Neural Generation of Dialogue Response Timings
- URL: http://arxiv.org/abs/2005.09128v1
- Date: Mon, 18 May 2020 23:00:57 GMT
- Title: Neural Generation of Dialogue Response Timings
- Authors: Matthew Roddy and Naomi Harte
- Abstract summary: We propose neural models that simulate the distributions of spoken response offsets.
The models are designed to be integrated into the pipeline of an incremental spoken dialogue system.
We show that human listeners consider certain response timings to be more natural based on the dialogue context.
- Score: 13.611050992168506
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The timings of spoken response offsets in human dialogue have been shown to
vary based on contextual elements of the dialogue. We propose neural models
that simulate the distributions of these response offsets, taking into account
the response turn as well as the preceding turn. The models are designed to be
integrated into the pipeline of an incremental spoken dialogue system (SDS). We
evaluate our models using offline experiments as well as human listening tests.
We show that human listeners consider certain response timings to be more
natural based on the dialogue context. The introduction of these models into
SDS pipelines could increase the perceived naturalness of interactions.
Related papers
- Attribution and Alignment: Effects of Local Context Repetition on
Utterance Production and Comprehension in Dialogue [6.886248462185439]
Repetition is typically penalised when evaluating language model generations.
Humans use local and partner specific repetitions; these are preferred by human users and lead to more successful communication in dialogue.
In this study, we evaluate (a) whether language models produce human-like levels of repetition in dialogue, and (b) what are the processing mechanisms related to lexical re-use they use during comprehension.
arXiv Detail & Related papers (2023-11-21T23:50:33Z) - Promoting Open-domain Dialogue Generation through Learning Pattern
Information between Contexts and Responses [5.936682548344234]
This paper improves the quality of generated responses by learning the implicit pattern information between contexts and responses in the training samples.
We also design a response-aware mechanism for mining the implicit pattern information between contexts and responses so that the generated replies are more diverse and approximate to human replies.
arXiv Detail & Related papers (2023-09-06T08:11:39Z) - Leveraging Implicit Feedback from Deployment Data in Dialogue [83.02878726357523]
We study improving social conversational agents by learning from natural dialogue between users and a deployed model.
We leverage signals like user response length, sentiment and reaction of the future human utterances in the collected dialogue episodes.
arXiv Detail & Related papers (2023-07-26T11:34:53Z) - EM Pre-training for Multi-party Dialogue Response Generation [86.25289241604199]
In multi-party dialogues, the addressee of a response utterance should be specified before it is generated.
We propose an Expectation-Maximization (EM) approach that iteratively performs the expectation steps to generate addressee labels.
arXiv Detail & Related papers (2023-05-21T09:22:41Z) - Improving a sequence-to-sequence nlp model using a reinforcement
learning policy algorithm [0.0]
Current neural network models of dialogue generation show great promise for generating answers for chatty agents.
But they are short-sighted in that they predict utterances one at a time while disregarding their impact on future outcomes.
This work commemorates a preliminary step toward developing a neural conversational model based on the long-term success of dialogues.
arXiv Detail & Related papers (2022-12-28T22:46:57Z) - "How Robust r u?": Evaluating Task-Oriented Dialogue Systems on Spoken
Conversations [87.95711406978157]
This work presents a new benchmark on spoken task-oriented conversations.
We study multi-domain dialogue state tracking and knowledge-grounded dialogue modeling.
Our data set enables speech-based benchmarking of task-oriented dialogue systems.
arXiv Detail & Related papers (2021-09-28T04:51:04Z) - DynaEval: Unifying Turn and Dialogue Level Evaluation [60.66883575106898]
We propose DynaEval, a unified automatic evaluation framework.
It is capable of performing turn-level evaluation, but also holistically considers the quality of the entire dialogue.
Experiments show that DynaEval significantly outperforms the state-of-the-art dialogue coherence model.
arXiv Detail & Related papers (2021-06-02T12:23:18Z) - Learning from Perturbations: Diverse and Informative Dialogue Generation
with Inverse Adversarial Training [10.17868476063421]
We propose Inverse Adversarial Training (IAT) algorithm for training neural dialogue systems.
IAT encourages the model to be sensitive to the perturbation in the dialogue history and therefore learning from perturbations.
We show that our approach can better model dialogue history and generate more diverse and consistent responses.
arXiv Detail & Related papers (2021-05-31T17:28:37Z) - Learning Reasoning Paths over Semantic Graphs for Video-grounded
Dialogues [73.04906599884868]
We propose a novel framework of Reasoning Paths in Dialogue Context (PDC)
PDC model discovers information flows among dialogue turns through a semantic graph constructed based on lexical components in each question and answer.
Our model sequentially processes both visual and textual information through this reasoning path and the propagated features are used to generate the answer.
arXiv Detail & Related papers (2021-03-01T07:39:26Z) - Weakly-Supervised Neural Response Selection from an Ensemble of
Task-Specialised Dialogue Agents [11.21333474984984]
We model the problem of selecting the best response from a set of responses generated by a heterogeneous set of dialogue agents.
The proposed method is trained to predict a coherent set of responses within a single conversation, considering its own predictions via a curriculum training mechanism.
arXiv Detail & Related papers (2020-05-06T18:40:26Z) - Dialogue-Based Relation Extraction [53.2896545819799]
We present the first human-annotated dialogue-based relation extraction (RE) dataset DialogRE.
We argue that speaker-related information plays a critical role in the proposed task, based on an analysis of similarities and differences between dialogue-based and traditional RE tasks.
Experimental results demonstrate that a speaker-aware extension on the best-performing model leads to gains in both the standard and conversational evaluation settings.
arXiv Detail & Related papers (2020-04-17T03:51:57Z)
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.