no code implementations • ACL 2021 • Vojt{\v{e}}ch Hude{\v{c}}ek, Ond{\v{r}}ej Du{\v{s}}ek, Zhou Yu
Our model demonstrates state-of-the-art performance in slot tagging without labeled training data on four different dialogue domains.
no code implementations • ACL 2020 • Xinnuo Xu, Ond{\v{r}}ej Du{\v{s}}ek, Jingyi Li, Verena Rieser, Ioannis Konstas
Abstractive summarisation is notoriously hard to evaluate since standard word-overlap-based metrics are insufficient.
no code implementations • WS 2020 • Jind{\v{r}}ich Libovick{\'y}, Zden{\v{e}}k Kasner, Jind{\v{r}}ich Helcl, Ond{\v{r}}ej Du{\v{s}}ek
While the use of additional data and our classifier filter were able to improve results, the paraphrasing model produced too many invalid outputs to further improve the output quality.
no code implementations • WS 2019 • Ond{\v{r}}ej Du{\v{s}}ek, Filip Jur{\v{c}}{\'\i}{\v{c}}ek
We present the first dataset targeted at end-to-end NLG in Czech in the restaurant domain, along with several strong baseline models using the sequence-to-sequence approach.
Ranked #2 on Data-to-Text Generation on Czech Restaurant NLG
1 code implementation • EMNLP 2018 • Xinnuo Xu, Ond{\v{r}}ej Du{\v{s}}ek, Ioannis Konstas, Verena Rieser
We present three enhancements to existing encoder-decoder models for open-domain conversational agents, aimed at effectively modeling coherence and promoting output diversity: (1) We introduce a measure of coherence as the GloVe embedding similarity between the dialogue context and the generated response, (2) we filter our training corpora based on the measure of coherence to obtain topically coherent and lexically diverse context-response pairs, (3) we then train a response generator using a conditional variational autoencoder model that incorporates the measure of coherence as a latent variable and uses a context gate to guarantee topical consistency with the context and promote lexical diversity.
no code implementations • WS 2016 • Roman Sudarikov, Ond{\v{r}}ej Du{\v{s}}ek, Martin Holub, Ond{\v{r}}ej Bojar, Vincent Kr{\'\i}{\v{z}}
We describe experiments in Machine Translation using word sense disambiguation (WSD) information.
no code implementations • LREC 2014 • Mat{\v{e}}j Korvas, Ond{\v{r}}ej Pl{\'a}tek, Ond{\v{r}}ej Du{\v{s}}ek, Luk{\'a}{\v{s}} {\v{Z}}ilka, Filip Jur{\v{c}}{\'\i}{\v{c}}ek
We present a dataset of telephone conversations in English and Czech, developed for training acoustic models for automatic speech recognition (ASR) in spoken dialogue systems (SDSs).
Automatic Speech Recognition Automatic Speech Recognition (ASR) +3
no code implementations • LREC 2014 • Zde{\v{n}}ka Ure{\v{s}}ov{\'a}, Jan Haji{\v{c}}, Pavel Pecina, Ond{\v{r}}ej Du{\v{s}}ek
This paper presents development and test sets for machine translation of search queries in cross-lingual information retrieval in the medical domain.
no code implementations • LREC 2012 • Ond{\v{r}}ej Bojar, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}, Ond{\v{r}}ej Du{\v{s}}ek, Petra Galu{\v{s}}{\v{c}}{\'a}kov{\'a}, Martin Majli{\v{s}}, David Mare{\v{c}}ek, Ji{\v{r}}{\'\i} Mar{\v{s}}{\'\i}k, Michal Nov{\'a}k, Martin Popel, Ale{\v{s}} Tamchyna
CzEng 1. 0 is automatically aligned at the level of sentences as well as words.