Papers by Ondřej Dušek
Learning Interpretable Latent Dialogue Actions With Less Supervision (2022.aacl-main)
Copied to clipboard
| Challenge: | supervised neural dialogue modeling requires a significant amount of work to obtain turn-level labels, usually with dialogue state annotation. |
| Approach: | They propose a novel architecture for explainable modeling of task-oriented dialogues with discrete latent variables to represent dialogue actions. |
| Outcome: | The proposed model outperforms previous approaches with less supervision in terms of perplexity and BLEU on three datasets. |
Better Conversations by Modeling, Filtering, and Optimizing for Coherence and Diversity (D18-1)
Copied to clipboard
| Challenge: | Existing encoder-decoder models for open domain dialogue generate generic, uninformative, and non-coherent responses. |
| Approach: | They propose to introduce a measure of coherence as the GloVe embedding similarity between dialogue context and generated response to improve output diversity. |
| Outcome: | The proposed model improves on the OpenSubtitles corpus in terms of BLEU score and diversity metrics. |
MiRANews: Dataset and Benchmarks for Multi-Resource-Assisted News Summarization (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Current news summarization systems often contain 'extrinsic hallucinations', i.e. facts that are not present in the source document, which are often derived via world knowledge. |
| Approach: | They propose to use multiple supplementary resource documents to assist the task by pairing a single document with a human authored summary as the summary. |
| Outcome: | The proposed model reduces 55% of hallucinations when compared to single-document summarization models trained on the main article only. |
RankME: Reliable Human Ratings for Natural Language Generation (N18-2)
Copied to clipboard
| Challenge: | Existing studies have shown that human evaluation for natural language generation often suffers from inconsistent user ratings. |
| Approach: | They propose a rank-based magnitude estimation method which combines continuous scales and relative assessments to improve the reliability of human ratings. |
| Outcome: | The proposed method significantly improves the reliability and consistency of human ratings compared to traditional evaluation methods. |
Fact-based Content Weighting for Evaluating Abstractive Summarisation (2020.acl-main)
Copied to clipboard
| Challenge: | Abstractive summarisation is notoriously hard to evaluate since word-overlap-based metrics are insufficient. |
| Approach: | They propose a new evaluation metric which is based on fact-level content weighting, relating the facts of the document to the facts in the summary. |
| Outcome: | The proposed evaluation metric is highly correlated to human perception and compares favourably to the recent manual highlight-based metric of Hardy et al. |
Discovering Dialogue Slots with Weak Supervision (2021.acl-long)
Copied to clipboard
| Challenge: | Task-oriented dialogue systems typically require manual annotation of dialogue slots in training data. |
| Approach: | They propose a method that uses weak supervision to identify slot candidates and automatically identify domain-relevant slots by using clustering algorithms. |
| Outcome: | The proposed method significantly improves an end-to-end dialogue response generation model compared to using no slot annotation at all. |
Polite Chatbot: A Text Style Transfer Application (2023.eacl-srw)
Copied to clipboard
| Challenge: | Creating polite chatbots requires complex setups that require reinforcement learning to produce coherent responses. |
| Approach: | They propose a polite chatbot that can generate coherent responses to given contexts by using a model that transfers neutral sentences into polite ones and trains a dialogue model. |
| Outcome: | The proposed method outperforms baselines in producing polite dialogue responses while staying competitive in terms of coherent to the given context. |
A Unifying View On Task-oriented Dialogue Annotation (2022.lrec-1)
Copied to clipboard
| Challenge: | Recent research attention in task-oriented dialogue systems focuses on end-to-end neural models. |
| Approach: | They present a dataset that combines annotated corpora from four domains to provide a unified ontology and annotation schema for task-oriented dialogues. |
| Outcome: | The proposed dataset improves language, information content and performance in dialogues with two recent models. |
AggGen: Ordering and Aggregating while Generating (2021.acl-long)
Copied to clipboard
| Challenge: | AggGen is a data-to-text model which re-introduces two explicit sentence planning stages into neural data- to-text systems: input ordering and input aggregation. |
| Approach: | AggGen re-introduces two explicit sentence planning stages into neural data-to-text systems: input ordering and input aggregation. |
| Outcome: | AggGen is a data-to-text model which re-introduces two explicit sentence planning stages into neural data- to-text systems: input ordering and input aggregation. |