Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems
By Andrea Madotto, Samuel Cahyawijaya, Genta Indra Winata, Yan Xu, Zihan Liu, Zhaojiang Lin, Pascale Fung. 2020
72 citations recorded by the source corpus.
Task-oriented dialogue systems are either modularized with separate dialogue state tracking (DST) and management steps or end-to-end trainable. In either case, the knowledge base (KB) plays an essential role in fulfilling user requests. Modularized systems rely on DST to interact with the KB, which is expensive in terms of annotation and inference time. End-to-end systems, instead, use the KB directly as input, but they cannot scale when the KB is larger than a few hundred entries. In this paper, we propose a method to embed the KB, of any size, directly into the model parameters. The resulting model does not require any DST or template responses, nor the KB as input, and it can dynamically update its KB via fine-tuning. We evaluate our solution in five task-oriented dialogue datasets with small, medium, and large KB size. Our experiments show that end-to-end models can effectively embed knowledge bases in their parameters and achieve competitive performance in all evaluated datasets.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Andrea Madotto
- Zhaojiang Lin
- Genta Indra Winata
- Pascale Fung
- Zihan Liu
- Nouha Dziri
- Etsuko Ishii
- Yan Xu
Citations in the corpus
- Language Models are Few-shot Multilingual Learners (2021, methodology): “We construct the inference for the multi-class prediction setup by extending the idea from Madotto et al. (2020b) of applying multiple binary predictions on each class.”
- Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding (2021, methodology): “Throughout our experiments, we rely on three representative baselines: GPT2KG, AdapterBot (Lin et al., 2020), and GPT2-KE (Madotto et al., 2020).”
- Contextualize Knowledge Bases with Transformer for End-to-end Task-Oriented Dialogue Systems (2020, unknown): “(Madotto et al., 2020a) directly embeds the KB into the parameters of GPT-2 (Radford et al.”
- Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters (2021, methodology): “For task-oriented dialogue systems, Madotto et al. (2020) stores the knowledge bases (KBs) with different sizes directly into the model parameters by aligning auto-extracted dialogue templates with the corresponding KBs for each data sample.”