Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking

Lin, Weizhe; Tseng, Bo-Hsiang; Byrne, Bill

doi:10.18653/v1/2021.emnlp-main.620

Cited by 22 publications

(13 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another benefit of using pretrained GPT2 is faster training time as we observed the VDTN+GPT2 converged much earlier than training it from scratch. From these observations, we are excited to see more future extension of SOTA unimodal DST models (Lin et al, 2021;Dai et al, 2021) and large pretrained LMs (Brown et al, 2020;Raffel et al, 2020), especially ones with multimodal learning such as (Lu et al, 2019;, to MM-DST task.…”

Section: Resultsmentioning

confidence: 99%

Multimodal Dialogue State Tracking

Lê¹,

Chen²,

Hoi³

2022

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

Designed for tracking user goals in dialogues, a dialogue state tracker is an essential component in a dialogue system. However, the research of dialogue state tracking has largely been limited to unimodality, in which slots and slot values are limited by knowledge domains (e.g. restaurant domain with slots of restaurant name and price range) and are defined by specific database schema. In this paper, we propose to extend the definition of dialogue state tracking to multimodality. Specifically, we introduce a novel dialogue state tracking task to track the information of visual objects that are mentioned in video-grounded dialogues. Each new dialogue utterance may introduce a new video segment, new visual objects, or new object attributes and a state tracker is required to update these information slots accordingly. We created a new synthetic benchmark and designed a novel baseline, Video-Dialogue Transformer Network (VDTN), for this task. VDTN combines both object-level features and segment-level features and learns contextual dependencies between videos and dialogues to generate multimodal dialogue states. We optimized VDTN for a state generation task as well as a self-supervised video understanding task which recovers video segment or object representations. Finally, we trained VDTN to use the decoded states in a response prediction task. Together with comprehensive ablation and qualitative analysis, we discovered interesting insights towards building more capable multimodal dialogue systems. Dialogue HUMAN: I am looking for a cheap restaurant in the centre of the city.Dialogue State PRICE = cheap AREA = centre Database NAME PRICE AREA FOOD CHOICE Pizza centre cheap centre italian JP house cheap centre japanese Pizza express moderate west italian Rice house expensive east chinese

show abstract

Section: Resultsmentioning

confidence: 99%

Multimodal Dialogue State Tracking

Lê¹,

Chen²,

Hoi³

2022

Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

show abstract

“…In a multi-domain dialog, slots from different domains can be correlated. The slot relationships can be modeled implicitly through self-attention or graph neural networks (Kim et al, 2020;Ye et al, 2021;Lin et al, 2021a), or explicitly through copy mechanism or a schema graph that encodes prior knowledge (Heck et al, 2020;Jiao et al, 2022;Feng et al, 2022). However, all of these methods are driven by multi-domain data.…”

Section: Multi-domain Dialog State Trackingmentioning

confidence: 99%

Building Multi-domain Dialog State Trackers from Single-domain Dialogs

Zhu,

Zhang,

Zhu

et al. 2023

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

View full text Add to dashboard Cite

Existing multi-domain dialog state tracking (DST) models are developed based on multidomain dialogs, which require significant manual effort to define domain relations and collect data. This process can be challenging and expensive, particularly when numerous domains are involved. In this paper, we propose a divide-and-conquer (DAC) DST paradigm and a multi-domain dialog synthesis framework, which makes building multi-domain DST models from single-domain dialogs possible. The DAC paradigm segments a multi-domain dialog into multiple single-domain dialogs for DST, which makes models generalize better on dialogs involving unseen domain combinations. The multi-domain dialog synthesis framework merges several potentially related single-domain dialogs into one multi-domain dialog and modifies the dialog to simulate domain relations. The synthesized dialogs can help DST models capture the value transfer between domains. Experiments with three representative DST models on two datasets demonstrate the effectiveness of our proposed DAC paradigm and data synthesis framework.

show abstract

“…In addition, we observe that the complete states of the dialogue session are updated at turn-8, while turn-9 and turn-10 simply show humans' politeness and respect without introducing any new domain-slots. Therefore, while the "last turn" has been studied before (Lin et al, 2021a), it is often not the case that only the last turn of a dialogue session generates summary states. Using redundant turns such as turn-9 and turn-10 for training not only requires additional labelling but also possibly distracts the DST model since it introduces irrelevant context information, thus hindering the overall performance .…”

Section: Will You Need Any Thing Else Now?mentioning

confidence: 99%

Turn-Level Active Learning for Dialogue State Tracking

Zhang,

Fang,

et al. 2023

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

View full text Add to dashboard Cite

Dialogue state tracking (DST) plays an important role in task-oriented dialogue systems. However, collecting a large amount of turnby-turn annotated dialogue data is costly and inefficient. In this paper, we propose a novel turn-level active learning framework for DST to actively select turns in dialogues to annotate. Given the limited labelling budget, experimental results demonstrate the effectiveness of selective annotation of dialogue turns. Additionally, our approach can effectively achieve comparable DST performance to traditional training approaches with significantly less annotated data, which provides a more efficient way to annotate new dialogue data 1 .

show abstract

Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State Tracking

Cited by 22 publications

References 4 publications

Multimodal Dialogue State Tracking

Multimodal Dialogue State Tracking

Building Multi-domain Dialog State Trackers from Single-domain Dialogs

Turn-Level Active Learning for Dialogue State Tracking

Contact Info

Product

Resources

About