This document discusses using latent variable models with reinforcement learning to define action spaces for end-to-end dialogue agents. It presents a baseline RNN encoder-decoder model trained with word-level reinforcement learning, and proposes using latent actions sampled from Gaussian or categorical distributions to shorten the horizon and allow for a smaller action space. The model is trained with a lite evidence lower bound objective and can incorporate the latent actions into response decoding through attention. Experiments on the MultiWoz dataset show the latent action models improve task success while maintaining language quality compared to the baseline.
International Journal of Engineering Research and Development (IJERD)IJERD Editor
journal publishing, how to publish research paper, Call For research paper, international journal, publishing a paper, IJERD, journal of science and technology, how to get a research paper published, publishing a paper, publishing of journal, publishing of research paper, reserach and review articles, IJERD Journal, How to publish your research paper, publish research paper, open access engineering journal, Engineering journal, Mathemetics journal, Physics journal, Chemistry journal, Computer Engineering, Computer Science journal, how to submit your paper, peer reviw journal, indexed journal, reserach and review articles, engineering journal, www.ijerd.com, research journals,
yahoo journals, bing journals, International Journal of Engineering Research and Development, google journals, hard copy of journal
VIDEO QUALITY ASSESSMENT USING LAPLACIAN MODELING OF MOTION VECTOR DISTRIBUTI...sipij
Video/Image quality assessment (VQA/IQA) is fundamental in various fields of video/image processing.
VQA reflects the quality of a video as most people commonly perceive. This paper proposes a reducedreference
mobile VQA, in which one-dimensional (1-D) motion vector (MV) distributions are used as
features of videos. This paper focuses on reduction of data size using Laplacian modeling of MV
distributions because network resource is restricted in the case of mobile video. The proposed method is
more efficient than the conventional methods in view of the computation time, because the proposed quality
metric decodes MVs directly from video stream in the parsing process rather than reconstructing the
distorted video at a receiver. Moreover, in view of data size, the proposed method is efficient because a
sender transmits only 28 parameters. We adopt the Laplacian distribution for modeling 1-D MV
histograms. 1-D MV histograms accumulated over the whole video sequences are used, which is different
from the conventional methods that assess each image frame independently. For testing the similarity
between MV histogram of reference and distorted videos and for minimizing the fitting error in Laplacian
modeling process, we use the chi-square method. To show the effectiveness of our proposed method, we
compare the proposed method with the conventional methods with coded video clips, which are coded
under varying bit rate, image size, and frame rate by H.263 and H.264/AVC. Experimental results show
that the proposed method gives the performance comparable with the conventional methods, especially, the
proposed method requires much lower transmission data.
International Journal of Engineering Research and Development (IJERD)IJERD Editor
journal publishing, how to publish research paper, Call For research paper, international journal, publishing a paper, IJERD, journal of science and technology, how to get a research paper published, publishing a paper, publishing of journal, publishing of research paper, reserach and review articles, IJERD Journal, How to publish your research paper, publish research paper, open access engineering journal, Engineering journal, Mathemetics journal, Physics journal, Chemistry journal, Computer Engineering, Computer Science journal, how to submit your paper, peer reviw journal, indexed journal, reserach and review articles, engineering journal, www.ijerd.com, research journals,
yahoo journals, bing journals, International Journal of Engineering Research and Development, google journals, hard copy of journal
VIDEO QUALITY ASSESSMENT USING LAPLACIAN MODELING OF MOTION VECTOR DISTRIBUTI...sipij
Video/Image quality assessment (VQA/IQA) is fundamental in various fields of video/image processing.
VQA reflects the quality of a video as most people commonly perceive. This paper proposes a reducedreference
mobile VQA, in which one-dimensional (1-D) motion vector (MV) distributions are used as
features of videos. This paper focuses on reduction of data size using Laplacian modeling of MV
distributions because network resource is restricted in the case of mobile video. The proposed method is
more efficient than the conventional methods in view of the computation time, because the proposed quality
metric decodes MVs directly from video stream in the parsing process rather than reconstructing the
distorted video at a receiver. Moreover, in view of data size, the proposed method is efficient because a
sender transmits only 28 parameters. We adopt the Laplacian distribution for modeling 1-D MV
histograms. 1-D MV histograms accumulated over the whole video sequences are used, which is different
from the conventional methods that assess each image frame independently. For testing the similarity
between MV histogram of reference and distorted videos and for minimizing the fitting error in Laplacian
modeling process, we use the chi-square method. To show the effectiveness of our proposed method, we
compare the proposed method with the conventional methods with coded video clips, which are coded
under varying bit rate, image size, and frame rate by H.263 and H.264/AVC. Experimental results show
that the proposed method gives the performance comparable with the conventional methods, especially, the
proposed method requires much lower transmission data.
4D AUTOMATIC LIP-READING FOR SPEAKER'S FACE IDENTIFCATION sipij
A novel based a trajectory-guided, concatenating approach for synthesizing high-quality image real sample renders video is proposed. The lips reading automated is seeking for modeled the closest real image sample sequence preserve in the library under the data video to the HMM predicted trajectory. The object trajectory is modeled obtained by projecting the face patterns into an KDA feature space is estimated. The approach for speaker's face identification by using synthesise the identity surface of a subject face from a small sample of patterns which sparsely each the view sphere. An KDA algorithm use to the Lip-reading image is discrimination, after that work consisted of in the low dimensional for the fundamental lip features vector is reduced by using the 2D-DCT. The mouth of the set area dimensionality is ordered by a normally reduction base on the PCA to obtain the Eigenlips approach, their proposed approach by[33]. The subjective performance results of the cost function under the automatic lips
reading modeled , which wasn’t illustrate the superior performance of the method.
A description about image Compression. What are types of redundancies, which are there in images. Two classes compression techniques. Four different lossless image compression techiques with proper diagrams(Huffman, Lempel Ziv, Run Length coding, Arithmetic coding).
Performance analysis of image compression using fuzzy logic algorithmsipij
With the increase in demand, product of multimedia is increasing fast and thus contributes to insufficient
network bandwidth and memory storage. Therefore image compression is more significant for reducing
data redundancy for save more memory and transmission bandwidth. An efficient compression technique
has been proposed which combines fuzzy logic with that of Huffman coding. While normalizing image
pixel, each value of pixel image belonging to that image foreground are characterized and interpreted. The
image is sub divided into pixel which is then characterized by a pair of set of approximation. Here
encoding represent Huffman code which is statistically independent to produce more efficient code for
compression and decoding represents rough fuzzy logic which is used to rebuilt the pixel of image. The
method used here are rough fuzzy logic with Huffman coding algorithm (RFHA). Here comparison of
different compression techniques with Huffman coding is done and fuzzy logic is applied on the Huffman
reconstructed image. Result shows that high compression rates are achieved and visually negligible
difference between compressed images and original images
Image Compression: It is the Art & Science of reducing the amount of data required to represent an image
The number of images compressed and decompressed daily is innumerable
TLDR (Twin Learning for Dimensionality Reduction) is an unsupervised dimensionality reduction method that combines neighborhood embedding learning with the simplicity and effectiveness of recent self-supervised learning losses.
MLSEV. Logistic Regression, Deepnets, and Time Series BigML, Inc
Supervised Learning (Part II): Logistic Regression, Deepnets, and Time Series, by BigML.
MLSEV 2019: 1st edition of the Machine Learning School in Seville, Spain.
4D AUTOMATIC LIP-READING FOR SPEAKER'S FACE IDENTIFCATION sipij
A novel based a trajectory-guided, concatenating approach for synthesizing high-quality image real sample renders video is proposed. The lips reading automated is seeking for modeled the closest real image sample sequence preserve in the library under the data video to the HMM predicted trajectory. The object trajectory is modeled obtained by projecting the face patterns into an KDA feature space is estimated. The approach for speaker's face identification by using synthesise the identity surface of a subject face from a small sample of patterns which sparsely each the view sphere. An KDA algorithm use to the Lip-reading image is discrimination, after that work consisted of in the low dimensional for the fundamental lip features vector is reduced by using the 2D-DCT. The mouth of the set area dimensionality is ordered by a normally reduction base on the PCA to obtain the Eigenlips approach, their proposed approach by[33]. The subjective performance results of the cost function under the automatic lips
reading modeled , which wasn’t illustrate the superior performance of the method.
A description about image Compression. What are types of redundancies, which are there in images. Two classes compression techniques. Four different lossless image compression techiques with proper diagrams(Huffman, Lempel Ziv, Run Length coding, Arithmetic coding).
Performance analysis of image compression using fuzzy logic algorithmsipij
With the increase in demand, product of multimedia is increasing fast and thus contributes to insufficient
network bandwidth and memory storage. Therefore image compression is more significant for reducing
data redundancy for save more memory and transmission bandwidth. An efficient compression technique
has been proposed which combines fuzzy logic with that of Huffman coding. While normalizing image
pixel, each value of pixel image belonging to that image foreground are characterized and interpreted. The
image is sub divided into pixel which is then characterized by a pair of set of approximation. Here
encoding represent Huffman code which is statistically independent to produce more efficient code for
compression and decoding represents rough fuzzy logic which is used to rebuilt the pixel of image. The
method used here are rough fuzzy logic with Huffman coding algorithm (RFHA). Here comparison of
different compression techniques with Huffman coding is done and fuzzy logic is applied on the Huffman
reconstructed image. Result shows that high compression rates are achieved and visually negligible
difference between compressed images and original images
Image Compression: It is the Art & Science of reducing the amount of data required to represent an image
The number of images compressed and decompressed daily is innumerable
TLDR (Twin Learning for Dimensionality Reduction) is an unsupervised dimensionality reduction method that combines neighborhood embedding learning with the simplicity and effectiveness of recent self-supervised learning losses.
MLSEV. Logistic Regression, Deepnets, and Time Series BigML, Inc
Supervised Learning (Part II): Logistic Regression, Deepnets, and Time Series, by BigML.
MLSEV 2019: 1st edition of the Machine Learning School in Seville, Spain.
Pascual, Santiago, Antonio Bonafonte, and Joan Serrà. "SEGAN: Speech Enhancement Generative Adversarial Network." INTERSPEECH 2017.
Current speech enhancement techniques operate on the spectral domain and/or exploit some higher-level feature. The majority of them tackle a limited number of noise conditions and rely on first-order statistics. To circumvent these issues, deep networks are being increasingly used, thanks to their ability to learn complex functions from large example sets. In this work, we propose the use of generative adversarial networks for speech enhancement. In contrast to current techniques, we operate at the waveform level, training the model end-to-end, and incorporate 28 speakers and 40 different noise conditions into the same model, such that model parameters are shared across them. We evaluate the proposed model using an independent, unseen test set with two speakers and 20 alternative noise conditions. The enhanced samples confirm the viability of the proposed model, and both objective and subjective evaluations confirm the effectiveness of it. With that, we open the exploration of generative architectures for speech enhancement, which may progressively incorporate further speech-centric design choices to improve their performance.
NO1 Uk best vashikaran specialist in delhi vashikaran baba near me online vas...Amil Baba Dawood bangali
Contact with Dawood Bhai Just call on +92322-6382012 and we'll help you. We'll solve all your problems within 12 to 24 hours and with 101% guarantee and with astrology systematic. If you want to take any personal or professional advice then also you can call us on +92322-6382012 , ONLINE LOVE PROBLEM & Other all types of Daily Life Problem's.Then CALL or WHATSAPP us on +92322-6382012 and Get all these problems solutions here by Amil Baba DAWOOD BANGALI
#vashikaranspecialist #astrologer #palmistry #amliyaat #taweez #manpasandshadi #horoscope #spiritual #lovelife #lovespell #marriagespell#aamilbabainpakistan #amilbabainkarachi #powerfullblackmagicspell #kalajadumantarspecialist #realamilbaba #AmilbabainPakistan #astrologerincanada #astrologerindubai #lovespellsmaster #kalajaduspecialist #lovespellsthatwork #aamilbabainlahore#blackmagicformarriage #aamilbaba #kalajadu #kalailam #taweez #wazifaexpert #jadumantar #vashikaranspecialist #astrologer #palmistry #amliyaat #taweez #manpasandshadi #horoscope #spiritual #lovelife #lovespell #marriagespell#aamilbabainpakistan #amilbabainkarachi #powerfullblackmagicspell #kalajadumantarspecialist #realamilbaba #AmilbabainPakistan #astrologerincanada #astrologerindubai #lovespellsmaster #kalajaduspecialist #lovespellsthatwork #aamilbabainlahore #blackmagicforlove #blackmagicformarriage #aamilbaba #kalajadu #kalailam #taweez #wazifaexpert #jadumantar #vashikaranspecialist #astrologer #palmistry #amliyaat #taweez #manpasandshadi #horoscope #spiritual #lovelife #lovespell #marriagespell#aamilbabainpakistan #amilbabainkarachi #powerfullblackmagicspell #kalajadumantarspecialist #realamilbaba #AmilbabainPakistan #astrologerincanada #astrologerindubai #lovespellsmaster #kalajaduspecialist #lovespellsthatwork #aamilbabainlahore #Amilbabainuk #amilbabainspain #amilbabaindubai #Amilbabainnorway #amilbabainkrachi #amilbabainlahore #amilbabaingujranwalan #amilbabainislamabad
Explore the innovative world of trenchless pipe repair with our comprehensive guide, "The Benefits and Techniques of Trenchless Pipe Repair." This document delves into the modern methods of repairing underground pipes without the need for extensive excavation, highlighting the numerous advantages and the latest techniques used in the industry.
Learn about the cost savings, reduced environmental impact, and minimal disruption associated with trenchless technology. Discover detailed explanations of popular techniques such as pipe bursting, cured-in-place pipe (CIPP) lining, and directional drilling. Understand how these methods can be applied to various types of infrastructure, from residential plumbing to large-scale municipal systems.
Ideal for homeowners, contractors, engineers, and anyone interested in modern plumbing solutions, this guide provides valuable insights into why trenchless pipe repair is becoming the preferred choice for pipe rehabilitation. Stay informed about the latest advancements and best practices in the field.
Water scarcity is the lack of fresh water resources to meet the standard water demand. There are two type of water scarcity. One is physical. The other is economic water scarcity.
Immunizing Image Classifiers Against Localized Adversary Attacksgerogepatton
This paper addresses the vulnerability of deep learning models, particularly convolutional neural networks
(CNN)s, to adversarial attacks and presents a proactive training technique designed to counter them. We
introduce a novel volumization algorithm, which transforms 2D images into 3D volumetric representations.
When combined with 3D convolution and deep curriculum learning optimization (CLO), itsignificantly improves
the immunity of models against localized universal attacks by up to 40%. We evaluate our proposed approach
using contemporary CNN architectures and the modified Canadian Institute for Advanced Research (CIFAR-10
and CIFAR-100) and ImageNet Large Scale Visual Recognition Challenge (ILSVRC12) datasets, showcasing
accuracy improvements over previous techniques. The results indicate that the combination of the volumetric
input and curriculum learning holds significant promise for mitigating adversarial attacks without necessitating
adversary training.
About
Indigenized remote control interface card suitable for MAFI system CCR equipment. Compatible for IDM8000 CCR. Backplane mounted serial and TCP/Ethernet communication module for CCR remote access. IDM 8000 CCR remote control on serial and TCP protocol.
• Remote control: Parallel or serial interface.
• Compatible with MAFI CCR system.
• Compatible with IDM8000 CCR.
• Compatible with Backplane mount serial communication.
• Compatible with commercial and Defence aviation CCR system.
• Remote control system for accessing CCR and allied system over serial or TCP.
• Indigenized local Support/presence in India.
• Easy in configuration using DIP switches.
Technical Specifications
Indigenized remote control interface card suitable for MAFI system CCR equipment. Compatible for IDM8000 CCR. Backplane mounted serial and TCP/Ethernet communication module for CCR remote access. IDM 8000 CCR remote control on serial and TCP protocol.
Key Features
Indigenized remote control interface card suitable for MAFI system CCR equipment. Compatible for IDM8000 CCR. Backplane mounted serial and TCP/Ethernet communication module for CCR remote access. IDM 8000 CCR remote control on serial and TCP protocol.
• Remote control: Parallel or serial interface
• Compatible with MAFI CCR system
• Copatiable with IDM8000 CCR
• Compatible with Backplane mount serial communication.
• Compatible with commercial and Defence aviation CCR system.
• Remote control system for accessing CCR and allied system over serial or TCP.
• Indigenized local Support/presence in India.
Application
• Remote control: Parallel or serial interface.
• Compatible with MAFI CCR system.
• Compatible with IDM8000 CCR.
• Compatible with Backplane mount serial communication.
• Compatible with commercial and Defence aviation CCR system.
• Remote control system for accessing CCR and allied system over serial or TCP.
• Indigenized local Support/presence in India.
• Easy in configuration using DIP switches.
Saudi Arabia stands as a titan in the global energy landscape, renowned for its abundant oil and gas resources. It's the largest exporter of petroleum and holds some of the world's most significant reserves. Let's delve into the top 10 oil and gas projects shaping Saudi Arabia's energy future in 2024.
AKS UNIVERSITY Satna Final Year Project By OM Hardaha.pdf
Rethinking action spaces for reinforcement learning in end-to-end dialog agents with latent variable models(LaRL)
1. Latent action Reinforcement learning
in End-to-end Dialogue System
Tiancheng Zhao, Kaige Xie, Maxine Esenazi: Rethinking Action Spaces for Reinforcement Learning in End-to-
end Dialog Agents with Latent Variable Models. NAACL-HLT 2019
2019. 07. 23.
presented by Jeong-Gwan Lee
1
2. 2
Table of contents
¨ Multi-turn goal-oriented Dialog System
• Component of Dialog system
• Type of action space in dialog system
¨ Baseline model
• RNN Encoder-Decoder model
• Word-level Reinforcement Learning
¨ Latent Action Reinforcement Learning
• Supervise pre-training & RL step
• Gaussian Latent Actions
• Categorical Latent Actions(with summation fusion)
• Attention Fusion
• Optimization Approaches (Full ELBO vs. Lite ELBO)
¨ Experiments (MultiWoz)
• Setting
• Results
¨ Summary
3. 3
Multi-turn goal-oriented dialog (MultiWoz)
”I am looking for a place to to stay that has cheap price range it
should be in a type of hotel"
"okay , do you have a specific area you want to stay in ?"
"no , i just need to make sure it s cheap. oh , and i need parking"
"i found 1 cheap hotel for you that include -s parking .
do you like me to book it ?",
"yes , please . 6 people 3 nights starting on thursday ."
i am sorry but i was not able to book that for you for 3
days. is there another day you would like to stay or
perhaps a shorter stay ?",
"how about only 2 nights .",
"booking was successful . reference number is [hotel_reference].
anything else i can do for you ?",
"no , that will be all . goodbye ."
"thank you for using our services."
User side System side
Red : inform, sky-blue : request(or book)
4. 4
Components of Dialog system
NLU DST Policy(Action) NLG
”I am looking for a place to to stay that has cheap price range it should be in a
type of hotel"
[NLU] ”I am looking for a place to to stay that has cheap price range it should
be in a type of hotel"
[DST] [“type” : Hotel, “price_range” : cheap]
[Policy] What the system’s next action?
5. 5
Types of action space in dialog system
NLU DST Policy(RL) NLG
[DST] [“type” : Hotel, “price_range” : cheap]
[Policy] [“Hotel parking?”, ”Hotel internet?”, …]
¨ The action space is defined by hand-crafted semantic representations
such as dialog acts and slot values
• Limit : only handle simple domains whose entire action space can be captured by hand-
crafted representations.
6. 6
Types of action space in dialog system
NLU DST Word-level RL
[DST] [“type” : Hotel, “price_range” : cheap]
¨ To apply RL to E2E dialog systems, the action space is defined as the
entire vocabulary. (Word-level RL)
• Every response output word is considered to be an action selection step.
• Limit
• direct application of word-level RL leads to degenerate behavior: the response
decoder deviates from human language and generates utterances that are
incomprehensible.
• Suffers from a long horizon(UT), leading to slow and sub optimal convergence.
[Word-level RL] [“parking”, “you”, ”need” ”internet”, …]
8. 8
Baseline approach(Word-level RL)
¨ E2E response generation can be treated as a conditional language
generation task.
¨ Training with RL usually has 2 steps:
supervised pre-training and policy gradient reinforcement learning.
• The supervised learning step maximizes the log likelihood on the training dialogs.
• RL step uses policy gradients, e.g., the REINFORCE[0] algorithm
[0] Williams, Ronald J. "Simple statistical gradient-following algorithms for connectionist reinforcement
learning." Machine learning 8.3-4 (1992): 229-256.
RL:SL=A:B è A policy gradient update, B supervised learning update
9. 9
Baseline model (Supervised Learning)
Encoder
Bi-
RNN
Bi-
RNN
Bi-
RNN
Bi-
RNN
…
Decoder
RNN
<GO>
RNN RNN RNN…
Output sequence
Input sequence
Attention
Belief
State
label
DB
label
Summary
Summary
Linear
Budzianowski, Paweł, et al. "Multiwoz-a large-scale multi-domain wizard-of-oz dataset for task-oriented dialogue
modelling." arXiv preprint arXiv:1810.00278 (2018).
11. 11
Latent Action Reinforcement Learning
¨ Define a latent variable
¨ The conditional distribution is factorized into
(1) given a dialog context , we first sample a latent action from
, where is the dialog encoder network
(2) generate the response by sampling based on via
, where is the response decoder network.
12. 12
Latent Action Reinforcement Learning
¨ Compared to Eq 2,
• Shortens the horizon from TU to T.
• Latent action space is designed to be low-dimensional, much smaller
than V.
• The policy gradient only updates the encoder and the decoder
stays intact.
13. 13
Gaussian Latent Actions
Belief
State
label
DB
labelSummary
Linear
Decoder
RNN
<GO>
RNN RNN RNN…
Output sequence
Gaussian Latent Actions
Linear
Encoder Summary
decoder initial state
To compute policy gradient in Eq 3,
Use reparametrization trick[1] to backprop.
[1] Kingma, Diederik P., and Max Welling. "Auto-encoding variational bayes." arXiv preprint arXiv:1312.6114 (2013).
14. 14
Categorical Latent Actions
Decoder
RNN
<GO>
RNN RNN RNN…
Belief
State
label
DB
labelSummary
Linear
Encoder Summary
(K) (K) (K)
(K)(K) (K)
Categorical Latent Actions
To compute policy gradient in Eq 3,
(M, K)
(M, K)
(M, K)
(M, D)
(D)
Use Gumbel-max trick[2] to backprop.
[2]Jang, Eric, Shixiang Gu, and Ben Poole. "Categorical reparameterization with gumbel-softmax." arXiv preprint
arXiv:1611.01144 (2016).
gumbel-max sampling
16. 16
Optimization Approaches
¨ Full ELBO
¨ Lite ELBO
• Full ELBO can suffer from exposure bias at latent space, i.e. the
decoder only sees z sampled from q at training time and never
experiences z sampled from p, which is always used at testing time.
• It sets the posterior network the same as our encoder,
• Add the additional regularization term
that encourages the posterior be similar to certain prior distribution
: a neural network that approximate the posterior distribution
and are achieved by
17. 17
Experiment Settings
¨ Multi-Woz dataset
• 10438 dialogs on 6 different domains.
• This paper focuses on the Dialog-Context-to-text Generation task.
• It assumes that the model has access to the ground-truth belief state
and is asked to generate the next response given user utterance.
Budzianowski, Paweł, et al. "Multiwoz-a large-scale multi-domain wizard-of-oz dataset for task-oriented dialogue
modelling." arXiv preprint arXiv:1810.00278 (2018).
18. 18
Multi-turn goal-oriented dialog (MultiWoz)
"usr": [ "am looking for a place to to stay that has [value_pricerange] price
range it should be in a type of hotel",
"no , i just need to make sure it s [value_pricerange] . oh , and i need
parking",
"yes , please . [value_count] people [value_count] nights starting on
[value_day] .",
"how about only [value_count] nights .",
"no , that will be all . goodbye ."
]
"sys": [ "okay , do you have a specific area you want to stay in ?",
"i found [value_count] [value_pricerange] hotel for you that include -
s parking . do you like me to book it ?",
"i am sorry but i was not able to book that for you for [value_day] . is
there another day you would like to stay or perhaps a shorter stay ?",
" booking was successful . reference number is [hotel_reference] .
anything else i can do for you ? ",
" thank you for using our services . "
],
"bs” : belief state label (94 dimension)
“db” : data base label (30 dimension)
20. 20
Language Constrained Reward(LCR) curve
¨ ROC-style curve to visualize the trade-off between high task
success and being faithful human language.
• It records two measures:
(1) Perplexity of a given model on the test data
(2) this model’s average cumulative task reward
• It creates a 2D plots where the x-axis is the maximum PPL allowed,
and the y-axis is the best achievable reward with the PPL budget.
Gaussian is under ”without RL”
21. 21
Summary
¨ End-to-end models that latent actions be expressive enough to capture
response semantics in complex domains, decoupling the discourse-level
decision making process from natural language generation.
¨ A novel training objective(lite ELBO) that outperforms the typical
evidence lower bound
¨ Attention mechanism for integrating discrete latent variables(LiteAttnCat)
in the decoder to better model long responses.