A Survey of Document Grounded Dialogue Systems (DGDS)

Ma, Longxuan; Zhang, Weinan; Li, Mingda; Liu, Ting

doi:10.48550/arxiv.2004.13818

Cited by 4 publications

(3 citation statements)

References 98 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Goal-oriented dialogue generation grounded in documents is a challenging and realistic task (Ma et al, 2020;. Researchers have increasingly utilized documents in a more flexible manner to improve the fluency and informativeness of model-generated responses, including in tasks such as Machine Reading Comprehension, Convention Question Answering, and the focus of this paper, DocGD.…”

Section: Document-grounded Dialoguementioning

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

Section: Document-grounded Dialoguementioning

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

show abstract

“…Yatskar [29] designed a model which firstly makes a three classification prediction (yes/no/span) and outputs an answer span only if Yes/No is not selected. On top of that, there are also many studies concentrating on the conversational sentiment analysis area [30] and dialogue systems with commonsense [31] or audio contexts [32]. Though these branches also lay on the multi-document, the goal is to generate conversational situations between humans and machines.…”

Section: Related Workmentioning

confidence: 99%

Incorporating Phrases in Latent Query Reformulation for Multi-Hop Question Answering

Tang

Chen

et al. 2022

Mathematics

View full text Add to dashboard Cite

In multi-hop question answering (MH-QA), the machine needs to infer the answer to a given question from multiple documents. Existing models usually apply entities as basic units in the reasoning path. Then they use relevant entities (in the same sentence or document) to expand the path and update the information of these entities to finish the QA. The process might add an entity irrelevant to the answer to the graph and then lead to incorrect predictions. It is further observed that state-of-the-art methods are susceptible to reasoning chains that pivot on compound entities. To make up the deficiency, we present a viable solution, i.e., incorporate phrases in the latent query reformulation method (IP-LQR), which incorporates phrases in the latent query reformulation to improve the cognitive ability of the proposed method for multi-hop question answering. Specifically, IP-LQR utilizes information from relevant contexts to reformulate the question in the semantic space. Then the updated query representations interact with contexts within which the answer is hidden. We also design a semantic-augmented fusion method based on the phrase graph, which is then used to propagate the information. IP-LQR is empirically evaluated on a popular MH-QA benchmark, HotpotQA, and the results of IP-LQR consistently outperform those of the state of the art, verifying its superiority. In summary, by incorporating phrases in the latent query reformulation and employing semantic-augmented embedding fusion, our proposed model can lead to better performance on MH-QA.

show abstract

“…However, most authentic dialog scenarios consist of more than one purpose, which makes recent studies introduce external unstructured or structured knowledge [24] to generate more informative responses for various conversational purposes. Some studies [25] have proved that it is more reasonable to divide dialog systems by background knowledge to reflect the dialog tasks and datasets. Lian et al used external knowledge to build an end-to-end neural network for single-turn dialog generation [26].…”

Section: Related Workmentioning

confidence: 99%

Modeling hierarchical attention interaction between contexts and triple-channel encoding networks for document-grounded dialog generation

2022

View full text Add to dashboard Cite

Dialog systems have attracted attention as they are promising in many intelligent applications. Generating fluent and informative responses is of critical importance for dialog systems. Some recent studies introduce documents as extra knowledge to improve the performance of dialog generation. However, it is hard to understand the unstructured document and extract crucial information related to dialog history and current utterance. This leads to uninformative and inflexible responses in existing studies. To address this issue, we propose a generative model of a neural network with an attention mechanism for document-grounded multi-turn dialog. This model encodes the context of utterances that contains the given document, dialog history, and the last utterance into distributed representations via a triple-channel. Then, it introduces a hierarchical attention interaction between dialog contexts and previously generated utterances into the decoder for generating an appropriate response. We compare our model with various baselines on dataset CMU_DoG in terms of the evaluation criteria. The experimental results demonstrate the state-of-the-art performance of our model as compared to previous studies. Furthermore, the results of ablation experiments show the effectiveness of the hierarchical attention interaction and the triple channel for encoding. We also conduct human judgment to evaluate the informativeness of responses and the consistency of responses with dialog history.

show abstract

A Survey of Document Grounded Dialogue Systems (DGDS)

Cited by 4 publications

References 98 publications

Causal Document-Grounded Dialogue Pre-training

Causal Document-Grounded Dialogue Pre-training

Incorporating Phrases in Latent Query Reformulation for Multi-Hop Question Answering

Modeling hierarchical attention interaction between contexts and triple-channel encoding networks for document-grounded dialog generation

Contact Info

Product

Resources

About