Low-Resource Knowledge-Grounded Dialogue Generation
By Xueliang Zhao, Wei Wu, Chongyang Tao, Can Xu, Dongyan Zhao, Rui Yan. 2020
117 citations recorded by the source corpus.
Responding with knowledge has been recognized as an important capability for an intelligent conversational agent. Yet knowledge-grounded dialogues, as training data for learning such a response generation model, are difficult to obtain. Motivated by the challenge in practice, we consider knowledge-grounded dialogue generation under a natural assumption that only limited training examples are available. In such a low-resource setting, we devise a disentangled response decoder in order to isolate parameters that depend on knowledge-grounded dialogues from the entire generation model. By this means, the major part of the model can be learned from a large number of ungrounded dialogues and unstructured documents, while the remaining small parameters can be well fitted using the limited training examples. Evaluation results on two benchmarks indicate that with only $1/8$ training data, our model can achieve the state-of-the-art performance and generalize well on out-of-domain knowledge.
Subfields: Artificial Intelligence, Dialogue & Conversational AI, Natural Language Generation
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Dialogue & Conversational AI
In Natural Language Generation
- Dan Su
- Ruslan Salakhutdinov
- Alan W. Black
- Minlie Huang
- Shrimai Prabhumoye
- Heiga Zen
- Junichi Yamagishi
Citations in the corpus
- Case Study: Deontological Ethics in NLP (2020, background): “, 1998), style (Niu and Bansal, 2018), content (Zhou et al., 2018; Zhao et al., 2020; Dinan et al., 2019) and persona (Zhang et al.”
- Are Pre-trained Language Models Knowledgeable to Ground Open Domain Dialogues? (2020, methodology): “Besides Transformer Memory Network (TMN) (Dinan et al., 2019) and Disentangled Response Decoder (DRD) (Zhao et al., 2020), we also compare the pre-trained models with Incremental Transformer with Deliberation Decoder (ITDD) (Li et al., 2019) and Posterior Knowledge Selection (PostKS) (Lian et al., 2”
- Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters (2021, methodology): “2019); (ii) DRD (Zhao et al. 2019) intends to combat in a low-resource setting with pre-training techniques; (iii) ZRGKG (Li et al.”
- Knowledge-Grounded Dialogue Generation with Pre-trained Language Models (2020, methodology): “…Transformer (SKT): a sequential latent variable model with state-of-the-art performance on knowledge selection published in a very recent paper (Kim et al., 2020 Disentangled Response Decoder (DRD): a model that tackles the low-resource challenge with pre-training techniques (Zhao et al., 2020).”
- Exploring Prompt-based Few-shot Learning for Grounded Dialog Generation (2021, methodology): “Unigram F1 (Dinan et al., 2018; Zhao et al., 2020) measures the lexical similarity between generated and golden responses (with NLTK tokenization).”
- Knowledge-Grounded Dialogue Generation with Term-level De-noising (2021, background): “…techniques that use knowledge, in addition to the original posts, to improve the quality of the generated responses (Ghazvinine-jad et al. (2018), Moghe et al. (2018), Dinan et al. (2019), Galley et al. (2019), Lian et al. (2019), Zheng and Zhou (2019), Zhao et al. (2020a), Zhao et al. (2020b)).”