|
--- |
|
license: cc-by-4.0 |
|
datasets: |
|
- jihyoung/ConversationChronicles |
|
language: |
|
- en |
|
pipeline_tag: conversational |
|
--- |
|
|
|
# 👫ReBot - Generation Module⏰ |
|
|
|
ReBot is a novel multi-session dialgoue model which can generate dialogue with chronological dynamics! ReBot consists two modules: (1) chronological summarization module; (2) dialogue generation module. |
|
|
|
**This repoistory for dialogue generation module.** You can check summarization module on [this repoistory](https://huggingface.co/jihyoung/rebot-summarization). |
|
|
|
🚨 Please be cautious when testing our model with the Hosted Inference API. Our model takes sequences as input, so you should provide sequences as input through the API as well. |
|
|
|
## Model description |
|
|
|
+ Paper: [Conversation Chronicles: Towards Diverse Temporal and Relational Dynamics in Multi-Session Conversations](https://arxiv.org/abs/2310.13420) |
|
+ Dataset : [Conversation Chronicles](https://huggingface.co/datasets/jihyoung/ConversationChronicles) |
|
+ Generation Module of Model : this repoistory |
|
+ Summarization Module of Model : [chronological summarization module](https://huggingface.co/jihyoung/rebot-summarization) |
|
|
|
## Load with Transformers |
|
|
|
To load our dataset with Hugging Face Transformers, please use the following code: |
|
|
|
```python |
|
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM |
|
|
|
tokenizer = AutoTokenizer.from_pretrained("jihyoung/rebot-generation") |
|
model = AutoModelForSeq2SeqLM.from_pretrained("jihyoung/rebot-generation") |
|
``` |
|
|
|
## Citation Information |
|
|
|
``` |
|
@inproceedings{jang2023conversation, |
|
title={Conversation Chronicles: Towards Diverse Temporal and Relational Dynamics in Multi-Session Conversations}, |
|
author={Jihyoung Jang, MinSeong Boo, Hyounghun Kim}, |
|
booktitle={The 2023 Conference on Empirical Methods in Natural Language Processing}, |
|
year={2023}, |
|
url={https://arxiv.org/abs/2310.13420} |
|
} |
|
``` |
|
|
