevant text from…”
Get full text

LEEETs-Dial: Linguistic Entrainment in End-to-End Task-oriented Dialogue systems by Kumar, Nalin, Dušek, Ondřej

“…Linguistic entrainment, or alignment, represents a phenomenon where linguistic patterns employed by conversational participants converge to one another. While…”
Get full text

Critic-Driven Decoding for Mitigating Hallucinations in Data-to-text Generation by Lango, Mateusz, Dušek, Ondřej

“…Hallucination of text ungrounded in the input is a well-known problem in neural data-to-text generation. Many methods have been proposed to mitigate it, but…”
Get full text

MooseNet: A Trainable Metric for Synthesized Speech with a PLDA Module by Plátek, Ondřej, Dušek, Ondřej

“…We present MooseNet, a trainable speech metric that predicts the listeners' Mean Opinion Score (MOS). We propose a novel approach where the Probabilistic…”
Get full text

Are LLMs All You Need for Task-Oriented Dialogue? by Hudeček, Vojtěch, Dušek, Ondřej

“…Instructions-tuned Large Language Models (LLMs) gained recently huge popularity thanks to their ability to interact with users through conversation. In this…”
Get full text

Learning Interpretable Latent Dialogue Actions With Less Supervision by Hudeček, Vojtěch, Dušek, Ondřej

“…We present a novel architecture for explainable modeling of task-oriented dialogues with discrete latent variables to represent dialogue actions. Our model is…”
Get full text

AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog by Nekvinda, Tomáš, Dušek, Ondřej

“…We introduce AARGH, an end-to-end task-oriented dialog system combining retrieval and generative approaches in a single model, aiming at improving dialog…”
Get full text

Neural Pipeline for Zero-Shot Data-to-Text Generation by Kasner, Zdeněk, Dušek, Ondřej

“…In data-to-text (D2T) generation, training on in-domain data leads to overfitting to the data representation and repeating training data noise. We examine how…”
Get full text

Shades of BLEU, Flavours of Success: The Case of MultiWOZ by Nekvinda, Tomáš, Dušek, Ondřej

“…The MultiWOZ dataset (Budzianowski et al.,2018) is frequently used for benchmarking context-to-response abilities of task-oriented dialogue systems. In this…”
Get full text

Are Large Language Models Actually Good at Text Style Transfer? by Mukherjee, Sourabrata, Ojha, Atul Kr, Dušek, Ondřej

“…We analyze the performance of large language models (LLMs) on Text Style Transfer (TST), specifically focusing on sentiment transfer and text detoxification…”
Get full text

Evaluating Semantic Accuracy of Data-to-Text Generation with Natural Language Inference by Dušek, Ondřej, Kasner, Zdeněk

“…A major challenge in evaluating data-to-text (D2T) generation is measuring the semantic accuracy of the generated text, i.e. checking if the output text…”
Get full text

Data-to-Text Generation with Iterative Text Editing by Kasner, Zdeněk, Dušek, Ondřej

“…We present a novel approach to data-to-text generation based on iterative text editing. Our approach maximizes the completeness and semantic accuracy of the…”
Get full text

Balancing the Style-Content Trade-Off in Sentiment Transfer Using Polarity-Aware Denoising by Mukherjee, Sourabrata, Kasner, Zdeněk, Dušek, Ondřej

“…Text sentiment transfer aims to flip the sentiment polarity of a sentence (positive to negative or vice versa) while preserving its sentiment-independent…”
Get full text

Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models by Kasner, Zdeněk, Konstas, Ioannis, Dušek, Ondřej

“…Pretrained language models (PLMs) for data-to-text (D2T) generation can use human-readable data labels such as column headings, keys, or relation names to…”
Get full text

SpeedySpeech: Efficient Neural Speech Synthesis by Vainer, Jan, Dušek, Ondřej

“…While recent neural sequence-to-sequence models have greatly improved the quality of speech synthesis, there has not been a system capable of fast training,…”
Get full text

One Model, Many Languages: Meta-learning for Multilingual Text-to-Speech by Nekvinda, Tomáš, Dušek, Ondřej

“…We introduce an approach to multilingual speech synthesis which uses the meta-learning concept of contextual parameter generation and produces natural-sounding…”
Get full text