Ondřej Dušek

Also published as: Ondrej Dusek


2023

pdf
TabGenie: A Toolkit for Table-to-Text Generation
Zdeněk Kasner | Ekaterina Garanina | Ondrej Platek | Ondrej Dusek
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)

Heterogenity of data-to-text generation datasets limits the research on data-to-text generation systems. We present TabGenie – a toolkit which enables researchers to explore, preprocess, and analyze a variety of data-to-text generation datasets through the unified framework of table-to-text generation. In TabGenie, all inputs are represented as tables with associated metadata. The tables can be explored through a web interface, which also provides an interactive mode for debugging table-to-text generation, facilitates side-by-side comparison of generated system outputs, and allows easy exports for manual analysis. Furthermore, TabGenie is equipped with command line processing tools and Python bindings for unified dataset loading and processing. We release TabGenie as a PyPI package and provide its open-source code and a live demo at https://github.com/kasnerz/tabgenie.

pdf
Mind the Labels: Describing Relations in Knowledge Graphs With Pretrained Models
Zdeněk Kasner | Ioannis Konstas | Ondrej Dusek
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics

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 generalize to out-of-domain examples. However, the models are well-known in producing semantically inaccurate outputs if these labels are ambiguous or incomplete, which is often the case in D2T datasets. In this paper, we expose this issue on the task of descibing a relation between two entities. For our experiments, we collect a novel dataset for verbalizing a diverse set of 1,522 unique relations from three large-scale knowledge graphs (Wikidata, DBPedia, YAGO). We find that although PLMs for D2T generation expectedly fail on unclear cases, models trained with a large variety of relation labels are surprisingly robust in verbalizing novel, unseen relations. We argue that using data with a diverse set of clear and meaningful labels is key to training D2T generation systems capable of generalizing to novel domains.

pdf
Polite Chatbot: A Text Style Transfer Application
Sourabrata Mukherjee | Vojtěch Hudeček | Ondřej Dušek
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop

Generating polite responses is essential to build intelligent and engaging dialogue systems. However, this task is far from well-explored due to the difficulties of rendering a particular style in coherent responses, especially when parallel datasets for regular-to-polite pairs are usually unavailable.This paper proposes a polite chatbot that can produce responses that are polite and coherent to the given context.In this study, a politeness transfer model is first used to generate polite synthetic dialogue pairs of contexts and polite utterances. Then, these synthetic pairs are employed to train a dialogue model. Automatic and human evaluations demonstrate that our method outperforms baselines in producing polite dialogue responses while staying competitive in terms of coherent to the given context.

2022

pdf
THEaiTRobot: An Interactive Tool for Generating Theatre Play Scripts
Rudolf Rosa | Patrícia Schmidtová | Alisa Zakhtarenko | Ondrej Dusek | Tomáš Musil | David Mareček | Saad Ul Islam | Marie Novakova | Klara Vosecka | Daniel Hrbek | David Kostak
Proceedings of the 15th International Conference on Natural Language Generation: System Demonstrations

We present a free online demo of THEaiTRobot, an open-source bilingual tool for interactively generating theatre play scripts, in two versions. THEaiTRobot 1.0 uses the GPT-2 language model with minimal adjustments. THEaiTRobot 2.0 uses two models created by fine-tuning GPT-2 on purposefully collected and processed datasets and several other components, generating play scripts in a hierarchical fashion (title synopsis script). The underlying tool is used in the THEaiTRE project to generate scripts for plays, which are then performed on stage by a professional theatre.

pdf
Two Reproductions of a Human-Assessed Comparative Evaluation of a Semantic Error Detection System
Rudali Huidrom | Ondřej Dušek | Zdeněk Kasner | Thiago Castro Ferreira | Anya Belz
Proceedings of the 15th International Conference on Natural Language Generation: Generation Challenges

In this paper, we present the results of two re- production studies for the human evaluation originally reported by Dušek and Kasner (2020) in which the authors comparatively evaluated outputs produced by a semantic error detection system for data-to-text generation against ref- erence outputs. In the first reproduction, the original evaluators repeat the evaluation, in a test of the repeatability of the original evalua- tion. In the second study, two new evaluators carry out the evaluation task, in a test of the reproducibility of the original evaluation under otherwise identical conditions. We describe our approach to reproduction, and present and analyse results, finding different degrees of re- producibility depending on result type, data and labelling task. Our resources are available and open-sourced.

pdf
A Unifying View On Task-oriented Dialogue Annotation
Vojtěch Hudeček | Leon-paul Schaub | Daniel Stancl | Patrick Paroubek | Ondřej Dušek
Proceedings of the Thirteenth Language Resources and Evaluation Conference

Every model is only as strong as the data that it is trained on. In this paper, we present a new dataset, obtained by merging four publicly available annotated corpora for task-oriented dialogues in several domains (MultiWOZ 2.2, CamRest676, DSTC2 and Schema-Guided Dialogue Dataset). This way, we assess the feasibility of providing a unified ontology and annotation schema covering several domains with a relatively limited effort. We analyze the characteristics of the resulting dataset along three main dimensions: language, information content and performance. We focus on aspects likely to be pertinent for improving dialogue success, e.g. dialogue consistency. Furthermore, to assess the usability of this new corpus, we thoroughly evaluate dialogue generation performance under various conditions with the help of two prominent recent end-to-end dialogue models: MarCo and GPT-2. These models were selected as popular open implementations representative of the two main dimensions of dialogue modelling. While we did not observe a significant gain for dialogue state tracking performance, we show that using more training data from different sources can improve language modelling capabilities and positively impact dialogue flow (consistency). In addition, we provide the community with one of the largest open dataset for machine learning experiments.

pdf
Neural Pipeline for Zero-Shot Data-to-Text Generation
Zdeněk Kasner | Ondrej Dusek
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

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 to avoid finetuning pretrained language models (PLMs) on D2T generation datasets while still taking advantage of surface realization capabilities of PLMs. Inspired by pipeline approaches, we propose to generate text by transforming single-item descriptions with a sequence of modules trained on general-domain text-based operations: ordering, aggregation, and paragraph compression. We train PLMs for performing these operations on a synthetic corpus WikiFluent which we build from English Wikipedia. Our experiments on two major triple-to-text datasets—WebNLG and E2E—show that our approach enables D2T generation from RDF triples in zero-shot settings.

pdf
Learning Interpretable Latent Dialogue Actions With Less Supervision
Vojtěch Hudeček | Ondřej Dušek
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

We present a novel architecture for explainable modeling of task-oriented dialogues with discrete latent variables to represent dialogue actions. Our model is based on variational recurrent neural networks (VRNN) and requires no explicit annotation of semantic information. Unlike previous works, our approach models the system and user turns separately and performs database query modeling, which makes the model applicable to task-oriented dialogues while producing easily interpretable action latent variables. We show that our model outperforms previous approaches with less supervision in terms of perplexity and BLEU on three datasets, and we propose a way to measure dialogue success without the need for expert annotation. Finally, we propose a novel way to explain semantics of the latent variables with respect to system actions.

pdf bib
Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue
Oliver Lemon | Dilek Hakkani-Tur | Junyi Jessy Li | Arash Ashrafzadeh | Daniel Hernández Garcia | Malihe Alikhani | David Vandyke | Ondřej Dušek
Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue

pdf
AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog
Tomáš Nekvinda | Ondřej Dušek
Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue

We introduce AARGH, an end-to-end task-oriented dialog system combining retrieval and generative approaches in a single model, aiming at improving dialog management and lexical diversity of outputs. The model features a new response selection method based on an action-aware training objective and a simplified single-encoder retrieval architecture which allow us to build an end-to-end retrieval-enhanced generation model where retrieval and generation share most of the parameters. On the MultiWOZ dataset, we show that our approach produces more diverse outputs while maintaining or improving state tracking and context-to-response generation performance, compared to state-of-the-art baselines.

pdf
GPT-2-based Human-in-the-loop Theatre Play Script Generation
Rudolf Rosa | Patrícia Schmidtová | Ondřej Dušek | Tomáš Musil | David Mareček | Saad Obaid | Marie Nováková | Klára Vosecká | Josef Doležal
Proceedings of the 4th Workshop of Narrative Understanding (WNU2022)

We experiment with adapting generative language models for the generation of long coherent narratives in the form of theatre plays. Since fully automatic generation of whole plays is not currently feasible, we created an interactive tool that allows a human user to steer the generation somewhat while minimizing intervention. We pursue two approaches to long-text generation: a flat generation with summarization of context, and a hierarchical text-to-text two-stage approach, where a synopsis is generated first and then used to condition generation of the final script. Our preliminary results and discussions with theatre professionals show improvements over vanilla language model generation, but also identify important limitations of our approach.

2021

pdf
MiRANews: Dataset and Benchmarks for Multi-Resource-Assisted News Summarization
Xinnuo Xu | Ondřej Dušek | Shashi Narayan | Verena Rieser | Ioannis Konstas
Findings of the Association for Computational Linguistics: EMNLP 2021

One of the most challenging aspects of current single-document news summarization is that the summary often contains ‘extrinsic hallucinations’, i.e., facts that are not present in the source document, which are often derived via world knowledge. This causes summarisation systems to act more like open-ended language models tending to hallucinate facts that are erroneous. In this paper, we mitigate this problem with the help of multiple supplementary resource documents assisting the task. We present a new dataset MiraNews and benchmark existing summarisation models. In contrast to multi-document summarization, which addresses multiple events from several source documents, we still aim at generating a summary for a single document. We show via data analysis that it’s not only the models which are to blame: more than 27% of facts mentioned in the gold summaries of MiraNews are better grounded on assisting documents than in the main source articles. An error analysis of generated summaries from pretrained models fine-tuned on MIRANEWS reveals that this has an even bigger effects on models: assisted summarisation reduces 55% of hallucinations when compared to single-document summarisation models trained on the main article only.

pdf
AuGPT: Auxiliary Tasks and Data Augmentation for End-To-End Dialogue with Pre-Trained Language Models
Jonáš Kulhánek | Vojtěch Hudeček | Tomáš Nekvinda | Ondřej Dušek
Proceedings of the 3rd Workshop on Natural Language Processing for Conversational AI

Attention-based pre-trained language models such as GPT-2 brought considerable progress to end-to-end dialogue modelling. However, they also present considerable risks for task-oriented dialogue, such as lack of knowledge grounding or diversity. To address these issues, we introduce modified training objectives for language model finetuning, and we employ massive data augmentation via back-translation to increase the diversity of the training data. We further examine the possibilities of combining data from multiples sources to improve performance on the target dataset. We carefully evaluate our contributions with both human and automatic methods. Our model substantially outperforms the baseline on the MultiWOZ data and shows competitive performance with state of the art in both automatic and human evaluation.

pdf
AggGen: Ordering and Aggregating while Generating
Xinnuo Xu | Ondřej Dušek | Verena Rieser | Ioannis Konstas
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

We present AggGen (pronounced ‘again’) a data-to-text model which re-introduces two explicit sentence planning stages into neural data-to-text systems: input ordering and input aggregation. In contrast to previous work using sentence planning, our model is still end-to-end: AggGen performs sentence planning at the same time as generating text by learning latent alignments (via semantic facts) between input representation and target text. Experiments on the WebNLG and E2E challenge data show that by using fact-based alignments our approach is more interpretable, expressive, robust to noise, and easier to control, while retaining the advantages of end-to-end systems in terms of fluency. Our code is available at https://github.com/XinnuoXu/AggGen.

pdf
Discovering Dialogue Slots with Weak Supervision
Vojtěch Hudeček | Ondřej Dušek | Zhou Yu
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Task-oriented dialogue systems typically require manual annotation of dialogue slots in training data, which is costly to obtain. We propose a method that eliminates this requirement: We use weak supervision from existing linguistic annotation models to identify potential slot candidates, then automatically identify domain-relevant slots by using clustering algorithms. Furthermore, we use the resulting slot annotation to train a neural-network-based tagger that is able to perform slot tagging with no human intervention. This tagger is trained solely on the outputs of our method and thus does not rely on any labeled data. Our model demonstrates state-of-the-art performance in slot tagging without labeled training data on four different dialogue domains. Moreover, we find that slot annotations discovered by our model significantly improve the performance of an end-to-end dialogue response generation model, compared to using no slot annotation at all.

pdf
Shades of BLEU, Flavours of Success: The Case of MultiWOZ
Tomáš Nekvinda | Ondřej Dušek
Proceedings of the 1st Workshop on Natural Language Generation, Evaluation, and Metrics (GEM 2021)

The MultiWOZ dataset (Budzianowski et al.,2018) is frequently used for benchmarkingcontext-to-response abilities of task-orienteddialogue systems. In this work, we identifyinconsistencies in data preprocessing and re-porting of three corpus-based metrics used onthis dataset, i.e., BLEU score and Inform &Success rates. We point out a few problemsof the MultiWOZ benchmark such as unsat-isfactory preprocessing, insufficient or under-specified evaluation metrics, or rigid database.We re-evaluate 7 end-to-end and 6 policy opti-mization models in as-fair-as-possible setups,and we show that their reported scores cannotbe directly compared. To facilitate compari-son of future systems, we release our stand-alone standardized evaluation scripts. We alsogive basic recommendations for corpus-basedbenchmarking in future works.

pdf
The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics
Sebastian Gehrmann | Tosin Adewumi | Karmanya Aggarwal | Pawan Sasanka Ammanamanchi | Anuoluwapo Aremu | Antoine Bosselut | Khyathi Raghavi Chandu | Miruna-Adriana Clinciu | Dipanjan Das | Kaustubh Dhole | Wanyu Du | Esin Durmus | Ondřej Dušek | Chris Chinenye Emezue | Varun Gangal | Cristina Garbacea | Tatsunori Hashimoto | Yufang Hou | Yacine Jernite | Harsh Jhamtani | Yangfeng Ji | Shailza Jolly | Mihir Kale | Dhruv Kumar | Faisal Ladhak | Aman Madaan | Mounica Maddela | Khyati Mahajan | Saad Mahamood | Bodhisattwa Prasad Majumder | Pedro Henrique Martins | Angelina McMillan-Major | Simon Mille | Emiel van Miltenburg | Moin Nadeem | Shashi Narayan | Vitaly Nikolaev | Andre Niyongabo Rubungo | Salomey Osei | Ankur Parikh | Laura Perez-Beltrachini | Niranjan Ramesh Rao | Vikas Raunak | Juan Diego Rodriguez | Sashank Santhanam | João Sedoc | Thibault Sellam | Samira Shaikh | Anastasia Shimorina | Marco Antonio Sobrevilla Cabezudo | Hendrik Strobelt | Nishant Subramani | Wei Xu | Diyi Yang | Akhila Yerukola | Jiawei Zhou
Proceedings of the 1st Workshop on Natural Language Generation, Evaluation, and Metrics (GEM 2021)

We introduce GEM, a living benchmark for natural language Generation (NLG), its Evaluation, and Metrics. Measuring progress in NLG relies on a constantly evolving ecosystem of automated metrics, datasets, and human evaluation standards. Due to this moving target, new models often still evaluate on divergent anglo-centric corpora with well-established, but flawed, metrics. This disconnect makes it challenging to identify the limitations of current models and opportunities for progress. Addressing this limitation, GEM provides an environment in which models can easily be applied to a wide set of tasks and in which evaluation strategies can be tested. Regular updates to the benchmark will help NLG research become more multilingual and evolve the challenge alongside models. This paper serves as the description of the data for the 2021 shared task at the associated GEM Workshop.

pdf
Définition et détection des incohérences du système dans les dialogues orientés tâche. (We present experiments on automatically detecting inconsistent behavior of task-oriented dialogue systems from the context)
Léon-Paul Schaub | Vojtech Hudecek | Daniel Stancl | Ondrej Dusek | Patrick Paroubek
Actes de la 28e Conférence sur le Traitement Automatique des Langues Naturelles. Volume 1 : conférence principale

Définition et détection des incohérences du système dans les dialogues orientés tâche. Nous présentons des expériences sur la détection automatique des comportements incohérents des systèmes de dialogues orientés tâche à partir du contexte. Nous enrichissons les données bAbI/DSTC2 (Bordes et al., 2017) avec une annotation automatique des incohérences de dialogue, et nous démontrons que les incohérences sont en corrélation avec les dialogues ratés. Nous supposons que l’utilisation d’un historique de dialogue limité et la prédiction du prochain tour de l’utilisateur peuvent améliorer la classification des incohérences. Si les deux hypothèses sont confirmées pour un modèle de dialogue basé sur les réseaux de mémoire, elles ne le sont pas pour un entraînement basé sur le modèle de langage GPT-2, qui bénéficie le plus de l’utilisation de l’historique complet du dialogue et obtient un score de précision de 0,99.

pdf
Underreporting of errors in NLG output, and what to do about it
Emiel van Miltenburg | Miruna Clinciu | Ondřej Dušek | Dimitra Gkatzia | Stephanie Inglis | Leo Leppänen | Saad Mahamood | Emma Manning | Stephanie Schoch | Craig Thomson | Luou Wen
Proceedings of the 14th International Conference on Natural Language Generation

We observe a severe under-reporting of the different kinds of errors that Natural Language Generation systems make. This is a problem, because mistakes are an important indicator of where systems should still be improved. If authors only report overall performance metrics, the research community is left in the dark about the specific weaknesses that are exhibited by ‘state-of-the-art’ research. Next to quantifying the extent of error under-reporting, this position paper provides recommendations for error identification, analysis and reporting.

pdf
Text-in-Context: Token-Level Error Detection for Table-to-Text Generation
Zdeněk Kasner | Simon Mille | Ondřej Dušek
Proceedings of the 14th International Conference on Natural Language Generation

We present our Charles-UPF submission for the Shared Task on Evaluating Accuracy in Generated Texts at INLG 2021. Our system can detect the errors automatically using a combination of a rule-based natural language generation (NLG) system and pretrained language models (LMs). We first utilize a rule-based NLG system to generate sentences with facts that can be derived from the input. For each sentence we evaluate, we select a subset of facts which are relevant by measuring semantic similarity to the sentence in question. Finally, we finetune a pretrained language model on annotated data along with the relevant facts for fine-grained error detection. On the test set, we achieve 69% recall and 75% precision with a model trained on a mixture of human-annotated and synthetic data.

2020

pdf
Train Hard, Finetune Easy: Multilingual Denoising for RDF-to-Text Generation
Zdeněk Kasner | Ondřej Dušek
Proceedings of the 3rd International Workshop on Natural Language Generation from the Semantic Web (WebNLG+)

We describe our system for the RDF-to-text generation task of the WebNLG Challenge 2020. We base our approach on the mBART model, which is pre-trained for multilingual denoising. This allows us to use a simple, identical, end-to-end setup for both English and Russian. Requiring minimal taskor languagespecific effort, our model placed in the first third of the leaderboard for English and first or second for Russian on automatic metrics, and it made it into the best or second-best system cluster on human evaluation.

pdf bib
Proceedings of the 1st Workshop on Evaluating NLG Evaluation
Shubham Agarwal | Ondřej Dušek | Sebastian Gehrmann | Dimitra Gkatzia | Ioannis Konstas | Emiel Van Miltenburg | Sashank Santhanam
Proceedings of the 1st Workshop on Evaluating NLG Evaluation

pdf
Fact-based Content Weighting for Evaluating Abstractive Summarisation
Xinnuo Xu | Ondřej Dušek | Jingyi Li | Verena Rieser | Ioannis Konstas
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Abstractive summarisation is notoriously hard to evaluate since standard word-overlap-based metrics are insufficient. We introduce a new evaluation metric which is based on fact-level content weighting, i.e. relating the facts of the document to the facts of the summary. We fol- low the assumption that a good summary will reflect all relevant facts, i.e. the ones present in the ground truth (human-generated refer- ence summary). We confirm this hypothe- sis by showing that our weightings are highly correlated to human perception and compare favourably to the recent manual highlight- based metric of Hardy et al. (2019).

pdf
Data-to-Text Generation with Iterative Text Editing
Zdeněk Kasner | Ondřej Dušek
Proceedings of the 13th International Conference on Natural Language Generation

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 output text while leveraging the abilities of recent pre-trained models for text editing (LaserTagger) and language modeling (GPT-2) to improve the text fluency. To this end, we first transform data items to text using trivial templates, and then we iteratively improve the resulting text by a neural model trained for the sentence fusion task. The output of the model is filtered by a simple heuristic and reranked with an off-the-shelf pre-trained language model. We evaluate our approach on two major data-to-text datasets (WebNLG, Cleaned E2E) and analyze its caveats and benefits. Furthermore, we show that our formulation of data-to-text generation opens up the possibility for zero-shot domain adaptation using a general-domain dataset for sentence fusion.

pdf
Evaluating Semantic Accuracy of Data-to-Text Generation with Natural Language Inference
Ondřej Dušek | Zdeněk Kasner
Proceedings of the 13th International Conference on Natural Language Generation

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 contains all and only facts supported by the input data. We propose a new metric for evaluating the semantic accuracy of D2T generation based on a neural model pretrained for natural language inference (NLI). We use the NLI model to check textual entailment between the input data and the output text in both directions, allowing us to reveal omissions or hallucinations. Input data are converted to text for NLI using trivial templates. Our experiments on two recent D2T datasets show that our metric can achieve high accuracy in identifying erroneous system outputs.

pdf
Expand and Filter: CUNI and LMU Systems for the WNGT 2020 Duolingo Shared Task
Jindřich Libovický | Zdeněk Kasner | Jindřich Helcl | Ondřej Dušek
Proceedings of the Fourth Workshop on Neural Generation and Translation

We present our submission to the Simultaneous Translation And Paraphrase for Language Education (STAPLE) challenge. We used a standard Transformer model for translation, with a crosslingual classifier predicting correct translations on the output n-best list. To increase the diversity of the outputs, we used additional data to train the translation model, and we trained a paraphrasing model based on the Levenshtein Transformer architecture to generate further synonymous translations. The paraphrasing results were again filtered using our classifier. 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. Our model without the paraphrasing component finished in the middle of the field for the shared task, improving over the best baseline by a margin of 10-22 % weighted F1 absolute.

2019

pdf
User Evaluation of a Multi-dimensional Statistical Dialogue System
Simon Keizer | Ondřej Dušek | Xingkun Liu | Verena Rieser
Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue

We present the first complete spoken dialogue system driven by a multiimensional statistical dialogue manager. This framework has been shown to substantially reduce data needs by leveraging domain-independent dimensions, such as social obligations or feedback, which (as we show) can be transferred between domains. In this paper, we conduct a user study and show that the performance of a multi-dimensional system, which can be adapted from a source domain, is equivalent to that of a one-dimensional baseline, which can only be trained from scratch.

pdf
Automatic Quality Estimation for Natural Language Generation: Ranting (Jointly Rating and Ranking)
Ondřej Dušek | Karin Sevegnani | Ioannis Konstas | Verena Rieser
Proceedings of the 12th International Conference on Natural Language Generation

We present a recurrent neural network based system for automatic quality estimation of natural language generation (NLG) outputs, which jointly learns to assign numerical ratings to individual outputs and to provide pairwise rankings of two different outputs. The latter is trained using pairwise hinge loss over scores from two copies of the rating network. We use learning to rank and synthetic data to improve the quality of ratings assigned by our system: We synthesise training pairs of distorted system outputs and train the system to rank the less distorted one higher. This leads to a 12% increase in correlation with human ratings over the previous benchmark. We also establish the state of the art on the dataset of relative rankings from the E2E NLG Challenge (Dusek et al., 2019), where synthetic data lead to a 4% accuracy increase over the base model.

pdf
Semantic Noise Matters for Neural Natural Language Generation
Ondřej Dušek | David M. Howcroft | Verena Rieser
Proceedings of the 12th International Conference on Natural Language Generation

Neural natural language generation (NNLG) systems are known for their pathological outputs, i.e. generating text which is unrelated to the input specification. In this paper, we show the impact of semantic noise on state-of-the-art NNLG models which implement different semantic control mechanisms. We find that cleaned data can improve semantic correctness by up to 97%, while maintaining fluency. We also find that the most common error is omitting information, rather than hallucination.

pdf
Neural Generation for Czech: Data and Baselines
Ondřej Dušek | Filip Jurčíček
Proceedings of the 12th International Conference on Natural Language Generation

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. While non-English NLG is under-explored in general, Czech, as a morphologically rich language, makes the task even harder: Since Czech requires inflecting named entities, delexicalization or copy mechanisms do not work out-of-the-box and lexicalizing the generated outputs is non-trivial. In our experiments, we present two different approaches to this this problem: (1) using a neural language model to select the correct inflected form while lexicalizing, (2) a two-step generation setup: our sequence-to-sequence model generates an interleaved sequence of lemmas and morphological tags, which are then inflected by a morphological generator.

2018

pdf bib
Neural Response Ranking for Social Conversation: A Data-Efficient Approach
Igor Shalyminov | Ondřej Dušek | Oliver Lemon
Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI

The overall objective of ‘social’ dialogue systems is to support engaging, entertaining, and lengthy conversations on a wide variety of topics, including social chit-chat. Apart from raw dialogue data, user-provided ratings are the most common signal used to train such systems to produce engaging responses. In this paper we show that social dialogue systems can be trained effectively from raw unannotated data. Using a dataset of real conversations collected in the 2017 Alexa Prize challenge, we developed a neural ranker for selecting ‘good’ system responses to user utterances, i.e. responses which are likely to lead to long and engaging conversations. We show that (1) our neural ranker consistently outperforms several strong baselines when trained to optimise for user ratings; (2) when trained on larger amounts of data and only using conversation length as the objective, the ranker performs better than the one trained using ratings – ultimately reaching a Precision@1 of 0.87. This advance will make data collection for social conversational agents simpler and less expensive in the future.

pdf
A Knowledge-Grounded Multimodal Search-Based Conversational Agent
Shubham Agarwal | Ondřej Dušek | Ioannis Konstas | Verena Rieser
Proceedings of the 2018 EMNLP Workshop SCAI: The 2nd International Workshop on Search-Oriented Conversational AI

Multimodal search-based dialogue is a challenging new task: It extends visually grounded question answering systems into multi-turn conversations with access to an external database. We address this new challenge by learning a neural response generation system from the recently released Multimodal Dialogue (MMD) dataset (Saha et al., 2017). We introduce a knowledge-grounded multimodal conversational model where an encoded knowledge base (KB) representation is appended to the decoder input. Our model substantially outperforms strong baselines in terms of text-based similarity measures (over 9 BLEU points, 3 of which are solely due to the use of additional information from the KB).

pdf
Improving Context Modelling in Multimodal Dialogue Generation
Shubham Agarwal | Ondřej Dušek | Ioannis Konstas | Verena Rieser
Proceedings of the 11th International Conference on Natural Language Generation

In this work, we investigate the task of textual response generation in a multimodal task-oriented dialogue system. Our work is based on the recently released Multimodal Dialogue (MMD) dataset (Saha et al., 2017) in the fashion domain. We introduce a multimodal extension to the Hierarchical Recurrent Encoder-Decoder (HRED) model and show that this extension outperforms strong baselines in terms of text-based similarity metrics. We also showcase the shortcomings of current vision and language models by performing an error analysis on our system’s output.

pdf
Findings of the E2E NLG Challenge
Ondřej Dušek | Jekaterina Novikova | Verena Rieser
Proceedings of the 11th International Conference on Natural Language Generation

This paper summarises the experimental setup and results of the first shared task on end-to-end (E2E) natural language generation (NLG) in spoken dialogue systems. Recent end-to-end generation systems are promising since they reduce the need for data annotation. However, they are currently limited to small, delexicalised datasets. The E2E NLG shared task aims to assess whether these novel approaches can generate better-quality output by learning from a dataset containing higher lexical richness, syntactic complexity and diverse discourse phenomena. We compare 62 systems submitted by 17 institutions, covering a wide range of approaches, including machine learning architectures – with the majority implementing sequence-to-sequence models (seq2seq) – as well as systems based on grammatical rules and templates.

pdf
RankME: Reliable Human Ratings for Natural Language Generation
Jekaterina Novikova | Ondřej Dušek | Verena Rieser
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)

Human evaluation for natural language generation (NLG) often suffers from inconsistent user ratings. While previous research tends to attribute this problem to individual user preferences, we show that the quality of human judgements can also be improved by experimental design. We present a novel rank-based magnitude estimation method (RankME), which combines the use of continuous scales and relative assessments. We show that RankME significantly improves the reliability and consistency of human ratings compared to traditional evaluation methods. In addition, we show that it is possible to evaluate NLG systems according to multiple, distinct criteria, which is important for error analysis. Finally, we demonstrate that RankME, in combination with Bayesian estimation of system quality, is a cost-effective alternative for ranking multiple NLG systems.

pdf
Better Conversations by Modeling, Filtering, and Optimizing for Coherence and Diversity
Xinnuo Xu | Ondřej Dušek | Ioannis Konstas | Verena Rieser
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

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. Experiments on the OpenSubtitles corpus show a substantial improvement over competitive neural models in terms of BLEU score as well as metrics of coherence and diversity.

2017

pdf
The E2E Dataset: New Challenges For End-to-End Generation
Jekaterina Novikova | Ondřej Dušek | Verena Rieser
Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue

This paper describes the E2E data, a new dataset for training end-to-end, data-driven natural language generation systems in the restaurant domain, which is ten times bigger than existing, frequently used datasets in this area. The E2E dataset poses new challenges: (1) its human reference texts show more lexical richness and syntactic variation, including discourse phenomena; (2) generating from this set requires content selection. As such, learning from this dataset promises more natural, varied and less template-like system utterances. We also establish a baseline on this dataset, which illustrates some of the difficulties associated with this data.

pdf
Why We Need New Evaluation Metrics for NLG
Jekaterina Novikova | Ondřej Dušek | Amanda Cercas Curry | Verena Rieser
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

The majority of NLG evaluation relies on automatic metrics, such as BLEU . In this paper, we motivate the need for novel, system- and data-independent automatic evaluation methods: We investigate a wide range of metrics, including state-of-the-art word-based and novel grammar-based ones, and demonstrate that they only weakly reflect human judgements of system outputs as generated by data-driven, end-to-end NLG. We also show that metric performance is data- and system-specific. Nevertheless, our results also suggest that automatic metrics perform reliably at system-level and can support system development by finding cases where a system performs poorly.

2016

pdf
Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings
Ondřej Dušek | Filip Jurčíček
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

pdf
A Context-aware Natural Language Generator for Dialogue Systems
Ondřej Dušek | Filip Jurčíček
Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue

pdf
Verb sense disambiguation in Machine Translation
Roman Sudarikov | Ondřej Dušek | Martin Holub | Ondřej Bojar | Vincent Kríž
Proceedings of the Sixth Workshop on Hybrid Approaches to Translation (HyTra6)

We describe experiments in Machine Translation using word sense disambiguation (WSD) information. This work focuses on WSD in verbs, based on two different approaches – verbal patterns based on corpus pattern analysis and verbal word senses from valency frames. We evaluate several options of using verb senses in the source-language sentences as an additional factor for the Moses statistical machine translation system. Our results show a statistically significant translation quality improvement in terms of the BLEU metric for the valency frames approach, but in manual evaluation, both WSD methods bring improvements.

pdf bib
Moses & Treex Hybrid MT Systems Bestiary
Rudolf Rosa | Martin Popel | Ondřej Bojar | David Mareček | Ondřej Dušek
Proceedings of the 2nd Deep Machine Translation Workshop

2015

pdf
Bilingual English-Czech Valency Lexicon Linked to a Parallel Corpus
Zdeňka Urešová | Ondřej Dušek | Eva Fučíková | Jan Hajič | Jana Šindlerová
Proceedings of the 9th Linguistic Annotation Workshop

pdf
Using Parallel Texts and Lexicons for Verbal Word Sense Disambiguation
Ondřej Dušek | Eva Fučíková | Jan Hajič | Martin Popel | Jana Šindlerová | Zdeňka Urešová
Proceedings of the Third International Conference on Dependency Linguistics (Depling 2015)

pdf
New Language Pairs in TectoMT
Ondřej Dušek | Luís Gomes | Michal Novák | Martin Popel | Rudolf Rosa
Proceedings of the Tenth Workshop on Statistical Machine Translation

pdf
Translation Model Interpolation for Domain Adaptation in TectoMT
Rudolf Rosa | Ondřej Dušek | Michal Novák | Martin Popel
Proceedings of the 1st Deep Machine Translation Workshop

pdf
Training a Natural Language Generator From Unaligned Data
Ondřej Dušek | Filip Jurčíček
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

2014

pdf bib
Verbal Valency Frame Detection and Selection in Czech and English
Ondřej Dušek | Jan Hajič | Zdeňka Urešová
Proceedings of the Second Workshop on EVENTS: Definition, Detection, Coreference, and Representation

pdf
Machine Translation of Medical Texts in the Khresmoi Project
Ondřej Dušek | Jan Hajič | Jaroslava Hlaváčová | Michal Novák | Pavel Pecina | Rudolf Rosa | Aleš Tamchyna | Zdeňka Urešová | Daniel Zeman
Proceedings of the Ninth Workshop on Statistical Machine Translation

pdf
Alex: Bootstrapping a Spoken Dialogue System for a New Domain by Real Users
Ondřej Dušek | Ondřej Plátek | Lukáš Žilka | Filip Jurčíček
Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)

pdf
Free English and Czech telephone speech corpus shared under the CC-BY-SA 3.0 license
Matěj Korvas | Ondřej Plátek | Ondřej Dušek | Lukáš Žilka | Filip Jurčíček
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)

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). The data comprise 45 hours of speech in English and over 18 hours in Czech. Large part of the data, both audio and transcriptions, was collected using crowdsourcing, the rest are transcriptions by hired transcribers. We release the data together with scripts for data pre-processing and building acoustic models using the HTK and Kaldi ASR toolkits. We publish also the trained models described in this paper. The data are released under the CC-BY-SA 3.0 license, the scripts are licensed under Apache 2.0. In the paper, we report on the methodology of collecting the data, on the size and properties of the data, and on the scripts and their use. We verify the usability of the datasets by training and evaluating acoustic models using the presented data and scripts.

pdf
Multilingual Test Sets for Machine Translation of Search Queries for Cross-Lingual Information Retrieval in the Medical Domain
Zdeňka Urešová | Jan Hajič | Pavel Pecina | Ondřej Dušek
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)

This paper presents development and test sets for machine translation of search queries in cross-lingual information retrieval in the medical domain. The data consists of the total of 1,508 real user queries in English translated to Czech, German, and French. We describe the translation and review process involving medical professionals and present a baseline experiment where our data sets are used for tuning and evaluation of a machine translation system.

2013

pdf
Robust multilingual statistical morphological generation models
Ondřej Dušek | Filip Jurčíček
51st Annual Meeting of the Association for Computational Linguistics Proceedings of the Student Research Workshop

2012

pdf
The Joy of Parallelism with CzEng 1.0
Ondřej Bojar | Zdeněk Žabokrtský | Ondřej Dušek | Petra Galuščáková | Martin Majliš | David Mareček | Jiří Maršík | Michal Novák | Martin Popel | Aleš Tamchyna
Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12)

CzEng 1.0 is an updated release of our Czech-English parallel corpus, freely available for non-commercial research or educational purposes. In this release, we approximately doubled the corpus size, reaching 15 million sentence pairs (about 200 million tokens per language). More importantly, we carefully filtered the data to reduce the amount of non-matching sentence pairs. CzEng 1.0 is automatically aligned at the level of sentences as well as words. We provide not only the plain text representation, but also automatic morphological tags, surface syntactic as well as deep syntactic dependency parse trees and automatic co-reference links in both English and Czech. This paper describes key properties of the released resource including the distribution of text domains, the corpus data formats, and a toolkit to handle the provided rich annotation. We also summarize the procedure of the rich annotation (incl. co-reference resolution) and of the automatic filtering. Finally, we provide some suggestions on exploiting such an automatically annotated sentence-parallel corpus.

pdf
Formemes in English-Czech Deep Syntactic MT
Ondřej Dušek | Zdeněk Žabokrtský | Martin Popel | Martin Majliš | Michal Novák | David Mareček
Proceedings of the Seventh Workshop on Statistical Machine Translation

pdf
DEPFIX: A System for Automatic Correction of Czech MT Outputs
Rudolf Rosa | David Mareček | Ondřej Dušek
Proceedings of the Seventh Workshop on Statistical Machine Translation

pdf
Using Parallel Features in Parsing of Machine-Translated Sentences for Correction of Grammatical Errors
Rudolf Rosa | Ondřej Dušek | David Mareček | Martin Popel
Proceedings of the Sixth Workshop on Syntax, Semantics and Structure in Statistical Translation

Search
Co-authors