Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userHi-DST: A Hierarchical Approach for Scalable and Extensible Dialogue State Tracking
مرحبا DST: نهج هرمي لتتبع حالة الحوار القابلة للتوسيع والمستجل
305
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تعد تتبع ولاية الحوار (DST) مهمة فرعية لأنظمة الحوار القائمة على المهام حيث يتم تتبع نية المستخدم من خلال ثلاثة أضعاف ثلاثة ثلاث مرات يمكن أن يكون من الصعب تمديد طرازات DST الحالية لمجموعات بيانات جديدة مع مجالات / فتحات أكبر ترجع أساسا إلى أي من السببين - 1) تنبؤ فتحة المجال كزوج، والثاني) تبعية المعلمات النموذجية على عدد الفتحات والمجالات وبعد في هذا العمل، نقترح معالجة هذه المشكلات باستخدام نموذج DST الهرمي (Hi-DS). بدور معين، يكتشف النموذج أولا تغيير في المجال متبوعا بتنبؤ المجال إذا لزم الأمر. ثم تقرر إجراء مناسب لكل فتحة في المجالات المتوقعة ويجد قيمتها وفقا لذلك. المعلمات النموذجية ل HI-DST مستقلة عن عدد المجالات / الفتحات. نظرا للنمذجة الهرمية، فإنه يحقق O (| M | + | N |) تنبؤ الدولة المعتقد بدوره واحد حيث M و N هي مجموعة من المجالات الفريدة والفتحات على التوالي. نقول أن الهيكل الهرمي يساعد في نموذج الشرح ويجعله قابل للتوسيع بسهولة إلى مجموعات بيانات جديدة. تشير التجارب في مجموعة بيانات MultiWoz إلى أن نموذجنا المقترح يحقق أداء دقة مشتركة قابلة للمقارنة بنماذج DST الحديثة.
Dialogue State Tracking (DST) is a sub-task of task-based dialogue systems where the user intention is tracked through a set of (domain, slot, slot-value) triplets. Existing DST models can be difficult to extend for new datasets with larger domains/slots mainly due to either of the two reasons- i) prediction of domain-slot as a pair, and ii) dependency of model parameters on the number of slots and domains. In this work, we propose to address these issues using a Hierarchical DST (Hi-DST) model. At a given turn, the model first detects a change in domain followed by domain prediction if required. Then it decides suitable action for each slot in the predicted domains and finds their value accordingly. The model parameters of Hi-DST are independent of the number of domains/slots. Due to the hierarchical modeling, it achieves O(|M|+|N|) belief state prediction for a single turn where M and N are the set of unique domains and slots respectively. We argue that the hierarchical structure helps in the model explainability and makes it easily extensible to new datasets. Experiments on the MultiWOZ dataset show that our proposed model achieves comparable joint accuracy performance to state-of-the-art DST models.
References used
https://aclanthology.org/
rate research
Read More
In task-oriented dialogue systems, recent dialogue state tracking methods tend to perform one-pass generation of the dialogue state based on the previous dialogue state. The mistakes of these models made at the current turn are prone to be carried ov
er to the next turn, causing error propagation. In this paper, we propose a novel Amendable Generation for Dialogue State Tracking (AG-DST), which contains a two-pass generation process: (1) generating a primitive dialogue state based on the dialogue of the current turn and the previous dialogue state, and (2) amending the primitive dialogue state from the first pass. With the additional amending generation pass, our model is tasked to learn more robust dialogue state tracking by amending the errors that still exist in the primitive dialogue state, which plays the role of reviser in the double-checking process and alleviates unnecessary error propagation. Experimental results show that AG-DST significantly outperforms previous works in two active DST datasets (MultiWOZ 2.2 and WOZ 2.0), achieving new state-of-the-art performances.
Dialogue State Tracking is central to multi-domain task-oriented dialogue systems, responsible for extracting information from user utterances. We present a novel hybrid architecture that augments GPT-2 with representations derived from Graph Attenti
on Networks in such a way to allow causal, sequential prediction of slot values. The model architecture captures inter-slot relationships and dependencies across domains that otherwise can be lost in sequential prediction. We report improvements in state tracking performance in MultiWOZ 2.0 against a strong GPT-2 baseline and investigate a simplified sparse training scenario in which DST models are trained only on session-level annotations but evaluated at the turn level. We further report detailed analyses to demonstrate the effectiveness of graph models in DST by showing that the proposed graph modules capture inter-slot dependencies and improve the predictions of values that are common to multiple domains.
Recently, the focus of dialogue state tracking has expanded from single domain to multiple domains. The task is characterized by the shared slots between domains. As the scenario gets more complex, the out-of-vocabulary problem also becomes severer.
Current models are not satisfactory for solving the challenges of ontology integration between domains and out-of-vocabulary problems. To address the problem, we explore the hierarchical semantic of ontology and enhance the interrelation between slots with masked hierarchical attention. In state value decoding stage, we solve the out-of-vocabulary problem by combining generation method and extraction method together. We evaluate the performance of our model on two representative datasets, MultiWOZ in English and CrossWOZ in Chinese. The results show that our model yields a significant performance gain over current state-of-the-art state tracking model and it is more robust to out-of-vocabulary problem compared with other methods.
Abstract Tracking dialogue states to better interpret user goals and feed downstream policy learning is a bottleneck in dialogue management. Common practice has been to treat it as a problem of classifying dialogue content into a set of pre-defined s
lot-value pairs, or generating values for different slots given the dialogue history. Both have limitations on considering dependencies that occur on dialogues, and are lacking of reasoning capabilities. This paper proposes to track dialogue states gradually with reasoning over dialogue turns with the help of the back-end data. Empirical results demonstrate that our method outperforms the state-of-the-art methods in terms of joint belief accuracy for MultiWOZ 2.1, a large-scale human--human dialogue dataset across multiple domains.
We present a fast and scalable architecture called Explicit Modular Decomposition (EMD), in which we incorporate both classification-based and extraction-based methods and design four modules (for clas- sification and sequence labelling) to jointly e
xtract dialogue states. Experimental results based on the MultiWoz 2.0 dataset validates the superiority of our proposed model in terms of both complexity and scalability when compared to the state-of-the-art methods, especially in the scenario of multi-domain dialogues entangled with many turns of utterances.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
