Papers by Ondřej Dušek

9 papers
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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations