Filters








28,453 Hits in 4.4 sec

A Conditional Variational Framework for Dialog Generation [article]

Xiaoyu Shen, Hui Su, Yanran Li, Wenjie Li, Shuzi Niu, Yang Zhao, Akiko Aizawa, Guoping Long
2017 arXiv   pre-print
In this paper, we propose a framework allowing conditional response generation based on specific attributes. These attributes can be either manually assigned or automatically detected.  ...  Deep latent variable models have been shown to facilitate the response generation for open-domain dialog systems.  ...  A snippet of the generated responses can be 4 Discussion and future work In this work, we propose a conditional variational framework for dialog generation and verify it on two scenarios.  ... 
arXiv:1705.00316v4 fatcat:72isabxomjdjjabbxjfgv66n3e

A Conditional Variational Framework for Dialog Generation

Xiaoyu Shen, Hui Su, Yanran Li, Wenjie Li, Shuzi Niu, Yang Zhao, Akiko Aizawa, Guoping Long
2017 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)  
In this paper, we propose a framework allowing conditional response generation based on specific attributes. These attributes can be either manually assigned or automatically detected.  ...  Deep latent variable models have been shown to facilitate the response generation for open-domain dialog systems.  ...  Discussion and future work In this work, we propose a conditional variational framework for dialog generation and verify it on two scenarios.  ... 
doi:10.18653/v1/p17-2080 dblp:conf/acl/ShenSLLNZAL17 fatcat:wxej3r6euveupnea6ztckeqnx4

Task-Oriented Dialog Systems That Consider Multiple Appropriate Responses under the Same Context

Yichi Zhang, Zhijian Ou, Zhou Yu
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
We propose a Multi-Action Data Augmentation (MADA) framework to utilize the one-to-many property to generate diverse appropriate dialog responses.  ...  By incorporating these additional pairs, the dialog policy learns a balanced action distribution, which further guides the dialog model to generate diverse responses.  ...  In another way, we are learning the correct dialog actions conditioned on a dialog state: L = t∈D log P (A t |S t ) (2) Due to the one-to-many property, for a specific dialog state S, there exists K different  ... 
doi:10.1609/aaai.v34i05.6507 fatcat:ofd3twwxt5h3pp4yahsn4lmzde

Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context [article]

Yichi Zhang, Zhijian Ou, Zhou Yu
2019 arXiv   pre-print
We propose a Multi-Action Data Augmentation (MADA) framework to utilize the one-to-many property to generate diverse appropriate dialog responses.  ...  By incorporating these additional pairs, the dialog policy learns a balanced action distribution, which further guides the dialog model to generate diverse responses.  ...  In another way, we are learning the correct dialog actions conditioned on a dialog state: L = t∈D log P (A t |S t ) (2) Due to the one-to-many property, for a specific dialog state S, there exists K different  ... 
arXiv:1911.10484v2 fatcat:24jjtd67xjg5jofmb4dspm4yku

Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders [article]

Tiancheng Zhao, Ran Zhao, Maxine Eskenazi
2017 arXiv   pre-print
Unlike past work that has focused on diversifying the output of the decoder at word-level to alleviate this problem, we present a novel framework based on conditional variational autoencoders that captures  ...  We have further developed a novel variant that is integrated with linguistic prior knowledge for better performance. Finally, the training procedure is improved by introducing a bag-of-word loss.  ...  Conditional Variational Autoencoder The variational autoencoder (VAE) (Kingma and Welling, 2013; Rezende et al., 2014) is one of the most popular frameworks for image generation.  ... 
arXiv:1703.10960v3 fatcat:eonwpha6rbfbnczrxw5kbg6zmi

A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning [article]

Yichi Zhang, Zhijian Ou, Huixin Wang, Junlan Feng
2020 arXiv   pre-print
Such latent variable modeling enables us to develop semi-supervised learning under the principled variational learning framework.  ...  Structured belief states are crucial for user goal tracking and database query in task-oriented dialog systems.  ...  Latent Belief State Dialog Models We first introduce LABES as a general dialog modeling framework in this section.  ... 
arXiv:2009.08115v3 fatcat:3rtcx454bje6ti747aucz72kde

Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders

Tiancheng Zhao, Ran Zhao, Maxine Eskenazi
2017 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
Unlike past work that has focused on diversifying the output of the decoder at word-level to alleviate this problem, we present a novel framework based on conditional variational autoencoders that captures  ...  We have further developed a novel variant that is integrated with linguistic prior knowledge for better performance. Finally, the training procedure is improved by introducing a bag-of-word loss.  ...  Conditional Variational Autoencoder The variational autoencoder (VAE) (Kingma and Welling, 2013; Rezende et al., 2014) is one of the most popular frameworks for image generation.  ... 
doi:10.18653/v1/p17-1061 dblp:conf/acl/ZhaoZE17 fatcat:xk3tee3k6faddj2ous37qulwyq

A study of interaction between dialog and decision for human-robot collaborative task achievement

Aurelie Clodic, Rachid Alami, Vincent Montreuil, Shuyin Li, Britta Wrede, Agnes Swadzba
2007 RO-MAN 2007 - The 16th IEEE International Symposium on Robot and Human Interactive Communication  
With this framework, we investigate various task negotiation situations for a social robot in a fetch-and-carry scenario.  ...  For the technical realization of the framework, the interface specification between the dialog and the decision making systems is also presented.  ...  In general, it is challenging for the dialog system to identify relationships between tasks.  ... 
doi:10.1109/roman.2007.4415214 dblp:conf/ro-man/ClodicAMLWS07 fatcat:utyqk3rawrcqfcx63cuom6ud7i

Dialog Simulation with Realistic Variations for Training Goal-Oriented Conversational Systems [article]

Chien-Wei Lin, Vincent Auvray, Daniel Elkind, Arijit Biswas, Maryam Fazel-Zarandi, Nehal Belgamwar, Shubhra Chandra, Matt Zhao, Angeliki Metallinou, Tagyoung Chung, Charlie Shucheng Zhu, Suranjit Adhikari (+1 others)
2020 arXiv   pre-print
not generate any novel dialog flow variations.  ...  50% relative accuracy improvements on a held-out test set compared to a baseline dialog generation approach that only samples natural language and entity value variations from existing catalogs but does  ...  To address the time and cost requirements of WoZ setups, the authors in [12] proposed a Machines-Talking-To-Machines (M2M) framework, where a user and a system simulator interact to generate dialog outlines  ... 
arXiv:2011.08243v1 fatcat:7usbi43uqnccjnap3df2sykvdi

Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models [article]

Tiancheng Zhao, Kaige Xie, Maxine Eskenazi
2019 arXiv   pre-print
This paper proposes a novel latent action framework that treats the action spaces of an end-to-end dialog agent as latent variables and develops unsupervised methods in order to induce its own action space  ...  Our detailed analysis also provides insights about various latent variable approaches for policy learning and can serve as a foundation for developing better latent actions in future research.  ...  Learning discourse-level diversity for neural dialog models using conditional variational autoencoders.  ... 
arXiv:1902.08858v2 fatcat:hkiixigjlzbq7njrmw3ztoohpa

Bootstrapping Dialog Models from Human to Human Conversation Logs

Pankaj Dhoolia, Vineet Kumar, Danish Contractor, Sachindra Joshi
2021 AAAI Conference on Artificial Intelligence  
However, a dialog designer needs to rely on domain experts to manually build the dialog model -by creating dialog flow nodes and modeling user intents.  ...  State-of-the-art commercial dialog platforms provide powerful tools to build a conversational agent. These platforms provide complete control to the dialog designer to model useragent interactions.  ...  These frameworks enable the Dialog Designer to specify user intents and a dialog flow.  ... 
dblp:conf/aaai/DhooliaKCJ21 fatcat:ygwrhp7hjfh7fgyqcwpkgffcdu

Adversarial Mutual Information for Text Generation [article]

Boyuan Pan, Yazheng Yang, Kaizhao Liang, Bhavya Kailkhura, Zhongming Jin, Xian-Sheng Hua, Deng Cai, Bo Li
2020 arXiv   pre-print
to lead to a tighter lower bound of maximum mutual information for the variational information maximization problem.  ...  In this paper, we propose Adversarial Mutual Information (AMI): a text generation framework which is formed as a novel saddle point (min-max) optimization aiming to identify joint interactions between  ...  Dialog Generation We first verify the effectiveness of our method on the dialog generation task, which requires to generate a coherent and meaningful response given a conversation history.  ... 
arXiv:2007.00067v1 fatcat:athwkrd73vgxjmwzutdwtkhjra

Hierarchy Response Learning for Neural Conversation Generation

Bo Zhang, Xiaoming Zhang
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
levels of diversity using the conditional variational autoencoders.  ...  Specifically, a hierarchical response generation (HRG) framework is proposed to capture the conversation intention in a natural and coherent way.  ...  Finally, an efficient training method is proposed to learn the model within the framework of conditional variational autoencoders (CVAE) (Doersch, 2016) .  ... 
doi:10.18653/v1/d19-1186 dblp:conf/emnlp/ZhangZ19 fatcat:kh2amcqnwbhbzd45wcbvaynf4e

Adversarial Learning on the Latent Space for Diverse Dialog Generation [article]

Kashif Khan, Gaurav Sahu, Vikash Balasubramanian, Lili Mou, Olga Vechtomova
2020 arXiv   pre-print
In this paper, we propose a two-step framework based on generative adversarial nets for generating conditioned responses.  ...  Generating relevant responses in a dialog is challenging, and requires not only proper modeling of context in the conversation but also being able to generate fluent sentences during inference.  ...  A dialog generation system can be divided into two parts: 1) encoding the context of the conversation, and 2) generating a response conditioned on the given context.  ... 
arXiv:1911.03817v3 fatcat:bd5zbc35mnbldik3pbaho5nn5i

Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models

Tiancheng Zhao, Kaige Xie, Maxine Eskenazi
2019 Proceedings of the 2019 Conference of the North  
This paper proposes a novel latent action framework that treats the action spaces of an end-to-end dialog agent as latent variables and develops unsupervised methods in order to induce its own action space  ...  Our detailed analysis also provides insights about various latent variable approaches for policy learning and can serve as a foundation for developing better latent actions in future research. 1  ...  Learning discourse-level diversity for neural dialog models using conditional variational autoencoders.  ... 
doi:10.18653/v1/n19-1123 dblp:conf/naacl/ZhaoXE19 fatcat:ykr5uujft5cznfikcno5wgyayy
« Previous Showing results 1 — 15 out of 28,453 results