|
--- |
|
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 |
|
|
|
|
|
### 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> |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
