Fg2seq: Effectively Encoding Knowledge for End-To-End Task-Oriented Dialog

He, Zhenhao; He, Yuhong; Wu, Qingyao; Chen, Jian

doi:10.1109/icassp40776.2020.9053667

Cited by 17 publications

(21 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Baselines: We compare CDNET against the following baselines: MLM (Reddy et al, 2019), DSR , GLMP , Entity Consistent (Qin et al, 2019), EER (He et al, 2020c), FG2Seq (He et al, 2020b), TTOS (He et al, 2020a) and DFNet (Qin et al, 2020).…”

Section: Methodsmentioning

confidence: 99%

“…We now briefly discuss approaches that improve other aspects of task oriented dialogs. He et al (2020c) and He et al (2020b) model KBs using Relational GCNs (Schlichtkrull et al, 2018). provide support for entities unseen during train.…”

Section: Related Workmentioning

confidence: 99%

“…To satisfy a user goal, the system is expected to retrieve necessary information from a knowledge base and convey it using natural language. Recently several end-to-end approaches (Bordes and Weston, 2017;He et al, 2020b;Madotto et al, 2018) have been proposed for learning these dialog systems.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Constraint based Knowledge Base Distillation in End-to-End Task Oriented Dialogs

Raghu¹,

Jain²,

Joshi³

2021

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

View full text Add to dashboard Cite

End-to-End task-oriented dialogue systems generate responses based on dialog history and an accompanying knowledge base (KB). Inferring those KB entities that are most relevant for an utterance is crucial for response generation. Existing state of the art scales to large KBs by softly filtering over irrelevant KB information. In this paper, we propose a novel filtering technique that consists of (1) a pairwise similarity based filter that identifies relevant information by respecting the n-ary structure in a KB record. and, (2) an auxiliary loss that helps in separating contextually unrelated KB information. We also propose a new metric -multiset entity F1 which fixes a correctness issue in the existing entity F1 metric. Experimental results on three publicly available task-oriented dialog datasets show that our proposed approach outperforms existing state-ofthe-art models.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Constraint based Knowledge Base Distillation in End-to-End Task Oriented Dialogs

Raghu¹,

Jain²,

Joshi³

2021

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

View full text Add to dashboard Cite

show abstract

“…In [18], relations in semantic knowledge graphs have been used for inferring answers in question answering dialogues.…”

Section: Related Workmentioning

confidence: 99%

End2End Acoustic to Semantic Transduction

Pelloin

Camelin

Laurent

et al. 2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

In this paper, we propose a novel end-to-end sequence-tosequence spoken language understanding model using an attention mechanism. It reliably selects contextual acoustic features in order to hypothesize semantic contents. An initial architecture capable of extracting all pronounced words and concepts from acoustic spans is designed and tested. With a shallow fusion language model, this system reaches a 13.6 concept error rate (CER) and an 18.5 concept value error rate (CVER) on the French MEDIA corpus, achieving an absolute 2.8 points reduction compared to the state-of-the-art. Then, an original model is proposed for hypothesizing concepts and their values. This transduction reaches a 15.4 CER and a 21.6 CVER without any new type of context.

show abstract

“…Dialogue Systems are categorized into chit-chat (Vinyals and Le, 2015;Serban et al, 2016) and task-oriented (Williams and Young, 2007;Young et al, 2013); in this paper we focus on the latter. Task-oriented dialogue systems are further classified into: modularized (Levin et al, 2000;Hori et al, 2009;Lee et al, 2009), retrieval (Henderson et al, 2019; end-to-end (Bordes and Weston, 2017;Eric et al, 2017a;Eric and Manning, 2017;Madotto et al, 2018;Madotto et al, 2020a;Neelakantan et al, 2019;He et al, 2020) and hybrid (Shu et al, 2018;Lei et al, 2018;Zhang et al, 2019a;Mehri et al, 2019;Peng et al, 2020a;Ham et al, 2020;Hosseini-Asl et al, 2020;Le et al, 2020;Lin et al, 2020). To the best of our knowledge, these methods use either DST/S-ACT annotations, template responses, or all/partial KB as the input to the model, where instead we only use the dialogue history.…”

Section: Related Workmentioning

confidence: 99%

Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems

Madotto¹,

Cahyawijaya²,

Winata³

et al. 2020

Findings of the Association for Computational Linguistics: EMNLP 2020

View full text Add to dashboard Cite

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. Endto-end systems 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 finetuning. We evaluate our solution in five taskoriented 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 1 .

show abstract

Fg2seq: Effectively Encoding Knowledge for End-To-End Task-Oriented Dialog

Cited by 17 publications

References 13 publications

Constraint based Knowledge Base Distillation in End-to-End Task Oriented Dialogs

Constraint based Knowledge Base Distillation in End-to-End Task Oriented Dialogs

End2End Acoustic to Semantic Transduction

Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems

Contact Info

Product

Resources

About