MTSS: Learn from Multiple Domain Teachers and Become a Multi-Domain Dialogue Expert
نویسندگان
چکیده
منابع مشابه
Integrating Topic Estimation and Dialogue History for Domain Selection in Multi-domain Spoken Dialogue Systems
本論文では,マルチドメイン音声対話システムにおいて,システム想定外発話に対 しても頑健に,応答すべきドメインを決定する方法について述べる.想定外発話は言 語理解誤りを引き起こし,ドメイン選択誤りの原因となる.そこで本論文ではまず, ユーザが意図したドメインをトピックとして定義し,Web から大量に収集した学習 文書と,Latent Semantic Mapping を用いてトピックを推定する.次に,対話履歴 とトピック推定を決定木を用いて統合し,想定外発話に頑健なドメイン選択器を構成 した.対話履歴とトピック推定は相補的な情報であり,これらの統合により高精度な ドメイン選択が実現できる.つまり我々が開発したトピック推定は,1 発話のみを対 象とするが,想定外発話に頑健である.一方で対話履歴は,対話の流れを考慮できる が,想定外発話による悪影響を強く受ける.話者 10 名 2,191 ...
متن کاملDialogue Management based on Multi-domain Corpus
Dialogue Management (DM) is a key issue in Spoken Dialogue System. Most of the existing data-driven DM schemes train the dialogue policy for some specific domain (or vertical domain), only using the dialogue corpus in this domain, which might suffer from the scarcity of dialogue corpus in some domains. In this paper, we divide Dialogue Act (DA), as semantic representation of utterance, into DA ...
متن کاملTowards dynamic multi-domain dialogue processing
This paper introduces SesaME, a generic dialogue management framework, especially designed for supporting dynamic multidomain dialogue processing. SesaME supports a multitude of highly distributed applications and facilitates simultaneous adaptation to individual users and their environment. The dynamic multi-domain dialogue processing is supported through the use of standardised and highly dis...
متن کاملClippyScript: A Programming Language for Multi-Domain Dialogue Systems
The past year has witnessed the revival of spoken dialogue systems. As these systems become multi-domain and more ubiquitous, the efficient scripting of dialogues increases in importantance. As of today, statistical approaches to dialogue control are not yet feasible; the problem remains quite firmly one of manual coding. This paper describes an object-oriented programming language that we have...
متن کاملPyDial: A Multi-domain Statistical Dialogue System Toolkit
Statistical Spoken Dialogue Systems have been around for many years. However, access to these systems has always been difficult as there is still no publicly available end-to-end system implementation. To alleviate this, we present PyDial, an opensource end-to-end statistical spoken dialogue system toolkit which provides implementations of statistical approaches for all dialogue system modules....
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the AAAI Conference on Artificial Intelligence
سال: 2020
ISSN: 2374-3468,2159-5399
DOI: 10.1609/aaai.v34i05.6384