ACL Findings2023
Value type: the bridge to a better DST model
QiXiang Gao, Mingyang Sun, Yutao Mou, Chen Zeng, Weiran Xu
Abstract
Value type of the slots can provide lots of useful information for DST tasks. However, it has been ignored in most previous works. In this paper, we propose a new framework for DST task based on these value types. Firstly, we extract the type of token from each turn. Specifically, we divide the slots in the dataset into 9 categories according to the type of slot value, and then train a Ner model to extract the corresponding type-entity from each turn of conversation according to the token. Secondly, we improve the attention mode which is integrated into value type information between the slot and the conversation history to help each slot pay more attention to the turns that contain the same value type. Meanwhile, we introduce a sampling strategy to integrate these types into the attention formula, which decrease the error of Ner model. Finally, we conduct a comprehensive experiment on two multi-domain taskoriented conversation datasets, MultiWOZ 2.1 and MultiWOZ 2.4. The ablation experimental results show that our method is effective on both datasets, which verify the necessity of considering the type of slot value.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
Builds on7
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
- Unified Named Entity Recognition as Word-Word Relation ClassificationJingye Li, Hao Fei, Jiang Liu, Shengqiong Wu et al.AAAI 2022 · 340 citations
- Efficient Dialogue State Tracking by Selectively Overwriting MemorySungdong Kim, Sohee Yang, Gyuwan Kim, Sang-Woo LeeACL 2020 · 189 citations
- Schema-Guided Multi-Domain Dialogue State Tracking with Graph Attention Neural NetworksLu Chen, Boer Lv, Chi Wang, Su Zhu et al.AAAI 2020 · 143 citations
- MA-DST: Multi-Attention-Based Scalable Dialog State TrackingAdarsh Kumar, Peter Ku, Anuj Kumar Goyal, Angeliki Metallinou et al.AAAI 2020 · 61 citations
Related papers
- Multi-Domain Dialogue State Tracking with Disentangled Domain-Slot AttentionLongfei Yang, Jiyi Li, Sheng Li, Takahiro ShinozakiACL Findings 2023 · 5 citations
- A Contextual Hierarchical Attention Network with Adaptive Objective for Dialogue State TrackingYong Shan, Zekang Li, Jinchao Zhang, Fandong Meng et al.ACL 2020 · 58 citations
- Knowledge-Aware Graph-Enhanced GPT-2 for Dialogue State TrackingWeizhe Lin, Bo-Hsiang Tseng, Bill ByrneEMNLP 2021 · 3 citations
- Slot Self-Attentive Dialogue State TrackingFanghua Ye, Jarana Manotumruksa, Qiang Zhang, Shenghui Li et al.WWW 2021 · 68 citations
- Non-Autoregressive Dialog State TrackingHung Le, Richard Socher, Steven C. H. HoiICLR 2020 · 54 citations
