Cascaded Span Extraction and Response Generation for Document-Grounded Dialog

Nico, Daheim,; Thulke, David; Dugast, Christian; Ney, Hermann

doi:10.18653/v1/2021.dialdoc-1.8

Cited by 4 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Baselines For knowledge identification, we compare UniGDD with several strong baselines, including BERTQA (Devlin et al, 2019), BERT-PR (Daheim et al, 2021), RoBERTa-PR (Daheim et al, 2021), Multi-Sentence (Wu et al, 2021), and DI-ALKI (Wu et al, 2021). These models formulate knowledge identification as the machine reading comprehension task and extract the grounding span from the document.…”

Section: Methodsmentioning

confidence: 99%

“…These models formulate knowledge identification as the machine reading comprehension task and extract the grounding span from the document. For response generation, we compare UniGDD with several pipeline methods, including DIALKI+BART (Wu et al, 2021) that uses DIALKI to conduct knowledge identification, followed by BART (Lewis et al, 2020) to conduct response generation and RoBERTa-PR+BART (Daheim et al, 2021). We also build a strong baseline model RoBERTa+T5 which uses the same pretrained generative model as ours.…”

Section: Methodsmentioning

confidence: 99%

“…Response generation then aims at generating a proper agent response according to the dialogue context and the selected knowledge. Therefore, one straightforward solution for this problem is to use two models to conduct KI and RG in a pipeline manner (Daheim et al, 2021;Kim et al, 2021;Xu et al, 2021;Chen et al, 2021;. However, such pipeline methods fail to capture the interdependence between KI and RG.…”

Section: Dialogue Contextmentioning

confidence: 99%

See 2 more Smart Citations

UniGDD: A Unified Generative Framework for Goal-Oriented Document-Grounded Dialogue

Gao¹,

Zhang²,

Lam³

2022

Preprint

View full text Add to dashboard Cite

The goal-oriented document-grounded dialogue aims at responding to the user query based on the dialogue context and supporting document. Existing studies tackle this problem by decomposing it into two sub-tasks: knowledge identification and response generation. However, such pipeline methods would unavoidably suffer from the error propagation issue. This paper proposes to unify these two sub-tasks via sequentially generating the grounding knowledge and the response. We further develop a prompt-connected multi-task learning strategy to model the characteristics and connections of different tasks and introduce linear temperature scheduling to reduce the negative effect of irrelevant document information. Experimental results demonstrate the effectiveness of our framework.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Dialogue Contextmentioning

confidence: 99%

See 1 more Smart Citation

UniGDD: A Unified Generative Framework for Goal-Oriented Document-Grounded Dialogue

Gao¹,

Zhang²,

Lam³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…For the generation, we use the noisy channel model instead of the RAG model. For a more detailed analysis of the effect of the RAG and Noisy Channel Model, we refer readers to Thulke et al [13] and Daheim et al [21].…”

Section: A Dstc9mentioning

confidence: 99%

Task-Oriented Document-Grounded Dialog Systems by HLTPR@RWTH for DSTC9 and DSTC10

Thulke

Nico

Dugast

et al. 2024

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

This paper summarizes our contributions to the document-grounded dialog tasks at the 9th and 10th Dialog System Technology Challenges (DSTC9 and DSTC10). In both iterations the task consists of three subtasks: first detect whether the current turn is knowledge seeking, second select a relevant knowledge document, and third generate a response grounded on the selected document. For DSTC9 we proposed different approaches to make the selection task more efficient. The best method, Hierarchical Selection, actually improves the results compared to the original baseline and gives a speedup of 24x. In the DSTC10 iteration of the task, the challenge was to adapt systems trained on written dialogs to perform well on noisy automatic speech recognition transcripts. Therefore, we proposed data augmentation techniques to increase the robustness of the models as well as methods to adapt the style of generated responses to fit well into the proceeding dialog. Additionally, we proposed a noisy channel model that allows for increasing the factuality of the generated responses. In addition to summarizing our previous contributions, in this work, we also report on a few small improvements and reconsider the automatic evaluation metrics for the generation task which have shown a low correlation to human judgments.

show abstract

“…In Doc2dial, for the task of knowledge identification, we compare CausalDD with several strong baselines, including UniGDD , BERTQA (Kenton and Toutanova, 2019), BERT-PR (Daheim et al, 2021), RoBERTa-PR (Daheim et al, 2021), Multi-Sentence (Wu et al, 2021), and DIALKI (Wu et al, 2021). The other models formulate knowledge identification as a machine reading comprehension task and extract the grounding span from the document.…”

Section: B2 Baselinesmentioning

confidence: 99%

Causal Document-Grounded Dialogue Pre-training

Zhao,

Yu,

et al. 2023

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

The goal of document-grounded dialogue (DocGD) is to generate a response by anchoring the evidence in a supporting document in accordance with the dialogue context. This entails four causally interconnected variables. While task-specific pre-training has significantly enhanced performances on numerous downstream tasks, existing DocGD methods still rely on general pre-trained language models without a specifically tailored pre-training approach that explicitly captures the causal relationships.To address this, we present the first causallycomplete dataset construction strategy for developing million-scale DocGD pre-training corpora. Additionally, we propose a causallyperturbed pre-training strategy to better capture causality by introducing perturbations on the variables and optimizing the overall causal effect. Experiments conducted on three benchmark datasets demonstrate that our causal pretraining yields substantial and consistent improvements in fully-supervised, low-resource, few-shot, and zero-shot settings 1 .

show abstract

Cascaded Span Extraction and Response Generation for Document-Grounded Dialog

Cited by 4 publications

References 12 publications

UniGDD: A Unified Generative Framework for Goal-Oriented Document-Grounded Dialogue

UniGDD: A Unified Generative Framework for Goal-Oriented Document-Grounded Dialogue

Task-Oriented Document-Grounded Dialog Systems by HLTPR@RWTH for DSTC9 and DSTC10

Causal Document-Grounded Dialogue Pre-training

Contact Info

Product

Resources

About