没有合适的资源?快使用搜索试试~ 我知道了~
李纪为《TEACHING MACHINES TO CONVERSE》
需积分: 13 13 下载量 149 浏览量
2018-02-25
12:23:17
上传
评论
收藏 2.72MB PDF 举报
温馨提示
试读
155页
斯坦福大神李纪为的博士论文。 这篇论文从多个方面尝试解决如今对话系统面临的诸多问题: 1.如何产生具体、贴切、有意思的答复; 2.如何赋予机器人格情感,从而产生具有一致性的答复; 3.最早提出使用对抗性学习方法来生成与人类水平相同的回复语句 ——让生成器与鉴别器不断进行类似[图灵测试]的训练; 4.最后提出了赋予机器人通过与人的交流自我更新的自学习模型。
资源推荐
资源详情
资源评论
TEACHING MACHINES TO CONVERSE
A DISSERTATION
SUBMITTED TO THE DEPARTMENT OF COMPUTER SCIENCE
AND THE COMMITTEE ON GRADUATE STUDIES
OF STANFORD UNIVERSITY
IN PARTIAL FULFILLMENT OF THE REQUIREMENTS
FOR THE DEGREE OF
DOCTOR OF PHILOSOPHY
Jiwei Li
October 2017
c
Copyright by Jiwei Li 2018
All Rights Reserved
ii
I certify that I have read this dissertation and that, in my opinion, it is fully
adequate in scope and quality as a dissertation for the degree of Doctor of
Philosophy.
(Dan Jurafsky) Principal Adviser
I certify that I have read this dissertation and that, in my opinion, it is fully
adequate in scope and quality as a dissertation for the degree of Doctor of
Philosophy.
(Christopher G. Potts)
I certify that I have read this dissertation and that, in my opinion, it is fully
adequate in scope and quality as a dissertation for the degree of Doctor of
Philosophy.
(Emma Brunskill)
Approved for the Stanford University Committee on Graduate Studies
iii
Abstract
The ability of a machine to communicate with humans has long been associated with the
general success of AI. This dates back to Alan Turing’s epoch-making work in the early
1950s, which proposes that a machine’s intelligence can be tested by how well it, the
machine, can fool a human into believing that the machine is a human through dialogue
conversations. Despite progress in the field of dialogue learning over the past decades,
conventional dialog systems still face a variety of major challenges such as robustness,
scalability and domain adaptation: many systems learn generation rules from a minimal set
of authored rules or labels on top of handcoded rules or templates, and thus are both expen-
sive and difficult to extend to open-domain scenarios. Meanwhile, dialogue systems have
become increasingly complicated: they usually involve building many different complex
components separately, rendering them unable to accommodate the large amount of data
that we have to date.
Recently, the emergence of neural network models the potential to solve many of the
problems in dialogue learning that earlier systems cannot tackle: the end-to-end neural
frameworks offer the promise of scalability and language-independence, together with the
ability to track the dialogue state and then mapping between states and dialogue actions
in a way not possible with conventional systems. On the other hand, neural systems bring
about new challenges: they tend to output dull and generic responses such as “I don’t know
what you are talking about”; they lack a consistent or a coherent persona; they are usually
optimized through single-turn conversations and are incapable of handling the long-term
success of a conversation; and they are not able to take the advantage of the interactions
with humans.
This dissertation attempts to tackle these challenges: Contributions are twofold: (1)
iv
这篇论文从多个方面尝试解决如今对话系统面临的诸多问题:
1.如何产生具体、贴切、有意思的答复;
2.如何赋予机器人格情感,从而产生具有一致性的答复;
3.最早提出使用对抗性学习方法来生成与人类水平相同的回复语句
——让生成器与鉴别器不断进行类似[图灵测试]的训练;
4.最后提出了赋予机器人通过与人的交流自我更新的自学习模型。
图灵测试
经典方法
端到端方法
we address new challenges presented by neural network models in open-domain dialogue
generation systems, which includes (a) using mutual information to avoid dull and generic
responses; (b) addressing user consistency issues to avoid inconsistent responses generated
by the same user; (c) developing reinforcement learning methods to foster the long-term
success of conversations; and (d) using adversarial learning methods to push machines
to generate responses that are indistinguishable from human-generated responses; (2) we
develop interactive question-answering dialogue systems by (a) giving the agent the ability
to ask questions and (b) training a conversation agent through interactions with humans in
an online fashion, where a bot improves through communicating with humans and learning
from the mistakes that it makes.
v
1.解决在公开域对话生成系统中,神经网络模型带来的挑战:
a.使用互信息避免无趣泛化的回答(Chapter 3)
b.解决用户一致性问题,避免生成不一致的回复(Chapter 4)
c.利用强化学习方法,增加长期对话成功率(Chapter 5)
d.使用对抗方法,推动机器生成与人类水平相同的回复(Chapter 6)
2.开发交互问答对话系统
a.赋予agent问问题的能力(Chapter 7)
b.通过在线与人类交互,训练对话agent,通过与人类交流、
从错误中学习,来获得提升(Chapter 8)
剩余154页未读,继续阅读
资源评论
woailaosang
- 粉丝: 8
- 资源: 3
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功