Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userGaining Experience with Structured Data: Using the Resources of Dialog State Tracking Challenge 2
اكتساب تجربة مع البيانات المهيكلة: استخدام موارد تحدي تتبع ولاية الحوار 2
93
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
توضح هذه الورقة مشروعا فئة لدورة المرحلة الجامعية المرحلة الجامعية تم تقديمها مؤخرا يمنح طلاب علوم الكمبيوتر الفرصة لاستكشاف بيانات تحدي تتبع ولاية الحوار 2 (DSTC 2).تمت مناقشة خلفية الطلاب وخيارات المناهج الدراسية وتفاصيل المشروع.تختتم الورقة مع بعض المشورة المدرس والانعكاسات النهائية.
This paper describes a class project for a recently introduced undergraduate NLP course that gives computer science students the opportunity to explore the data of Dialog State Tracking Challenge 2 (DSTC 2). Student background, curriculum choices, and project details are discussed. The paper concludes with some instructor advice and final reflections.
References used
https://aclanthology.org/
rate research
Read More
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.
Task-oriented conversational systems often use dialogue state tracking to represent the user's intentions, which involves filling in values of pre-defined slots. Many approaches have been proposed, often using task-specific architectures with special
-purpose classifiers. Recently, good results have been obtained using more general architectures based on pretrained language models. Here, we introduce a new variation of the language modeling approach that uses schema-driven prompting to provide task-aware history encoding that is used for both categorical and non-categorical slots. We further improve performance by augmenting the prompting with schema descriptions, a naturally occurring source of in-domain knowledge. Our purely generative system achieves state-of-the-art performance on MultiWOZ 2.2 and achieves competitive performance on two other benchmarks: MultiWOZ 2.1 and M2M. The data and code will be available at https://github.com/chiahsuan156/DST-as-Prompting.
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.
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.
Sequence-to-sequence models have been applied to a wide variety of NLP tasks, but how to properly use them for dialogue state tracking has not been systematically investigated. In this paper, we study this problem from the perspectives of pre-trainin
g objectives as well as the formats of context representations. We demonstrate that the choice of pre-training objective makes a significant difference to the state tracking quality. In particular, we find that masked span prediction is more effective than auto-regressive language modeling. We also explore using Pegasus, a span prediction-based pre-training objective for text summarization, for the state tracking model. We found that pre-training for the seemingly distant summarization task works surprisingly well for dialogue state tracking. In addition, we found that while recurrent state context representation works also reasonably well, the model may have a hard time recovering from earlier mistakes. We conducted experiments on the MultiWOZ 2.1-2.4, WOZ 2.0, and DSTC2 datasets with consistent observations.
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
