Slot Attention with Value Normalization for Multi-Domain Dialogue State Tracking

Wang, Yexiang; Guo, Yi; Zhu, Siqi

doi:10.18653/v1/2020.emnlp-main.243

Cited by 13 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sentiment shift detection arises from the sentiment coherence of dialogue, which aims to model the change of sentiment polarity between the current utterance and the previous utterance, and tries to establish the correlation between the change of sentiment polarity and semantics. Zhang et al [36] focused on emotional transitions in conversations, which gave us a lot of inspiration. Given a context C = {U 1 , U 2 , ..., U m }, for setting equal weight to all utterances, pseudo utterance U 0 is added to each dialogue.…”

Section: Sentiment Shift Detectionmentioning

confidence: 99%

Dialogue Sentiment Analysis Based on Dialogue Structure Pre-training

Yang,

Zeng

et al. 2024

Preprint

View full text Add to dashboard Cite

The task of dialogue sentiment analysis aims to identify the sentiment polarity of utterances in the context of a dialogue. Pre-trained models often struggle to capture the logical structure of a dialogue, making this task challenging. To address this issue, we propose a dialogue sentiment analysis framework that leverages pre-training on dialogue structure. Our proposed framework includes three sub-tasks for pre-training: utterance order sorting, sentence backbone regularization, and sentiment shift detection. These tasks are designed to improve the model's ability to mine dialogue logical relationships and sentiment interactions. By focusing on learning the logical structure of dialogues and the perception of sentiment interactions, our framework is able to improve the performance of pre-trained models on recognizing the sentiment polarity of dialogues. This is demonstrated by the convincing results obtained on the public MEISD dataset.

show abstract

Section: Sentiment Shift Detectionmentioning

confidence: 99%

Dialogue Sentiment Analysis Based on Dialogue Structure Pre-training

Yang,

Zeng

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…To conclude, the NLU module tries to tag the user message while the DST module tries to find values from the user message to fill in a pre-existing form. Some dialogue systems took the output of the NLU module as the input of DST module (Williams et al, 2013;Henderson et al, 2014a,b), while others directly used raw user messages to track the state (Kim et al, 2019;Wang et al, 2020e;Hu et al, 2020).…”

Section: Dialogue State Trackingmentioning

confidence: 99%

“…Thus, the tracker could copy slot values from the connected slots directly, alleviating the burden of reasoning and learning. Wang et al (2020e) proposed Value Normalization (VN) to convert supporting dialogue spans into state values and could achieve high accuracy with only 30% available ontology.…”

Section: Research Challenges and Hot Topicsmentioning

confidence: 99%

“…Ouyang et al (2020) used a slot connection mechanism to directly copy slot values from the source slot, which reduced the expense of reasoning. Hu et al (2020) and Wang et al (2020e) proposed slot attention to calculate the relations between the slot and dialogue context, thus only focusing on the relevant slots at each turn.…”

Section: Research Challenges and Hot Topicsmentioning

confidence: 99%

“…Furthermore, the slot values were predicted based on the retrieved information. Similarly,Wang et al (2020e) used BERT for slot value prediction. They performed Slot Attention (SA) to retrieve related spans and Value Normalization (VN) to convert the spans into final values.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey

Ni¹,

Young²,

Pandelea³

et al. 2021

Preprint

View full text Add to dashboard Cite

Dialogue systems are a popular Natural Language Processing (NLP) task as it is promising in real-life applications. It is also a complicated task since many NLP tasks deserving study are involved. As a result, a multitude of novel works on this task are carried out, and most of them are deep learning based due to the outstanding performance. In this survey, we mainly focus on the deep learning based dialogue systems. We comprehensively review state-of-the-art research outcomes in dialogue systems and analyze them from two angles: model type and system type. Specifically, from the angle of model type, we discuss the principles, characteristics, and applications of different models that are widely used in dialogue systems. This will help researchers acquaint these models and see how they are applied in state-of-the-art frameworks, which is rather helpful when designing a new dialogue system. From the angle of system type, we discuss task-oriented and open-domain dialogue systems as two streams of research, providing insight into the hot topics related. Furthermore, we comprehensively review the evaluation methods and datasets for dialogue systems to pave the way for future research. Finally, some possible research trends are identified based on the recent research outcomes. To the best of our knowledge, this survey is the most comprehensive and up-to-date one at present in the area of dialogue systems and dialogue-related tasks, extensively covering the popular frameworks, topics, and datasets 1 . * Equal contribution ‡ Corresponding author 1 The frameworks, topics, and datasets discussed are originated from the extensive literature review of state-of-the-art research. We have tried our best to cover all but may still omit some works. Readers are welcome to provide suggestions regarding the omissions and mistakes in this article. We also intend to update this article with time as and when new approaches or definitions are proposed and used by the community Preprint. Under review.

show abstract