Neural Dialog Systems

Notes:

A neural dialog model is a type of machine learning model that is used to generate responses to user inputs in a natural language dialog system. Neural dialog models are based on artificial neural networks, which are computational systems that are inspired by the structure and function of the human brain. Neural dialog models are trained on large datasets of dialogs between human users, and they learn to generate responses that are similar to the responses that a human would provide in a given context.

In a neural dialog system, the neural dialog model is used to generate responses to user inputs in real-time. The system receives the user’s input, processes it using the neural dialog model, and then generates a response that is intended to continue the conversation in a natural and appropriate way. The neural dialog model is able to generate a wide range of potential responses, and the system selects the most appropriate response based on the context of the conversation and the user’s previous inputs. By using a neural dialog model, a dialog system can provide more natural, human-like responses to user inputs, improving the overall quality and effectiveness of the conversation.

Resources:

  • cim.mcgill.ca .. centre for intelligent machines, mcgill university

References:

See also:

Autoencoder & Dialog Systems 2016 | CNN (Convolutional Neural Network) & Dialog Systems 2016 | Language Modeling & Dialog Systems 2017 | Neural Conversation Models 2016 | Neural Network & Dialog Systems 2016 | NMT (Neural Machine Translation) & Dialog Systems 2016 | RNN (Recurrent Neural Network) & Dialog Systems 2016 | Sequence-to-Sequence (seq2seq) & Dialog Systems 2016 | Word2vec & Dialog Systems 2016

End-to-end task-completion neural dialogue systems
X Li, YN Chen, L Li, J Gao – arXiv preprint arXiv:1703.01008, 2017 – arxiv.org
Abstract: This paper presents an end-to-end learning framework for task-completion neural dialogue systems, which leverages supervised and reinforcement learning with various deep-learning models. The system is able to interface with a structured database, and

Conditional generation and snapshot learning in neural dialogue systems
TH Wen, M Gasic, N Mrksic… – arXiv preprint arXiv …, 2016 – arxiv.org
Abstract: Recently a variety of LSTM-based conditional language models (LM) have been applied across a range of language generation tasks. In this work we study various model architectures and different ways to represent and aggregate the source information in an

Incorporating unstructured textual knowledge sources into neural dialogue systems
R Lowe, N Pow, I Serban, L Charlin… – … Systems Workshop on …, 2015 – blueanalysis.com
Abstract We present initial methods for incorporating unstructured external textual information into neural dialogue systems for predicting the next utterance of a user in a two-party chat conversation. The main objective is to leverage additional information about the

On the evaluation of dialogue systems with next utterance classification
R Lowe, IV Serban, M Noseworthy, L Charlin… – arXiv preprint arXiv …, 2016 – arxiv.org
… In Pro- ceedings of SIGDIAL. R. Lowe, N. Pow, IV Serban, L. Charlin, and J. Pineau. 2015b. Incorporating unstructured textual knowledge sources into neural dialogue systems. In NIPS Workshop on Machine Learning for Spoken Language Understanding …

Training end-to-end dialogue systems with the ubuntu dialogue corpus
RT Lowe, N Pow, IV Serban, L Charlin… – Dialogue & …, 2017 – dad.uni-bielefeld.de
Page 1. Dialogue & Discourse 8(1) (2017) 31–65 doi: 10.5087/dad.2017.102 Training End-to-End Dialogue Systems with the Ubuntu Dialogue Corpus Ryan Lowe RYAN.LOWE@ CS.MCGILL.CA School of Computer Science, McGill University Nissan Pow …

Neural text generation from structured data with application to the biography domain
R Lebret, D Grangier, M Auli – arXiv preprint arXiv:1603.07771, 2016 – arxiv.org
… to generate it. This mechanism is inspired by recent work on attention based word copying for neural machine translation (Luong et al., 2015) as well as delexicalization for neural dialog systems (Wen et al., 2015). It also builds …

An end-to-end trainable neural network model with belief tracking for task-oriented dialog
B Liu, I Lane – arXiv preprint arXiv:1708.05956, 2017 – arxiv.org
… Our proposed model suc- cessfully predicts 52.8% of the true system responses, outper- forming prior end-to-end trainable neural dialog systems. Table 5: Performance of the proposed model in per-response accuracy comparing to previous approaches …

How to make context more useful? an empirical study on context-aware neural conversational models
Z Tian, R Yan, L Mou, Y Song, Y Feng… – Proceedings of the 55th …, 2017 – aclweb.org
… pooling or con- catenation. • RQ2. What is the effect of context on neural dialog systems? We find context information is useful to neural conversational models. It yields longer, more informative and diversi- fied replies. To sum up …

Semantic refinement gru-based neural language generation for spoken dialogue systems
VK Tran, LM Nguyen – arXiv preprint arXiv:1706.00134, 2017 – arxiv.org
… 670–680. [15] R. Lowe, N. Pow, I. Serban, L. Charlin, and J. Pineau, “Incorporating unstructured textual knowledge sources into neural dialogue systems,” in NIPS Workshop MLNLU, 2015. [16] T. Mikolov, “Recurrent neural network based language model.” 2010 …

Natural language generation in dialogue using lexicalized and delexicalized data
S Sharma, J He, K Suleman, H Schulz… – arXiv preprint arXiv …, 2016 – arxiv.org
… In: CoRR abs/1603.08023. Lowe, Ryan et al. (2015). “Incorporating Unstructured Textual Knowledge Sources into Neural Dialogue Systems”. In: NIPS Workshop on Machine Learning for Spoken Language Understanding. Mikolov, Tomas et al. (2010) …

Iterative policy learning in end-to-end trainable task-oriented neural dialog models
B Liu, I Lane – arXiv preprint arXiv:1709.06136, 2017 – arxiv.org
… game. Our contribution in this work is two-fold. Firstly, we pro- pose an iterative dialog policy learning method that jointly optimizes the dialog agent and the user simulator in end-to- end trainable neural dialog systems. Secondly …

Investigation of Language Understanding Impact for Reinforcement Learning Based Dialogue Systems
X Li, YN Chen, L Li, J Gao, A Celikyilmaz – arXiv preprint arXiv:1703.07055, 2017 – arxiv.org
… In this paper, we investigate how the language understanding module influences the dialogue system perfor- mance by conducting a series of systematic experiments on a task-oriented neural dialogue system in a reinforcement learn- ing based setting …

A user simulator for task-completion dialogues
X Li, ZC Lipton, B Dhingra, L Li, J Gao… – arXiv preprint arXiv …, 2016 – arxiv.org
… In NIPS, 2014. [22] Tsung-Hsien Wen, Milica Gašic, Nikola Mrkšic, Lina M. Rojas-Barahona, Pei-Hao Su, Stefan Ultes, David Vandyke, and Steve Young. Conditional generation and snapshot learning in neural dialogue systems. EMNLP, 2016 …

Augmenting end-to-end dialog systems with commonsense knowledge
T Young, E Cambria, I Chaturvedi, M Huang… – arXiv preprint arXiv …, 2017 – arxiv.org
… Lowe, R.; Pow, N.; Charlin, L.; Pineau, J.; and Serban, IV 2015a. Incorporating unstructured textual knowledge sources into neural dialogue systems. In Machine Learning for Spoken Language Understanding and Interaction, NIPS 2015 Workshop …

Latent intention dialogue models
TH Wen, Y Miao, P Blunsom, S Young – arXiv preprint arXiv:1705.10229, 2017 – arxiv.org
Page 1. Latent Intention Dialogue Models Tsung-Hsien Wen 1 * Yishu Miao 2 * Phil Blunsom 2 Steve Young 1 Abstract Developing a dialogue agent that is capable of making autonomous decisions and communicat- ing by natural …

Online adaptation of an attention-based neural network for natural language generation
M Riou, B Jabaian, S Huet… – Proc. Interspeech …, 2017 – pdfs.semanticscholar.org
… 0036). 3347 Page 5. 8. References [1] T.-H. Wen, M. Gašic, N. Mrkšic, LMR Barahona, P.-H. Su, S. Ultes, D. Vandyke, and S. Young, “Conditional generation and snapshot learning in neural dialogue systems,” in EMNLP, 2016. [2 …

End-to-End Optimization of Task-Oriented Dialogue Model with Deep Reinforcement Learning
B Liu, G Tur, D Hakkani-Tur, P Shah, L Heck – arXiv preprint arXiv …, 2017 – arxiv.org
… oriented dialog. In Interspeech, 2017. [13] Xuijun Li, Yun-Nung Chen, Lihong Li, and Jianfeng Gao. End-to-end task-completion neural dialogue systems. arXiv preprint arXiv:1703.01008, 2017. [14] Bing Liu and Ian Lane. Iterative …

Learning through dialogue interactions
J Li, AH Miller, S Chopra, MA Ranzato… – arXiv preprint arXiv …, 2016 – arxiv.org
… Higgins et al., 2002; Latham, 1997; Werts et al., 1995). In the context of dialogue, with the recent popularity of deep learning models, many neural dialogue systems have been proposed. These include the chit-chat type end-to-end …

Towards Neural Speaker Modeling in Multi-Party Conversation: The Task, Dataset, and Models
Z Meng, L Mou, Z Jin – arXiv preprint arXiv:1708.03152, 2017 – arxiv.org
… Abstract Neural network-based dialog systems are attracting increasing attention in both academia and industry. Recently, re- searchers have begun to realize the impor- tance of speaker modeling in neural dialog systems, but there lacks established tasks and datasets …

Speaker role contextual modeling for language understanding and dialogue policy learning
TC Chi, PC Chen, SY Su, YN Chen – arXiv preprint arXiv:1710.00164, 2017 – arxiv.org
… arXiv preprint arXiv:1412.6980 . Xuijun Li, Yun-Nung Chen, Lihong Li, Jianfeng Gao, and Asli Celikyilmaz. 2017. End-to-end task- completion neural dialogue systems. In Proceedings of The 8th International Joint Conference on Natu- ral Language Processing …

A review of evaluation techniques for social dialogue systems
AC Curry, H Hastie, V Rieser – Proceedings of the 1st ACM SIGCHI …, 2017 – dl.acm.org
… 2.1 Word-Overlap Metrics Word-overlap metrics, such as BLEU [9] and ROUGE [4], are bor- rowed from Machine Translation (MT) and Summarisation and have been widely been used to evaluate neural dialogue system output, as reported in, for example [3, 11] …

Generating high-quality and informative conversation responses with sequence-to-sequence models
Y Shao, S Gouws, D Britz, A Goldie, B Strope… – Proceedings of the …, 2017 – aclweb.org
Page 1. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2210–2219 Copenhagen, Denmark, September 7–11, 2017. cO2017 Association for Computational Linguistics Generating …

Composite Task-Completion Dialogue System via Hierarchical Deep Reinforcement Learning
B Peng, X Li, L Li, J Gao, A Celikyilmaz, S Lee… – arXiv preprint arXiv …, 2017 – arxiv.org
… considering the joint constraints between domains. 3 Neural Dialogue System As illustrated in Figure 1, a typical task- completion dialogue system consists of the follow- ing components: Natural Language Understanding (NLU): given …

Character-Level Neural Translation for Multilingual Media Monitoring in the SUMMA Project
G Barzdins, S Renals, D Gosko – arXiv preprint arXiv:1604.01221, 2016 – arxiv.org
… For stream segmentation into the stories it is possible to utilize the exceptional generalization and memorization capacity of the neural networks, which is already applied in the neural dialogue systems such as Gmail Smart Replies (Corrado, 2015; Vinyals&Le, 2015) …

Affective Neural Response Generation
N Asghar, P Poupart, J Hoey, X Jiang, L Mou – arXiv preprint arXiv …, 2017 – arxiv.org
Page 1. Affective Neural Response Generation Nabiha Asghar†, Pascal Poupart†, Jesse Hoey†, Xin Jiang‡, Lili Mou† †Cheriton School of Computer Science, University of Waterloo, Canada {nasghar,ppoupart,jhoey}@uwaterloo …

Answerer in Questioner’s Mind for Goal-Oriented Visual Dialogue
SW Lee, YJ Heo, BT Zhang – arXiv preprint arXiv:1802.03881, 2018 – arxiv.org
… di- alogue. We further use AQM as a tool for analyz- ing the mechanism of deep reinforcement learning approach and discuss the future direction of prac- tical goal-oriented neural dialogue systems. 1. Introduction Goal-oriented …

Dynamic Time-Aware Attention to Speaker Roles and Contexts for Spoken Language Understanding
PC Chen, TC Chi, SY Su, YN Chen – arXiv preprint arXiv:1710.00165, 2017 – arxiv.org
… 484–495. [4] Xiujun Li, Yun-Nung Chen, Lihong Li, Jianfeng Gao, and Asli Celikyilmaz, “End-to-end task-completion neural dialogue systems,” in Proceedings of The 8th In- ternational Joint Conference on Natural Language Pro- cessing, 2017 …

Open-Domain Neural Dialogue Systems
YN Chen, J Gao – Proceedings of the IJCNLP 2017, Tutorial Abstracts, 2017 – aclweb.org
Until recently, the goal of developing opendomain dialogue systems that not only emulate human conversation but fulfill complex tasks, such as travel planning, seemed elusive. However, we start to observe promising results in the last few years as the large amount of

Research data supporting” Conditional Generation and Snapshot Learning in Neural Dialogue Systems”
TH Wen, N Mrksic, S Young – 2016 – repository.cam.ac.uk
Cambridge restaurant dialogue domain dataset collected for developing neural network based dialogue systems. The two papers published based on this dataset are: 1. A Network-based End-to-End Trainable Task-oriented Dialogue System 2. Conditional Generation and

Task-oriented Neural Dialogue Systems
THS Wen – mi.eng.cam.ac.uk
M: Hello, welcome to the Cambridge dialogue system, What kind of food would you like? H: Yeah I want to find a restaurant that serves European food. M: Hotel du Vin and Bistro is a nice place. It serves European food. H: Uh what is the address and phone number? M: Hotel

Why Do Neural Dialog Systems Generate Short and Meaningless Replies? A Comparison between Dialog and Translation
B Wei, S Lu, L Mou, H Zhou, P Poupart, G Li… – arXiv preprint arXiv …, 2017 – arxiv.org
Abstract: This paper addresses the question: Why do neural dialog systems generate short and meaningless replies? We conjecture that, in a dialog system, an utterance may have multiple equally plausible replies, causing the deficiency of neural networks in the dialog

Domain Aware Neural Dialog System
S Choudhary, P Srivastava, L Ungar… – arXiv preprint arXiv …, 2017 – arxiv.org
Abstract: We investigate the task of building a domain aware chat system which generates intelligent responses in a conversation comprising of different domains. The domain, in this case, is the topic or theme of the conversation. To achieve this, we present DOM-Seq2Seq, a

McGill Reasoning & Learning Lab: Research Overview
R Lowe – cs.mcgill.ca
… Single hyperparameter controls accuracy/speed trade-off Figure: Probability distributions of the dropout policy for class 0 (left) and class 1 (right) Page 12. Neural Dialogue Systems Page 13. End-to-End Dialogue Systems • A single model trained directly on conversational data …

Collaboration-based User Simulation for Goal-oriented Dialog Systems
D Didericksen, ORKSL Zhou, J Kramer – alborz-geramifard.com
… [21] Xiujun Li, Yun-Nung Chen, Lihong Li, Jianfeng Gao, and Asli Celikyilmaz. End-to-end task-completion neural dialogue systems. In Proceedings of the International Joing Conference on Natural Language Processing (IJCNLP), 2017 …

Sequence-to-Sequence Learning for End-to-End Dialogue Systems
J Van Landeghem – 2016 – researchgate.net
… [9] A Network-based End-to-End Trainable Task-oriented Dialogue System [10] Incorporating Unstructured Textual Knowledge Sources into Neural Dialogue Systems [11] A Neural Network Approach to Context-Sensitive Generation of Conversational Responses …

Fine Grained Knowledge Transfer for Personalized Task-oriented Dialogue Systems
K Mo, Y Zhang, Q Yang, P Fung – arXiv preprint arXiv:1711.04079, 2017 – arxiv.org
Page 1. Fine Grained Knowledge Transfer for Personalized Task-oriented Dialogue Systems Kaixiang Mo† and Yu Zhang† and Qiang Yang† and Pascale Fung‡ Hong Kong University of Science and Technology, Hong Kong …

A Survey of Task-oriented Dialogue Systems
K Mo – 2017 – cse.ust.hk
Page 1. A Survey of Task-oriented Dialogue Systems HKUST CSE PhD Qualifying Examination Kaixiang Mo Committee Members: Prof. Qiang Yang (Supervisor), Dr. Yangqiu Song (Chairperson), Dr. Xiaojuan Ma, Prof. Pascale Fung (ECE) 16th January, 2017 1 Page 2 …

Goal-Oriented Chatbot Dialog Management Bootstrapping with Transfer Learning
V Ilievski, C Musat, A Hossmann… – arXiv preprint arXiv …, 2018 – arxiv.org
… A user simulator for task-completion dialogues. arXiv preprint arXiv:1612.05688, 2016. [Li et al., 2017] Xuijun Li, Yun-Nung Chen, Lihong Li, and Jianfeng Gao. End-to-end task-completion neural dialogue systems. arXiv preprint arXiv:1703.01008, 2017 …

Neural Conversational Model with Mutual Information Ranking
H Ho, C Zhu – stanford.edu
… 2 Previous Work Researchers have developed many neural dialogue systems in the past. The … In their paper ”A Neural Conversational Model”, Vinyals et. al [8] demonstrate their neural dialogue system on several datasets. In …

A Survey on Dialogue Systems: Recent Advances and New Frontiers
H Chen, X Liu, D Yin, J Tang – arXiv preprint arXiv:1711.01731, 2017 – arxiv.org
… [36] trained the end-to-end system as a task completion neural dialogue system, where its final goal is to complete a task, such as movie-ticket booking. Task-oriented systems usually need to query outside knowl- edge base …

Deep Learning for Dialogue Systems
YN Chen, A Celikyilmaz, D Hakkani-Tür – Proceedings of ACL 2017 …, 2017 – aclweb.org
… LM NLG – Phrase-based NLG – RNN-LM NLG – Semantic Conditioned LSTM – Structural NLG – Contextual NLG 3. Evaluation [10 min.] • Crowdsourcing • User simulation 4. Recent Trends on Learning Dialogues [45 min.] • End-to-end neural dialogue systems – Chit-chat …

Proceedings of the IJCNLP 2017, Tutorial Abstracts
S Kurohashi, M Strube – Proceedings of the IJCNLP 2017, Tutorial …, 2017 – aclweb.org
… 3 Open-Domain Neural Dialogue Systems Yun-Nung Chen and Jianfeng Gao … 9:00–12:30 Multilingual Vector Representations of Words, Sentences, and Documents Gerard de Melo 9:00–12:30 Open-Domain Neural Dialogue Systems Yun-Nung Chen and Jianfeng Gao …

Learning Robust Dialog Policies in Noisy Environments
M Fazel-Zarandi, SW Li, J Cao, J Casale… – arXiv preprint arXiv …, 2017 – arxiv.org
… arXiv preprint arXiv:1612.05688. [19] Li, X.; Chen, YN; Li, L.; Gao, J.; Celikyilmaz, A. (2017). End-to-End Task-Completion Neural Dialogue Systems, in Proceedings of The 8th International Joint Conference on Natural Language Processing. [20] Mahrt, T. (2016). PyAcoustics …

Personalization in Goal-Oriented Dialog
CK Joshi, F Mi, B Faltings – arXiv preprint arXiv:1706.07503, 2017 – arxiv.org
… oriented scenarios. End-to-end trained neural dialog systems are an important line of research for such generalized dialog models as they do not resort to any situation-specific handcrafting of rules. Modelling personalization …

Customized Nonlinear Bandits for Online Response Selection in Neural Conversation Models
B Liu, T Yu, I Lane, OJ Mengshoel – arXiv preprint arXiv:1711.08493, 2017 – arxiv.org
Page 1. Customized Nonlinear Bandits for Online Response Selection in Neural Conversation Models Bing Liu?, Tong Yu?, Ian Lane, Ole J. Mengshoel Electrical and Computer Engineering, Carnegie Mellon University {liubing …

Proceedings of the First Workshop on Neural Machine Translation
T Luong, A Birch, G Neubig, A Finch – … of the First Workshop on Neural …, 2017 – aclweb.org
… Vyas and Xing Niu x Page 11. Friday, August 4, 2017 (continued) Domain Aware Neural Dialogue System (extended abstract) Sajal Choudhary, Prerna Srivastava, Joao Sedoc and Lyle Ungar Interactive Beam Search for Visualizing …

Emotional Human-Machine Conversation Generation Based on Long Short-Term Memory
X Sun, X Peng, S Ding – Cognitive Computation, 2017 – Springer
Page 1. Cognitive Computation https://doi.org/10.1007/s12559-017-9539-4 Emotional Human-Machine Conversation Generation Based on Long Short-Term Memory Xiao Sun1,2 · Xiaoqi Peng2 · Shuai Ding1 Received: 10 …

Sample efficient deep reinforcement learning for dialogue systems with large action spaces
G Weisz, P Budzianowski, PH Su, M Gaši? – arXiv preprint arXiv …, 2018 – arxiv.org
Page 1. 1 Sample efficient deep reinforcement learning for dialogue systems with large action spaces Gellért Weisz, Pawe? Budzianowski, Student Member, IEEE, Pei-Hao Su, Student Member, IEEE, and Milica Gašic, Member, IEEE …

Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
G Kondrak, T Watanabe – Proceedings of the Eighth International Joint …, 2017 – aclweb.org
… Joshi . . . . . 723 End-to-End Task-Completion Neural Dialogue Systems Xiujun Li, Yun-Nung Chen, Lihong Li, Jianfeng Gao and Asli Celikyilmaz . . . . . 733 End …

Evorus: A Crowd-powered Conversational Assistant Built to Automate Itself Over Time
THK Huang, JC Chang, JP Bigham – arXiv preprint arXiv:1801.02668, 2018 – arxiv.org
Page 1. Evorus: A Crowd-powered Conversational Assistant Built to Automate Itself Over Time Ting-Hao (Kenneth) Huang, Joseph Chee Chang, and Jeffrey P. Bigham Language Technologies Institute and Human-Computer …

Improving Mild Cognitive Impairment Prediction via Reinforcement Learning and Dialogue Simulation
F Tang, K Lin, I Uchendu, HH Dodge, J Zhou – arXiv preprint arXiv …, 2018 – arxiv.org
Page 1. Improving Mild Cognitive Impairment Prediction via Reinforcement Learning and Dialogue Simulation Fengyi Tang1, Kaixiang Lin1, Ikechukwu Uchendu1, Hiroko H. Dodge2,3, Jiayu Zhou1 1Computer Science and Engineering …

Dialog for natural language to code
S Chaurasia – 2017 – repositories.lib.utexas.edu
Page 1. Copyright by Shobhit Chaurasia 2017 Page 2. The Thesis Committee for Shobhit Chaurasia certifies that this is the approved version of the following thesis: Dialog for Natural Language to Code Approved by Supervising Committee: Raymond J. Mooney, Supervisor …

Reinforced Self-Attention Network: a Hybrid of Hard and Soft Attention for Sequence Modeling
T Shen, T Zhou, G Long, J Jiang, S Wang… – arXiv preprint arXiv …, 2018 – arxiv.org
Page 1. Reinforced Self-Attention Network: a Hybrid of Hard and Soft Attention for Sequence Modeling Tao Shen†, Tianyi Zhou‡, Guodong Long†, Jing Jiang†, Sen Wang§, Chengqi Zhang† †Centre for Artificial Intelligence, School …

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
J Su, K Duh, X Carreras – Proceedings of the 2016 Conference on …, 2016 – aclweb.org
Page 1. November 1–5, 2016 Austin, Texas, USA emnlp2016 CONFERENCE PROCEEDINGS Conference on Empirical Methods in Natural Language Processing www.emnlp2016.net Page 2. Page 3. EMNLP 2016 gratefully …

Centre For Intelligent Machines (CIM)
JJ Clark – pdfs.semanticscholar.org
Page 1. CENTRE FOR INTELLIGENT MACHINES (CIM) Centre de recherche sur les machines intelligentes www.cim.mcgill.ca Annual Report 2015 Director Professor James J. Clark Page 2. McGill Centre for Intelligent Machines (CIM) Annual Report 2015 2 Table of Contents …

A novel X-FEM based fast computational method for crack propagation
Z Cheng, H Wang, PMB Vitanyi, N Chater, M Barzegari… – arxiv.org
Attention Submitters: The submission interface will be unavailable due to maintenance for ~2 hours starting 04:00 ET (09:00 UTC) on Thursday, January 18, 2018 …