# Multi-level Memory for Task Oriented Dialogs

arXiv: https://arxiv.org/abs/1810.10647 · HTML: https://mlsanity.com/paper/1810.10647/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Oct 2018.

## Built on by (most cited first, 14 of 14)

- [Few-Shot Bot: Prompt-Based Learning for Dialogue Systems](https://mlsanity.com/paper/2110.08118/) (2021)
- [BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling](https://mlsanity.com/paper/2106.02787/) (2021)
- [Continual Learning for Task-oriented Dialogue System with Iterative Network Pruning, Expanding and Masking](https://mlsanity.com/paper/2107.08173/) (2021)
- [End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs](https://mlsanity.com/paper/2109.07263/) (2021)
- [DialoKG: Knowledge-Structure Aware Task-Oriented Dialogue Generation](https://mlsanity.com/paper/2204.09149/) (2022)
- [End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions](https://mlsanity.com/paper/2311.09008/) (2023)
- [Constraint based Knowledge Base Distillation in End-to-End Task Oriented Dialogs](https://mlsanity.com/paper/2109.07396/) (2021)
- [Commonsense and Named Entity Aware Knowledge Grounded Dialogue Generation](https://mlsanity.com/paper/2205.13928/) (2022)
- [Autoregressive Entity Generation for End-to-End Task-Oriented Dialog](https://mlsanity.com/paper/2209.08708/) (2022)
- [A Comparative Study on Language Models for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2201.08687/) (2022)
- [CDialog: A Multi-turn Covid-19 Conversation Dataset for Entity-Aware Dialog Generation](https://mlsanity.com/paper/2212.06049/) (2022)
- [Variational Learning for Unsupervised Knowledge Grounded Dialogs](https://mlsanity.com/paper/2112.00653/) (2021)
- [A Unified Framework for Slot based Response Generation in a Multimodal Dialogue System](https://mlsanity.com/paper/2305.17433/) (2023)
- [Mix-and-Match: Scalable Dialog Response Retrieval using Gaussian Mixture Embeddings](https://mlsanity.com/paper/2204.02710/) (2022)

## Abstract (arXiv)

Recent end-to-end task oriented dialog systems use memory architectures to incorporate external knowledge in their dialogs. Current work makes simplifying assumptions about the structure of the knowledge base, such as the use of triples to represent knowledge, and combines dialog utterances (context) as well as knowledge base (KB) results as part of the same memory. This causes an explosion in the memory size, and makes the reasoning over memory harder. In addition, such a memory design forces hierarchical properties of the data to be fit into a triple structure of memory. This requires the memory reader to infer relationships across otherwise connected attributes. In this paper we relax the strong assumptions made by existing architectures and separate memories used for modeling dialog context and KB results. Instead of using triples to store KB results, we introduce a novel multi-level memory architecture consisting of cells for each query and their corresponding results. The multi-level memory first addresses queries, followed by results and finally each key-value pair within a result. We conduct detailed experiments on three publicly available task oriented dialog data sets and we find that our method conclusively outperforms current state-of-the-art models. We report a 15-25% increase in both entity F1 and BLEU scores.