End-to-End Task-Oriented Dialog Modeling With Semi-Structured Knowledge Management

Gao, Silin; Takanobu, Ryuichi; Huang, Minlie

doi:10.1109/taslp.2022.3153255

Cited by 5 publications

(11 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…TripPy-R (Heck et al, 2022) for DST with task names as prompts. SeKnow-PLM (Gao et al, 2022) improves dialogue modeling grounded on semi-structured knowledge. DiS-TRICT (Venkateswaran et al, 2022) utilizes retrieved in-context examples to fine-tune the language model.…”

Section: Baselinementioning

confidence: 99%

Act-Aware Slot-Value Predicting in Multi-Domain Dialogue State Tracking

Su¹,

Wu²,

Juang³

2021

Interspeech 2021

View full text Add to dashboard Cite

Tracking dialogue states is an essential topic in task-oriented dialogue systems, which involve filling in the necessary information in pre-defined slots corresponding to a schema. While general pre-trained language models have been shown effective in slot-filling, their performance is limited when applied to specific domains. We propose a graph-based framework that learns domain-specific prompts by incorporating the dialogue schema. Specifically, we embed domain-specific schema encoded by a graph neural network into the pretrained language model, which allows for relations in the schema to guide the model for better adaptation to the specific domain. Our experiments demonstrate that the proposed graphbased method outperforms other multi-domain DST approaches while using similar or fewer trainable parameters. We also conduct a comprehensive study of schema graph architectures, parameter usage, and module ablation that demonstrate the effectiveness of our model on multi-domain dialogue state tracking.

show abstract

Section: Baselinementioning

confidence: 99%

Act-Aware Slot-Value Predicting in Multi-Domain Dialogue State Tracking

Su¹,

Wu²,

Juang³

2021

Interspeech 2021

View full text Add to dashboard Cite

show abstract

“…Thus, typical task-oriented dialog systems require generating a belief state, that can be used to query a knowledge base to fetch entity results; these results are then used to generate responses. Recognizing that information is not always present in structured resources, recently methods that can additionally use unstructured knowledge (eg: document collections), have also been developed (Kim et al, 2020;Gao et al, 2021a). However, current state-of-the-art models designed for such tasks make limiting assumptions about the nature of knowledge sources, that make them unsuitable for use in real-world settings.…”

Section: Introductionmentioning

confidence: 99%

“…However, relevant information required to generate responses may also reside in unstructured sources, such as documents. Recent state of the art models such as HyKnow (Gao et al, 2021b) and SEKNOW (Gao et al, 2021a) aimed at overcoming these challenges make limiting assumptions about the knowledge sources. For instance, these systems assume that certain types of information, such as a phone number, is always present in a structured knowledge base (KB) while information about aspects such as entrance ticket prices, would always be available in documents.In this paper, we create a modified version of the MutliWOZ-based dataset prepared by (Gao et al, 2021a) to demonstrate how current methods have significant degradation in performance when strict assumptions about the source of information are removed.…”

mentioning

confidence: 99%

“…Recent state of the art models such as HyKnow (Gao et al, 2021b) and SEKNOW (Gao et al, 2021a) aimed at overcoming these challenges make limiting assumptions about the knowledge sources. For instance, these systems assume that certain types of information, such as a phone number, is always present in a structured knowledge base (KB) while information about aspects such as entrance ticket prices, would always be available in documents.In this paper, we create a modified version of the MutliWOZ-based dataset prepared by (Gao et al, 2021a) to demonstrate how current methods have significant degradation in performance when strict assumptions about the source of information are removed. Then, in line with recent work exploiting pre-trained language models, we fine-tune a BART (Lewis et al, 2020) based model using prompts (Brown et al, 2020; for the tasks of querying knowledge sources, as well as, for response generation, without making assumptions about the information present in each knowledge source.…”

mentioning

confidence: 99%

“…In this paper, we create a modified version of the MutliWOZ-based dataset prepared by (Gao et al, 2021a) to demonstrate how current methods have significant degradation in performance when strict assumptions about the source of information are removed. Then, in line with recent work exploiting pre-trained language models, we fine-tune a BART (Lewis et al, 2020) based model using prompts (Brown et al, 2020; for the tasks of querying knowledge sources, as well as, for response generation, without making assumptions about the information present in each knowledge source.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Joint Reasoning on Hybrid-knowledge sources for Task-Oriented Dialog

Mishra,

Contractor,

Raghu

2023

Findings of the Association for Computational Linguistics: EACL 2023

View full text Add to dashboard Cite

Traditional systems designed for task oriented dialog utilize knowledge present only in structured knowledge sources to generate responses. However, relevant information required to generate responses may also reside in unstructured sources, such as documents. Recent state of the art models such as HyKnow (Gao et al., 2021b) and SEKNOW (Gao et al., 2021a) aimed at overcoming these challenges make limiting assumptions about the knowledge sources. For instance, these systems assume that certain types of information, such as a phone number, is always present in a structured knowledge base (KB) while information about aspects such as entrance ticket prices, would always be available in documents.In this paper, we create a modified version of the MutliWOZ-based dataset prepared by (Gao et al., 2021a) to demonstrate how current methods have significant degradation in performance when strict assumptions about the source of information are removed. Then, in line with recent work exploiting pre-trained language models, we fine-tune a BART (Lewis et al., 2020) based model using prompts (Brown et al., 2020; for the tasks of querying knowledge sources, as well as, for response generation, without making assumptions about the information present in each knowledge source. Through a series of experiments, we demonstrate that our model is robust to perturbations to knowledge modality (source of information), and that it can fuse information from structured as well as unstructured knowledge to generate responses.

show abstract

OPERA: Harmonizing Task-Oriented Dialogs and Information Seeking Experience

Li,

Peng,

Gao

et al. 2024

ACM Trans. Web

View full text Add to dashboard Cite

Existing studies in conversational AI mostly treat task-oriented dialog (TOD) and question answering (QA) as separate tasks. Towards the goal of constructing a conversational agent that can complete user tasks and support information seeking, it is important to develop a system that can handle both TOD and QA with access to various external knowledge sources. In this work, we propose a new task, Open-Book TOD (OB-TOD), which combines TOD with QA and expands the external knowledge sources to include both explicit sources (e.g., the web) and implicit sources (e.g., pre-trained language models). We create a new dataset OB-MultiWOZ, where we enrich TOD sessions with QA-like information-seeking experience grounded on external knowledge. We propose a unified model OPERA ( Op en-book E nd-to-end Task-o r iented Di a log) which can appropriately access explicit and implicit external knowledge to tackle the OB-TOD task. Experimental results show that OPERA outperforms closed-book baselines, highlighting the value of both types of knowledge.

show abstract

End-to-End Task-Oriented Dialog Modeling With Semi-Structured Knowledge Management

Cited by 5 publications

References 42 publications

Act-Aware Slot-Value Predicting in Multi-Domain Dialogue State Tracking

Act-Aware Slot-Value Predicting in Multi-Domain Dialogue State Tracking

Joint Reasoning on Hybrid-knowledge sources for Task-Oriented Dialog

OPERA: Harmonizing Task-Oriented Dialogs and Information Seeking Experience

Contact Info

Product

Resources

About