COMEDY_7B / README.md
Nuo97's picture
Update README.md
fbb22f1 verified
|
raw
history blame
2.3 kB
---
license: apache-2.0
datasets:
- Nuo97/Dolphin-DPO
language:
- zh
metrics:
- bleu
pipeline_tag: conversational
---
# COMEDY: COmpressive Memory-Enhanced Dialogue sYstems framework.
Github: https://github.com/nuochenpku/COMEDY
<br>
<div align="center">
<img src="comedy.png" width="40%" title="Introduction Figure">
</div>
### Task: Long-Term Conversation Dialogue Generation
Different from previous retrieval-based methods, COMEDY doesn't rely on any **retrieval module or database**.
Instead, COMEDY adopts a groundbreaking ''**One-for-All**'' approach, utilizing a single, unified model to manage the entire process from memory generation, compression to final response generation for long-term memory dialogue generation.
- COMEDY firstly involves distilling session-specific memory from past dialogues, encompassing fine-grained session summaries, including event recaps, and detailed user and bot portraits;
- In a break from traditional systems, COMEDY eschews the use of a memory database for storing these insights. Instead, it reprocesses and condenses memories from all past interactions, forming a *Compressive Memory*: The first part is the **concise events** that have occurred throughout all the conversations, creating a historical narrative that the system can draw upon. The second and third parts consist of a **detailed user profile** and the **dynamic relationship changes** between the user and chatbot across sessions, both derived from past conversational events.
- Finally, COMEDY skillfully integrates this compressive memory into ongoing conversations, enabling contextually memory-enhanced interactions.
### Training Dataset
**Dolphin**, the biggest Chinese long-term conversation dataset, from actual online user-chatbot interactions.
This dataset contains three tasks:
**Session-Level Memory Summarization**;
**Memory Compression**;
**Memory-Grounded Response Generation**,
comprising an extensive collection of 100k samples.
Dolphin is available at [**Dolphin**](https://huggingface.co/datasets/Nuo97/Dolphin-DPO)
### Training Strategy
Our training strategies include two stages: Mixed-task training and DPO Alignment.
<br>
<div align="center">
<img src="training_strategy.png" width="90%" title="Introduction Figure">
</div>