Modeling Real-Time Interactive Conversations as Timed Diarized Transcripts
- URL: http://arxiv.org/abs/2405.13203v1
- Date: Tue, 21 May 2024 21:14:31 GMT
- Title: Modeling Real-Time Interactive Conversations as Timed Diarized Transcripts
- Authors: Garrett Tanzer, Gustaf Ahdritz, Luke Melas-Kyriazi,
- Abstract summary: We present a simple yet general method to simulate real-time interactive conversations using pretrained language models.
We demonstrate the promise of this method with two case studies: instant messenger dialogues and spoken conversations.
- Score: 11.067252960486272
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Chatbots built upon language models have exploded in popularity, but they have largely been limited to synchronous, turn-by-turn dialogues. In this paper we present a simple yet general method to simulate real-time interactive conversations using pretrained text-only language models, by modeling timed diarized transcripts and decoding them with causal rejection sampling. We demonstrate the promise of this method with two case studies: instant messenger dialogues and spoken conversations, which require generation at about 30 tok/s and 20 tok/s respectively to maintain real-time interactivity. These capabilities can be added into language models using relatively little data and run on commodity hardware.
Related papers
- Computational Argumentation-based Chatbots: a Survey [0.4024850952459757]
The present survey sifts through the literature to review papers concerning this kind of argumentation-based bot.
It draws conclusions about the drawbacks and benefits of this approach.
It also envisaging possible future development and integration with the Transformer-based architecture and state-of-the-art Large Language models.
arXiv Detail & Related papers (2024-01-07T11:20:42Z) - Pheme: Efficient and Conversational Speech Generation [52.34331755341856]
We introduce the Pheme model series that offers compact yet high-performing conversational TTS models.
It can be trained efficiently on smaller-scale conversational data, cutting data demands by more than 10x but still matching the quality of the autoregressive TTS models.
arXiv Detail & Related papers (2024-01-05T14:47:20Z) - An Interleaving Semantics of the Timed Concurrent Language for
Argumentation to Model Debates and Dialogue Games [0.0]
We propose a language for modelling concurrent interaction between agents.
Such a language exploits a shared memory used by the agents to communicate and reason on the acceptability of their beliefs.
We show how it can be used to model interactions such as debates and dialogue games taking place between intelligent agents.
arXiv Detail & Related papers (2023-06-13T10:41:28Z) - Stabilized In-Context Learning with Pre-trained Language Models for Few
Shot Dialogue State Tracking [57.92608483099916]
Large pre-trained language models (PLMs) have shown impressive unaided performance across many NLP tasks.
For more complex tasks such as dialogue state tracking (DST), designing prompts that reliably convey the desired intent is nontrivial.
We introduce a saliency model to limit dialogue text length, allowing us to include more exemplars per query.
arXiv Detail & Related papers (2023-02-12T15:05:10Z) - Grounding Language Models to Images for Multimodal Inputs and Outputs [89.30027812161686]
We propose an efficient method to ground pretrained text-only language models to the visual domain.
We process arbitrarily interleaved image-and-text data, and generate text interleaved with retrieved images.
arXiv Detail & Related papers (2023-01-31T18:33:44Z) - Effectiveness of French Language Models on Abstractive Dialogue
Summarization Task [5.556906034471034]
We present a study on the summarization of spontaneous oral dialogues in French using several language specific pre-trained models.
Results show that the BARThez models offer the best performance far above the previous state-of-the-art on DECODA.
arXiv Detail & Related papers (2022-07-17T21:43:18Z) - CloneBot: Personalized Dialogue-Response Predictions [0.0]
The project task was to create a model that, given a speaker ID, chat history, and an utterance query, can predict the response utterance in a conversation.
The model is personalized for each speaker. This task can be a useful tool for building speech bots that talk in a human-like manner in a live conversation.
arXiv Detail & Related papers (2021-03-31T01:15:37Z) - Plug-and-Play Conversational Models [62.77150879036442]
We introduce an approach that does not require further computation at decoding time, while also does not require any fine-tuning of a large language model.
We demonstrate, through extensive automatic and human evaluation, a high degree of control over the generated conversational responses with regard to multiple desired attributes.
arXiv Detail & Related papers (2020-10-09T03:17:51Z) - The Adapter-Bot: All-In-One Controllable Conversational Model [66.48164003532484]
We propose a dialogue model that uses a fixed backbone model such as DialGPT and triggers on-demand dialogue skills via different adapters.
Depending on the skills, the model is able to process multiple knowledge types, such as text, tables, and emphatic responses.
We evaluate our model using automatic evaluation by comparing it with existing state-of-the-art conversational models.
arXiv Detail & Related papers (2020-08-28T10:59:31Z) - Knowledge Injection into Dialogue Generation via Language Models [85.65843021510521]
InjK is a two-stage approach to inject knowledge into a dialogue generation model.
First, we train a large-scale language model and query it as textual knowledge.
Second, we frame a dialogue generation model to sequentially generate textual knowledge and a corresponding response.
arXiv Detail & Related papers (2020-04-30T07:31:24Z)
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.