HyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge Management

Gao, Silin; Takanobu, Ryuichi; Peng, Wei; Liu, Qun; Huang, Minlie

doi:10.18653/v1/2021.findings-acl.139

Cited by 12 publications

(9 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It refers to pre-training large language models on text or task-related data and then fine-tuning on a few samples. Such systems have proved their success in task-oriented DS such as the work presented in [12][13][14][15][16][17][18][19][20][21][22].…”

Section: English Task Oriented Dialogue Systemsmentioning

confidence: 99%

AraConv: Developing an Arabic Task-Oriented Dialogue System Using Multi-Lingual Transformer Model mT5

Fuad

Al-Yahya

2022

Applied Sciences

View full text Add to dashboard Cite

Task-oriented dialogue systems (DS) are designed to help users perform daily activities using natural language. Task-oriented DS for English language have demonstrated promising performance outcomes; however, developing such systems to support Arabic remains a challenge. This challenge is mainly due to the lack of Arabic dialogue datasets. This study introduces the first Arabic end-to-end generative model for task-oriented DS (AraConv), which uses the multi-lingual transformer model mT5 with different settings. We also present an Arabic dialogue dataset (Arabic-TOD) and used it to train and test the proposed AraConv model. The results obtained are reasonable compared to those reported in the studies of English and Chinese using the same mono-lingual settings. To avoid problems associated with a small training dataset and to improve the AraConv model’s results, we suggest joint-training, in which the model is jointly trained on Arabic dialogue data and data from one or two high-resource languages such as English and Chinese. The findings indicate the AraConv model performed better in the joint-training setting than in the mono-lingual setting. The results obtained from AraConv on the Arabic dialogue dataset provide a baseline for other researchers to build robust end-to-end Arabic task-oriented DS that can engage with complex scenarios.

show abstract

Section: English Task Oriented Dialogue Systemsmentioning

confidence: 99%

AraConv: Developing an Arabic Task-Oriented Dialogue System Using Multi-Lingual Transformer Model mT5

Fuad

Al-Yahya

2022

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…The DSTC10 task 2 (Kim et al, 2021) is based on the dataset from (Kim et al, 2020) with a similar focus. HyKnow (Gao et al, 2021) also proposes to insert turns into TOD grounded on knowledge from unstructured documents. These datasets focus on the challenge of detecting those turns requiring external knowledge and selecting the knowledge to generate the responses.…”

Section: Related Workmentioning

confidence: 99%

KETOD: Knowledge-Enriched Task-Oriented Dialogue

Chen¹,

Liu²,

Moon³

et al. 2022

Preprint

View full text Add to dashboard Cite

Existing studies in dialogue system research mostly treat task-oriented dialogue and chitchat as separate domains. Towards building a human-like assistant that can converse naturally and seamlessly with users, it is important to build a dialogue system that conducts both types of conversations effectively. In this work, we investigate how task-oriented dialogue and knowledge-grounded chit-chat can be effectively integrated into a single model. To this end, we create a new dataset, KETOD (Knowledge-Enriched Task-Oriented Dialogue), where we naturally enrich taskoriented dialogues with chit-chat based on relevant entity knowledge. We also propose two new models, SimpleToDPlus and Combiner, for the proposed task. Experimental results on both automatic and human evaluations show that the proposed methods can significantly improve the performance in knowledge-enriched response generation while maintaining a competitive task-oriented dialog performance. We believe our new dataset will be a valuable resource for future studies. Our dataset and code are publicly available 1 . * Work done as a research intern at Meta. 1 https://github.com/facebookresearch/ ketod) I would like to see a Musical show. system user I would like to find an event around SD. What type of event do you prefer? KETOD Alejandro Sanz is at Cal Coast Credit Union Amphitheater on March 7th at 7:30 pm. He is known for flamenco-influenced ballads, but experiments with other genres too, it's sure to be a good show! Knowledge from Wikipedia Alejandro Sánchez Pizarro, better known as Alejandro Sanz born December 18, 1968), is a Spanish musician, singer and composer. … The singer is notable for his flamenco-influenced ballads, and has also experimented with several other genres including pop, rock, funk, R&B and jazz.system user

show abstract

“…Among these works, SimpleTOD (Hosseini-Asl et al, 2020), SOLOIST (Peng et al, 2020), and UBAR attempt to concatenate the dialog history, user utterance, belief state, dialog act, and system response into a long sequence, which is then modeled by a sequence-to-sequence generation model. HyKnow (Gao et al, 2021) extends the belief state to handle both structured and unstructured knowledge and trains the dialog state tracking and response generation modules jointly. Nevertheless, these systems are not the end-to-end solutions we pursue in this work since they still need intermediate annotations.…”

Section: Related Workmentioning

confidence: 99%

Autoregressive Entity Generation for End-to-End Task-Oriented Dialog

Huang¹,

Wang²

2022

Preprint

View full text Add to dashboard Cite

Task-oriented dialog (TOD) systems often require interaction with an external knowledge base to retrieve necessary entity (e.g., restaurant) information to support the response generation. Most current end-to-end TOD systems either retrieve the KB information explicitly or embed it into model parameters for implicit access. While the former approach demands scanning the KB at each turn of response generation, which is inefficient when the KB scales up, the latter approach shows higher flexibility and efficiency. In either approach, the systems may generate a response with conflicting entity information. To address this issue, we propose to generate the entity autoregressively first and leverage it to guide the response generation in an end-to-end system. To ensure entity consistency, we impose a trie constraint on entity generation. We also introduce a logit concatenation strategy to facilitate gradient backpropagation for end-to-end training. Experiments on MultiWOZ 2.1 single and CAMREST show that our system can generate more high-quality and entity-consistent responses.

show abstract

HyKnow: End-to-End Task-Oriented Dialog Modeling with Hybrid Knowledge Management

Cited by 12 publications

References 25 publications

AraConv: Developing an Arabic Task-Oriented Dialogue System Using Multi-Lingual Transformer Model mT5

AraConv: Developing an Arabic Task-Oriented Dialogue System Using Multi-Lingual Transformer Model mT5

KETOD: Knowledge-Enriched Task-Oriented Dialogue

Autoregressive Entity Generation for End-to-End Task-Oriented Dialog

Contact Info

Product

Resources

About