面向任务的对话系统的最新进展和挑战【清华大学】.pdf

dialog_system

需积分: 10 51 浏览量 2020-03-24 17:53:43 上传评论收藏 575KB PDF 举报

资源推荐

资源详情

资源评论

SCIENCE CHINA

Information Sciences

REVIEW

Recent Advances and Challenges in

Task-oriented Dialog System

Zheng Zhang, Ryuichi Takanobu, Minlie Huang

& Xiaoyan Zhu

Dept. of Computer Science & Technology, Tsinghua University, Beijing 100084, China;

Institute for Artiﬁcial Intelligence, Tsinghua University (THUAI), Beijing 100084, China;

Beijing National Research Center for Information Science & Technology, Beijing 100084, China

Abstract Due to the signiﬁcance and value in human-computer interaction and natural language process-

ing, task-oriented dialog systems are attracting more and more attention in both academic and industrial

communities. In this paper, we survey recent advances and challenges in an issue-speciﬁc manner. We discuss

three critical topics for task-oriented dialog systems: (1) improving data eﬃciency to facilitate dialog system

modeling in low-resource settings, (2) modeling multi-turn dynamics for dialog policy learning to achieve

better task-completion performance, and (3) integrating domain ontology knowledge into the dialog model

in both pipeline and end-to-end models. We also review the recent progresses in dialog evaluation and some

widely-used corpora. We believe that this survey can shed a light on future research in task-oriented dialog

systems.

Keywords task-oriented dialog, low-resource, dialog state tracking, dialog policy, end-to-end model

Citation Zhang Z, Takanobu R, Huang M, Zhu X. Recent Advances and Challenges in Task-oriented Dialog

System. Sci China Inf Sci, for review

1 Introduction

Building task-oriented (also referred to as goal-oriented) dialog systems has become a hot topic in the

research community and the industry. A task-oriented dialog system aims to assist the user in completing

certain tasks in a speciﬁc domain, such as restaurant booking, weather query, and ﬂight booking, which

makes it valuable for real-world business. Compared to open-domain dialog systems where the major

goal is to maximize user engagement [1], task-oriented dialog systems are more targeting at accomplishing

some speciﬁc tasks in one or multiple domains. Typically, the task-oriented dialog systems are built on

top of a structured ontology, which deﬁnes the domain knowledge of the tasks.

1.1 General Framework

The architecture of task-oriented dialog systems can be roughly divided into two classes: pipeline and

end-to-end approaches. In pipeline approaches, the model often consists of several components, includ-

ing Natural Language Understanding (NLU), Dialog State Tracking (DST), Dialog Policy, and Natural

Language Generation (NLG), which are combined in a pipeline manner as shown in Figure 1. The NLU,

DST and NLG components are often trained individually before being aggregated together, while the

dialog policy component is trained within the composed system. It is worth noting that although the

NLU-DST-Policy-NLG framework is a typical conﬁguration of the pipeline system, there are still some

* Corresponding author (email: aihuang@tsinghua.edu.cn)

arXiv:2003.07490v2 [cs.CL] 19 Mar 2020

Zhang Z, et al. Sci China Inf Sci 2

Natural Language

Understanding

User

Dialog State

Tracking

Natural Language

Generation

Dialog Policy

Dialog State

“I want to find a

Chinese restaurant.”

“Where do you

want to eat? ”

Inform (cuisine=“Chinese”)

Request (location)

Dialog

Manager

Query

Figure 1 General framework of a pipeline task-oriented dialog system.

other kinds of conﬁgurations. Recently, there are works that merge some of the typical components, such

as word-level DST and word-level policy, resulting in various pipeline conﬁgurations.

In end-to-end approaches, the dialog systems are trained in an end-to-end manner, without specifying

each individual component. Commonly, the training process is formulated as generating a responding

utterance given the dialog context and the backend knowledge base.

1.1.1 Natural Language Understanding

Given a user utterance, the natural language understanding (NLU) component maps it to a structured

semantic representation. A popular schema for semantic representation is the dialog act, which consists

of intent and slot-values, as illustrated in Table 1. The intent type is a high-level representation of an

utterance, such as Query and Inform. Slot-value pairs are the task-speciﬁc semantic elements that are

mentioned in an utterance. Based on the dialog act structure, the task of NLU can be further decomposed

into two tasks: intent detection and slot-value extraction. The former is normally formulated as an intent

classiﬁcation task by taking the utterance as input, and the slot-value extraction task is often viewed as

a sequence labeling problem:

intent

(d|x

, x

, ..., x

) (1)

slot

, y

, ..., y

, x

, ..., x

) (2)

where the d indicates intent class and y

to y

are the labels of each token in the utterance [x

, x

, ..., x

]

in which x

is a token and n means the number of tokens. p

intent

and p

slot

are often implemented

using recurrent neural networks, such as LSTM, to predict the intent class d and the sequence label y

respectively.

Table 1 An example of dialog act for an utterance in the restaurant reservation domain.

Utterance How about a British restaurant in north part of town.

Intent Query

Slot Value Cuisine=British, Location=North

1.1.2 Dialog State Tracking

The dialog state tracker estimates the user’s goal in each time step by taking the entire dialog context

as input. The dialog state at time t can be regarded as an abstracted representation of the previous

turns until t. Most existing works adopted belief state for dialog state representation, in which the state

is composed of several probability distributions over the value vocabulary of each slot. Therefore, this

Zhang Z, et al. Sci China Inf Sci 3

problem can be formulated as a multi-task classiﬁcation task:

i,t

, u

, ..., u

) (3)

where for each speciﬁc slot i, there is a tracker p

. u

represents the utterance in turn t. The class of

slot i in the t-th turn is d

i,t

. However, this approach falls short when facing previously unseen values at

running time. To mitigate this issue, there are some generative approaches that generalize well on new

domains and previous unseen values.

𝑆

"#$

𝑆

"%$

𝑆

"%&

𝑅

"#$

𝑅

"%$

𝑎

"#$

𝑎

"%$

Reward

State

Action

Figure 2 The framework of Markov Decision Process [2]. At time t, the system takes an action a

, receiving a reward R

and transferring to a new state S

t+1

1.1.3 Dialog Policy

Conditioned on the dialog state, the dialog policy generates the next system action. Since the dialog

acts in a session are generated sequentially, it is often formulated as a Markov Decision Process (MDP),

which can be addressed by Reinforcement Learning (RL). As illustrated in Figure 2, at a speciﬁc time

step t, the uesr takes an action a

, receiving a reward R

and the state is updated to S

A typical approach is to ﬁrst train the dialog policy oﬀ-line through supervised learning or imitation

learning based on the dialog corpus, and then ﬁne-tune the model through RL with real users. Since real

user dialogs are costly, user simulation techniques are introduced to provide aﬀordable training dialogs.

1.1.4 Natural Language Generation

Given the dialog act generated by the dialog policy, the natural language generation component maps the

act to a natural language utterance, which is often modeled as a conditioned language generation task [3].

To improve user experience, the generated utterance should (1) fully convey the semantics of a dialog act

for task-completion, and (2) be natural, speciﬁc, and informative, analogous to human language.

1.1.5 End-to-end Methods

The end-to-end approaches for task-oriented dialog systems are inspired by the researches on open-

domain dialog systems, which use neural models to build the system in an end-to-end manner without

modular design, as shown in Figure 3. Most of these methods utilized seq2seq neural networks as the

infrastructural framework. End-to-end formulation can avoid the problem of error propagation within

cascaded components during training.

1.2 Main Challenges

Recent advances in task-oriented dialog systems are dominated by neural approaches. These approaches

can be roughly classiﬁed into two genres: pipeline and end-to-end methods.

Zhang Z, et al. Sci China Inf Sci 4

Encoder Decoder

Latent

Variable

Query

knowledge

Figure 3 The framework of end-to-end dialog systems. It ﬁrst encodes natural language context to get some latent

variables, which can be used for KB query. Then based on the latent variables and query results, the decoder generates a

natural language response.

In pipeline methods, recent researches focus more on the dialog state tracking and dialog policy com-

ponents, which are also called Dialog Management. This is because both NLU and NLG components are

standalone language processing tasks, which is less interweaved to the task in dialog systems. Based on

the domain ontology, the DST task can be seen as a classiﬁcation task by predicting the value of each

slot. However, when the training data is not suﬃcient, such classiﬁcation-based methods can suﬀer from

the out-of-vocabulary (OOV) problem and can not be directly generalized to new domains. The dialog

policy learning task is often considered as a reinforcement learning task. Nevertheless, diﬀerent from

other well-known RL tasks, such as playing video games and Go, the training of dialog policy requires

real humans to serve as the environment, which is very costly. Furthermore, most existing methods used

manually deﬁned rewards, such as task-completion rate and session turn number, which cannot reliably

evaluate the performance of a system.

For end-to-end methods, the data-hungry nature of the vanilla sequence-to-sequence model makes it

diﬃcult to learn the sophisticated slot ﬁlling mechanism in task-oriented dialog systems with a limited

amount of domain-speciﬁc data. The knowledge base query issue requires the model to generate an

intermediate query besides the encoder and the decoder, which is not straightforward. Another drawback

is that the encoder-decoder framework utilizes a word-level strategy, which may lead to sub-optimal

performance because the strategy and language functions are entangled together.

Based on the above analysis, we elaborate three key issues in task-oriented dialog systems which we

will discuss in detail:

• Data Eﬃciency Most neural approaches are data-hungry, requiring a large amount of data to

fully train the model. However, in task-oriented dialog systems, the domain-speciﬁc data is often

hard to collect and expensive to annotate. Therefore, the problem of low-resource learning is one

of the major challenges.

• Multi-turn Dynamics The core feature of task-oriented dialog as compared to open-domain

dialog is its emphasis on goal-driven in multi-turn strategy. In each turn, the system action should

be consistent with the dialog history and should guide the subsequent dialog to larger task reward.

Nevertheless, the model-free RL methods which have shown superior performance on many tasks,

can not be directly adopted to task-oriented dialog, due to the costly training environment and

imperfect reward deﬁnition. Therefore, many solutions are proposed to tackle these problems in

multi-turn interactive training to learn a better policy, including model-based planning, reward

estimation and end-to-end policy learning.

• Knowledge Integration A task-oriented dialog system has to query the knowledge base (KB)

to retrieve some entities for response generation. In pipeline methods, the KB query is mostly

constructed according to DST results. Compared to pipeline models, the end-to-end approaches

剩余18页未读，继续阅读

评论收藏

内容反馈

syp_net

粉丝: 158
资源: 1196

面向任务的对话系统的最新进展和挑战【清华大学】.pdf

面向任务的对话系统的最新进展和挑战_中文译文.docx

任务型对话系统最新的进展和挑战（2020年04月最新进展）

对话管理的综述论文：最近的进展和挑战

Rokid ALab NLP负责人陈见耸：任务式对话系统实践

面向任务型的对话系统研究进展

任务型对话系统研究综述.pdf

任务导向型对话系统 -- 对话管理模型研究最新进展-阿里云开发者社区.pdf

论文研究-面向特定任务的对话主题建模 .pdf

利用ChatGPT技术构建面向多轮对话的任务导向型系统.docx

C++程序设计谭浩强100%完整·清华大学.pdf（pdf格式ppt）

习题解答-Java面向对象程序设计-邢国波-清华大学出版社.pdf

C++程序设计谭浩强完整版·清华大学.pdf

C++程序设计ppt_谭浩强·清华大学.pdf

人工智能在机对话系统中的技术现状与挑战.pdf

哈工大张伟男：任务型对话系统 _ 机器之心.pdf

面向任务的基于深度学习的多轮对话系统与技术.pdf

论文研究-基于管道的任务型对话系统的研究与设计 .pdf

基于小样本机器学习的跨任务对话系统.pdf

C++程序设计谭浩强100%完整·清华大学.pdf

C++程序设计谭浩强100%25完整·清华大学.pdf

C++程序设计_谭浩强·清华大学.pdf

C++程序设计谭浩强·清华大学.pdf

企业运营管理-清华大学.pdf

面向任务的对话系统中条件和连接查询的烛光分解_CANDLE Decomposing Conditional and Conjun

2003年——口语对话系统中语音识别的研究——清华大学博士论文.pdf

构建面向任务的在线购物对话系统

Multi-intent-dialoguer:联合训练多目标分类和空位填充的面向任务的对话系统研究项目

教学大纲-Python程序设计教程(第2版)-杨年华-清华大学出版社.pdf

最新资源