Discovering Dialogue Slots with Weak Supervision

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.

Response Generation Task-Oriented Dialogue Systems

Fact-based Content Weighting for Evaluating Abstractive Summarisation

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.

Expand and Filter: CUNI and LMU Systems for the WNGT 2020 Duolingo Shared Task

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.

Translation

Neural Generation for Czech: Data and Baselines

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.

Data-to-Text Generation Language Modelling

Better Conversations by Modeling, Filtering, and Optimizing for Coherence and Diversity

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.

Dialogue Generation

Verb sense disambiguation in Machine Translation

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.

Machine Translation Translation +1

Moses \& Treex Hybrid MT Systems Bestiary

no code implementations • WS 2016 • Rudolf Rosa, Martin Popel, Ond{\v{r}}ej Bojar, David Mare{\v{c}}ek, Ond{\v{r}}ej Du{\v{s}}ek

Language Modelling Machine Translation +1

A Context-aware Natural Language Generator for Dialogue Systems

1 code implementation • WS 2016 • Ond{\v{r}}ej Du{\v{s}}ek, Filip Jur{\v{c}}{\'\i}{\v{c}}ek

Spoken Dialogue Systems Text Generation

Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings

1 code implementation • ACL 2016 • Ond{\v{r}}ej Du{\v{s}}ek, Filip Jur{\v{c}}{\'\i}{\v{c}}ek

Spoken Dialogue Systems Text Generation

New Language Pairs in TectoMT

no code implementations • WS 2015 • Ond{\v{r}}ej Du{\v{s}}ek, Lu{\'\i}s Gomes, Michal Nov{\'a}k, Martin Popel, Rudolf Rosa

Machine Translation

Using Parallel Texts and Lexicons for Verbal Word Sense Disambiguation

no code implementations • WS 2015 • Ond{\v{r}}ej Du{\v{s}}ek, Eva Fu{\v{c}}{\'\i}kov{\'a}, Jan Haji{\v{c}}, Martin Popel, Jana {\v{S}}indlerov{\'a}, Zde{\v{n}}ka Ure{\v{s}}ov{\'a}

Machine Translation Word Sense Disambiguation

Training a Natural Language Generator From Unaligned Data

1 code implementation • IJCNLP 2015 • Ond{\v{r}}ej Du{\v{s}}ek, Filip Jur{\v{c}}{\'\i}{\v{c}}ek

Text Generation

Bilingual English-Czech Valency Lexicon Linked to a Parallel Corpus

no code implementations • WS 2015 • Zde{\v{n}}ka Ure{\v{s}}ov{\'a}, Ond{\v{r}}ej Du{\v{s}}ek, Eva Fu{\v{c}}{\'\i}kov{\'a}, Jan Haji{\v{c}}, Jana {\v{S}}indlerov{\'a}

Machine Translation Semantic Role Labeling

Translation Model Interpolation for Domain Adaptation in TectoMT

no code implementations • WS 2015 • Rudolf Rosa, Ond{\v{r}}ej Du{\v{s}}ek, Michal Nov{\'a}k, Martin Popel

Domain Adaptation Translation

Machine Translation of Medical Texts in the Khresmoi Project

no code implementations • WS 2014 • Ond{\v{r}}ej Du{\v{s}}ek, Jan Haji{\v{c}}, Jaroslava Hlav{\'a}{\v{c}}ov{\'a}, Michal Nov{\'a}k, Pavel Pecina, Rudolf Rosa, Ale{\v{s}} Tamchyna, Zde{\v{n}}ka Ure{\v{s}}ov{\'a}, Daniel Zeman

Domain Adaptation Image Retrieval +3

Alex: Bootstrapping a Spoken Dialogue System for a New Domain by Real Users

no code implementations • WS 2014 • Ond{\v{r}}ej Du{\v{s}}ek, Ond{\v{r}}ej Pl{\'a}tek, Luk{\'a}{\v{s}} {\v{Z}}ilka, Filip Jur{\v{c}}{\'\i}{\v{c}}ek

Dialogue Management Language Modelling +4

Verbal Valency Frame Detection and Selection in Czech and English

no code implementations • WS 2014 • Ond{\v{r}}ej Du{\v{s}}ek, Jan Haji{\v{c}}, Zde{\v{n}}ka Ure{\v{s}}ov{\'a}

Predicate Detection Word Sense Disambiguation

Free English and Czech telephone speech corpus shared under the CC-BY-SA 3.0 license

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

Multilingual Test Sets for Machine Translation of Search Queries for Cross-Lingual Information Retrieval in the Medical Domain

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.

Cross-Lingual Information Retrieval Domain Adaptation +4

Robust multilingual statistical morphological generation models

no code implementations • ACL 2013 • Ond{\v{r}}ej Du{\v{s}}ek, Filip Jur{\v{c}}{\'\i}{\v{c}}ek

Morphological Inflection Text Generation

Using Parallel Features in Parsing of Machine-Translated Sentences for Correction of Grammatical Errors

no code implementations • WS 2012 • Rudolf Rosa, Ond{\v{r}}ej Du{\v{s}}ek, David Mare{\v{c}}ek, Martin Popel

Machine Translation Morphological Inflection

Formemes in English-Czech Deep Syntactic MT

no code implementations • WS 2012 • Ond{\v{r}}ej Du{\v{s}}ek, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}, Martin Popel, Martin Majli{\v{s}}, Michal Nov{\'a}k, David Mare{\v{c}}ek

Machine Translation

DEPFIX: A System for Automatic Correction of Czech MT Outputs

no code implementations • WS 2012 • Rudolf Rosa, David Mare{\v{c}}ek, Ond{\v{r}}ej Du{\v{s}}ek

Machine Translation Word Alignment

The Joy of Parallelism with CzEng 1.0

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.

Machine Translation Sentence