AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog
- URL: http://arxiv.org/abs/2209.03632v1
- Date: Thu, 8 Sep 2022 08:15:22 GMT
- Title: AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog
- Authors: Tom\'a\v{s} Nekvinda, Ond\v{r}ej Du\v{s}ek
- Abstract summary: AARGH is an end-to-end task-oriented dialog system combining retrieval and generative approaches in a single model.
We show that our approach produces more diverse outputs while maintaining or improving state tracking and context-to-response generation performance.
- Score: 3.42658286826597
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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.
Related papers
- DialCLIP: Empowering CLIP as Multi-Modal Dialog Retriever [83.33209603041013]
We propose a parameter-efficient prompt-tuning method named DialCLIP for multi-modal dialog retrieval.
Our approach introduces a multi-modal context generator to learn context features which are distilled into prompts within the pre-trained vision-language model CLIP.
To facilitate various types of retrieval, we also design multiple experts to learn mappings from CLIP outputs to multi-modal representation space.
arXiv Detail & Related papers (2024-01-02T07:40:12Z) - Using Textual Interface to Align External Knowledge for End-to-End
Task-Oriented Dialogue Systems [53.38517204698343]
We propose a novel paradigm that uses a textual interface to align external knowledge and eliminate redundant processes.
We demonstrate our paradigm in practice through MultiWOZ-Remake, including an interactive textual interface built for the MultiWOZ database.
arXiv Detail & Related papers (2023-05-23T05:48:21Z) - DIONYSUS: A Pre-trained Model for Low-Resource Dialogue Summarization [127.714919036388]
DIONYSUS is a pre-trained encoder-decoder model for summarizing dialogues in any new domain.
Our experiments show that DIONYSUS outperforms existing methods on six datasets.
arXiv Detail & Related papers (2022-12-20T06:21:21Z) - KGI: An Integrated Framework for Knowledge Intensive Language Tasks [16.511913995069097]
In this paper, we propose a system based on an enhanced version of this approach for other knowledge intensive language tasks.
Our system achieves results comparable to the best models in the KILT leaderboards.
arXiv Detail & Related papers (2022-04-08T10:36:21Z) - Retrieval-Augmented Transformer-XL for Close-Domain Dialog Generation [16.90730526207747]
We present a transformer-based model for multi-turn dialog response generation.
Our solution is based on a hybrid approach which augments a transformer-based generative model with a novel retrieval mechanism.
arXiv Detail & Related papers (2021-05-19T16:34:33Z) - Modeling Long Context for Task-Oriented Dialogue State Generation [51.044300192906995]
We propose a multi-task learning model with a simple yet effective utterance tagging technique and a bidirectional language model.
Our approaches attempt to solve the problem that the performance of the baseline significantly drops when the input dialogue context sequence is long.
In our experiments, our proposed model achieves a 7.03% relative improvement over the baseline, establishing a new state-of-the-art joint goal accuracy of 52.04% on the MultiWOZ 2.0 dataset.
arXiv Detail & Related papers (2020-04-29T11:02:25Z) - Paraphrase Augmented Task-Oriented Dialog Generation [68.1790912977053]
We propose a paraphrase augmented response generation (PARG) framework that jointly trains a paraphrase model and a response generation model.
We also design a method to automatically construct paraphrase training data set based on dialog state and dialog act labels.
arXiv Detail & Related papers (2020-04-16T05:12:36Z) - Variational Hierarchical Dialog Autoencoder for Dialog State Tracking
Data Augmentation [59.174903564894954]
In this work, we extend this approach to the task of dialog state tracking for goal-oriented dialogs.
We propose the Variational Hierarchical Dialog Autoencoder (VHDA) for modeling the complete aspects of goal-oriented dialogs.
Experiments on various dialog datasets show that our model improves the downstream dialog trackers' robustness via generative data augmentation.
arXiv Detail & Related papers (2020-01-23T15:34:56Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.