Filters








1,168 Hits in 3.5 sec

Diversifying Dialog Generation via Adaptive Label Smoothing

Yida Wang, Yinhe Zheng, Yong Jiang, Minlie Huang
2021 Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)   unpublished
Although existing approaches such as label smoothing can alleviate this issue, they fail to adapt to diverse dialog contexts.  ...  In this paper, we propose an Adaptive Label Smoothing (AdaLabel) approach that can adaptively estimate a target label distribution at each time step for different contexts.  ...  We demonstrate the hard target, label smoothing, and Adaptive Label Smoothing approach when learning to predict the next word ("human").  ... 
doi:10.18653/v1/2021.acl-long.272 fatcat:t6ksc2drqre2hgt4dmi6xkayq4

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

Tiancheng Zhao, Ran Zhao, Maxine Eskenazi
2017 arXiv   pre-print
While recent neural encoder-decoder models have shown great promise in modeling open-domain conversations, they often generate dull and generic responses.  ...  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  ...  Inspired by CVAE, we view the dialog contexts as the conditional attributes and adapt CVAE to generate diverse responses instead of images.  ... 
arXiv:1703.10960v3 fatcat:eonwpha6rbfbnczrxw5kbg6zmi

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)  
While recent neural encoder-decoder models have shown great promise in modeling open-domain conversations, they often generate dull and generic responses.  ...  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  ...  Inspired by CVAE, we view the dialog contexts as the conditional attributes and adapt CVAE to generate diverse responses instead of images.  ... 
doi:10.18653/v1/p17-1061 dblp:conf/acl/ZhaoZE17 fatcat:xk3tee3k6faddj2ous37qulwyq

Big Data Stream Analytics for Near Real-Time Sentiment Analysis

Otto K. M. Cheng, Raymond Lau
2015 Journal of Computer and Communications  
In the era of big data, huge volumes of data are generated from online social networks, sensor networks, mobile devices, and organizations' enterprise systems.  ...  With Jelinek-Mercer smoothing [13] , the probability of the document generating a query term t (i.e., nek-Mercer smoothing parameter [13] .  ...  For instance, a consumer may connect to other consumers via a social network.  ... 
doi:10.4236/jcc.2015.35024 fatcat:hibfywzdavd7vo6tiav7xfyopq

Building A User-Centric and Content-Driven Socialbot [article]

Hao Fang
2020 arXiv   pre-print
, and a language generation process that realizes the response plan and makes adjustments for speech synthesis.  ...  The architecture consists of a multi-dimensional language understanding module for analyzing user utterances, a hierarchical dialog management framework for dialog context tracking and complex dialog control  ...  , and smoothness.  ... 
arXiv:2005.02623v1 fatcat:oxsgfakzbzb7njqgfileddlsry

Conditional Text Generation for Harmonious Human-Machine Interaction [article]

Bin Guo, Hao Wang, Yasan Ding, Wei Wu, Shaoyang Hao, Yueqi Sun, Zhiwen Yu
2020 arXiv   pre-print
text generation, personalized text generation, and so on.  ...  The automatically generated text is becoming more and more fluent so researchers begin to consider more anthropomorphic text generation technology, that is the conditional text generation, including emotional  ...  CONCLUSION We have made a systematic review of the research trends of conditional text generation (c-TextGen).  ... 
arXiv:1909.03409v2 fatcat:s2zfmwxtubgwjks4luoby6vdoq

Video Clip and Artiste's Image as Tools of the Song Hit's Mediavirus Action Strengthening (Based on the Ukrainian and Russian Compositions of Late 20th – Early 21st Centuries)

Ivanna Shnur
2019 Bulletin of Kyiv National University of Culture and Arts. Series in Musical Art  
Razzakov's cites a dialog between A. Pugacheva and A.  ...  Our study's historical framework (the late 20th -the early 21th centuries) reflects the various stages of the viral component's adaptation in the song hit.  ... 
doi:10.31866/2616-7581.2.1.2019.171792 fatcat:qkq2643k7neszbqfn5djzobasm

ZOE

Nicholas D. Lane, Petko Georgiev, Cecilia Mascolo, Ying Gao
2015 Proceedings of the 13th Annual International Conference on Mobile Systems, Applications, and Services - MobiSys '15  
Crucially, and unlike other rich-sensing or dialog supporting wearables, ZOE achieves this without cloud or smartphone support -this has important side-effects for privacy since all user information can  ...  key aspects of everyday life (viz. personal, social and place information) on continuously sensed data; while also offering this data not only within conventional analytics but also through a speech dialog  ...  Our dialog system is a composite of code adapted from three open-source projects.  ... 
doi:10.1145/2742647.2742672 dblp:conf/mobisys/LaneGMG15 fatcat:wkfkgrccbzhohf4z6hvyr3z7qq

News, Trends and Comments

1984 Information Services and Use  
One approach which could rescue the home market is the trend toward adapting the technology in such a way that a user may access a videotex service via his microcomputer -rather than exclusively via a  ...  We might note that the LC information is to a large extent already available online -via DIALOG -in the form of the LC MARC and REMARC data bases, the latter produced by Carrollton Press (a subsidiary  ... 
doi:10.3233/isu-1984-4608 fatcat:25zrrp42qzbifmcuphdq352gom

Data Manipulation: Towards Effective Instance Learning for Neural Dialogue Generation via Learning to Augment and Reweight [article]

Hengyi Cai, Hongshen Chen, Yonghao Song, Cheng Zhang, Xiaofang Zhao, Dawei Yin
2020 arXiv   pre-print
Extensive experiments show that our framework can improve the dialogue generation performance with respect to various automatic evaluation metrics and human judgments.  ...  It not only manipulates training samples to optimize the dialogue generation model, but also learns to increase its manipulation skills through gradient descent with validation samples.  ...  This work is supported by the National Natural Science Foundation of China-Joint Fund for Ba-sic Research of General Technology under Grant U1836111 and U1736106.  ... 
arXiv:2004.02594v5 fatcat:yxg4fizbgndubh6y62q4sigagy

Evaluating embodied conversational agents in multimodal interfaces

Benjamin Weiss, Ina Wechsung, Christine Kühnel, Sebastian Möller
2015 Computational Cognitive Science  
The SUS questionnaire also offers rather generic questions, which might be adaptable to ECAs (Brooke 1996) . However, there are instrumental means to assess the cognitive load.  ...  Moraes and Silveira (2006) updated and adapted this set first to the evaluation of animated agents in general and later to the evaluation of pedagogical agents in particular (Moraes and Silveira 2009)  ... 
doi:10.1186/s40469-015-0006-9 fatcat:3qgvabqeffbwzlx3smclvs4f4u

Natural Language Generation with Neural Variational Models [article]

Hareesh Bahuleyan
2018 arXiv   pre-print
In this thesis, we explore the use of deep neural networks for generation of natural language.  ...  VAEs for text generation are difficult to train due to issues associated with the Kullback-Leibler (KL) divergence term of the loss function vanishing to zero.  ...  With empirical results on two tasks -question generation and dialog systems, we show that variational attention yields more diversified samples while retaining high quality.  ... 
arXiv:1808.09012v1 fatcat:2s5l5k5cr5bg3oqzvpbb5yt3zi

Finding Your Voice: The Linguistic Development of Mental Health Counselors

Justine Zhang, Robert Filbin, Christine Morrison, Jaclyn Weiser, Cristian Danescu-Niculescu-Mizil
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
this general vocabulary.  ...  Future work could adapt our framework to examine more complex forms of conversational development.  ... 
doi:10.18653/v1/p19-1089 dblp:conf/acl/ZhangFMWD19 fatcat:bz43uh3vu5gehoanih7dq5i6hy

On the Generation of Medical Question-Answer Pairs

Sheng Shen, Yaliang Li, Nan Du, Xian Wu, Yusheng Xie, Shen Ge, Tao Yang, Kai Wang, Xingzheng Liang, Wei Fan
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In the light of these challenges, we study the task of generating medical QA pairs in this paper.  ...  Further investigation shows that, by incorporating the generated QA pairs for training, significant improvement in terms of accuracy can be achieved for the examination QA system. 1  ...  Conditional Variational Autoencoder Motivated by (Serban et al. 2017) , we adapt the original CVAE for dialog generation to our setting by considering question generation as an iterative phrase generation  ... 
doi:10.1609/aaai.v34i05.6410 fatcat:uay5k4maczabvoksvccrvln4tm

On the Generation of Medical Question-Answer Pairs [article]

Sheng Shen, Yaliang Li, Nan Du, Xian Wu, Yusheng Xie, Shen Ge, Tao Yang, Kai Wang, Xingzheng Liang, Wei Fan
2019 arXiv   pre-print
In the light of these challenges, we study the task of generating medical QA pairs in this paper.  ...  Further investigation shows that, by incorporating the generated QA pairs for training, significant improvement in terms of accuracy can be achieved for the examination QA system.  ...  Conditional Variational Autoencoder Motivated by (Serban et al. 2017) , we adapt the original CVAE for dialog generation to our setting by considering question generation as an iterative phrase generation  ... 
arXiv:1811.00681v2 fatcat:z67vwse34vakbdur3tqdclh4d4
« Previous Showing results 1 — 15 out of 1,168 results