Filters








15,164 Hits in 8.1 sec

Joint Effects of Context and User History for Predicting Online Conversation Re-entries [article]

Xingshan Zeng, Jing Li, Lu Wang, Kam-Fai Wong
2019 arXiv   pre-print
In order to help users better engage with each other online, we study a challenging problem of re-entry prediction foreseeing whether a user will come back to a conversation they once participated in.  ...  Specifically, we propose a neural framework with three main layers, each modeling context, user history, and interactions between them, to explore how the conversation context and user chatting history  ...  We thank the three anonymous reviewers for the insightful suggestions on various aspects of this work.  ... 
arXiv:1906.01185v1 fatcat:ixh2tq447ne33owwstlgxbi2vm

Joint Effects of Context and User History for Predicting Online Conversation Re-entries

Xingshan Zeng, Jing Li, Lu Wang, Kam-Fai Wong
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
In order to help users better engage with each other online, we study a challenging problem of re-entry prediction foreseeing whether a user will come back to a conversation they once participated in.  ...  Specifically, we propose a neural framework with three main layers, each modeling context, user history, and interactions between them, to explore how the conversation context and user chatting history  ...  We thank the three anonymous reviewers for the insightful suggestions on various aspects of this work.  ... 
doi:10.18653/v1/p19-1270 dblp:conf/acl/ZengLWW19 fatcat:442rryiebjb7rjnanlr5dxy3bu

Successful New-entry Prediction for Multi-Party Online Conversations via Latent Topics and Discourse Modeling [article]

Lingzhi Wang, Jing Li, Xingshan Zeng, Kam-Fai Wong
2022 arXiv   pre-print
in a multi-party conversation (henceforth Successful New-entry Prediction).  ...  from newcomer's chatting history and conversation's ongoing context.  ...  the prediction of user responses [3, 7] , thread-ending turns [26] , and re-entry behavior [54] , etc.  ... 
arXiv:2108.06975v3 fatcat:kt37vjplcjbpxjjlbmxiptz7ay

Re-entry Prediction for Online Conversations via Self-Supervised Learning [article]

Lingzhi Wang, Xingshan Zeng, Huang Hu, Kam-Fai Wong, Daxin Jiang
2021 arXiv   pre-print
In this paper, we propose three interesting and well-founded auxiliary tasks, namely, Spread Pattern, Repeated Target user, and Turn Authorship, as the self-supervised signals for re-entry prediction.  ...  Re-entry prediction task is thus proposed to help people keep track of the discussions which they wish to continue.  ...  We thank the three anonymous reviewers for the insightful suggestions on various aspects of this work.  ... 
arXiv:2109.02020v1 fatcat:7ujnns7wmzeafb7xgy6x5r7ewq

Modeling Global and Local Interactions for Online Conversation Recommendation

Xingshan Zeng, Jing Li, Lingzhi Wang, Kam-Fai Wong
2022 ACM Transactions on Information Systems (TOIS; Formerly: ACM Transactions on Office Information Systems)  
The popularity of social media platforms results in a huge volume of online conversations produced every day.  ...  To help users better engage in online conversations, this article presents a novel framework to automatically recommend conversations to users based on what they said and how they behaved in their chatting  ...  ACKNOWLEDGMENTS We thank the reviewers for the insightful suggestions on various aspects of this work.  ... 
doi:10.1145/3473970 fatcat:cufyoyuegbferldx2fjohe67gq

User Response Prediction in Online Advertising [article]

Zhabiz Gharibshah, Xingquan Zhu
2021 arXiv   pre-print
What are the parties involved in the online digital advertising eco-systems? What type of data are available for user response prediction?  ...  In this survey, we provide a comprehensive review of user response prediction in online advertising and related recommender applications.  ...  They analyzed the effect of elapsed time as a feature for conversion rate prediction and using targeting and retargeting 2 paradigm for different users in online advertising systems.  ... 
arXiv:2101.02342v2 fatcat:clgefamcd5fmbeg5ephizy3zqu

Parsing Natural Language Conversations using Contextual Cues

Shashank Srivastava, Amos Azaria, Tom Mitchell
2017 Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence  
However, understanding conversations also requires an understanding of conversational context and discourse structure across sentences.  ...  We create a dataset for semantic parsing of conversations, consisting of 113 real-life sequences of interactions of human users with an automated email assistant.  ...  InMind project and by the Samsung GRO program. Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence  ... 
doi:10.24963/ijcai.2017/571 dblp:conf/ijcai/SrivastavaAM17 fatcat:othzbjb3sneabi2dvectasym2q

Multimedia Semantics: Interactions Between Content and Community

Hari Sundaram, Lexing Xie, Munmun De Choudhury, Yu-Ru Lin, Apostol Natsev
2012 Proceedings of the IEEE  
For each case, we present an overview of recent work and review the state of the art.  ...  We examine the inter-relationship between content and social context through the prism of three key questions. First, how do we extract context in which social interactions occur?  ...  We extract conversational themes for determining the "interestingness" of online conversations.  ... 
doi:10.1109/jproc.2012.2191529 fatcat:tayhtgkr6jfz7l2efpic4ygaqy

Online Advertising Response Models: Incorporating Multiple Creatives and Impression Histories

Michael Braun, Wendy W. Moe
2011 Social Science Research Network  
We also allow for the accumulation and decay of advertising effects, as well as ad wear-out and restoration effects.  ...  We propose a model that evaluates the effectiveness of each creative in a campaign given the targeted individual's ad impression history, as characterized by the timing and mix of previously seen ad creatives  ...  context of an impression history.  ... 
doi:10.2139/ssrn.1896486 fatcat:bqce3qgt5vfejh7fhtvjkwhbpu

UNITER-Based Situated Coreference Resolution with Rich Multimodal Input [article]

Yichen Huang, Yuchen Wang, Yik-Cheung Tam
2021 arXiv   pre-print
We present our work on the multimodal coreference resolution task of the Situated and Interactive Multimodal Conversation 2.0 (SIMMC 2.0) dataset as a part of the tenth Dialog System Technology Challenge  ...  We propose a UNITER-based model utilizing rich multimodal context such as textual dialog history, object knowledge base and visual dialog scenes to determine whether each object in the current scene is  ...  Table 1: Examples of knowledge base entry templates for log.  ... 
arXiv:2112.03521v1 fatcat:v7aoucyybfgnpju5hu4kvovdpu

Towards Expressive Communication with Internet Memes: A New Multimodal Conversation Dataset and Benchmark [article]

Zhengcong Fei, Zekang Li, Jinchao Zhang, Yang Feng, Jie Zhou
2021 arXiv   pre-print
As a kind of new expression elements, Internet memes are popular and extensively used in online chatting scenarios since they manage to make dialogues vivid, moving, and interesting.  ...  The dataset consists of ∼45K Chinese conversations with ∼606K utterances.  ...  For the Internet meme selection, we use R n @k as the evaluation metrics where k is set to 1,2,5, and the model prediction is considered to be correct only if the true response is among the top-k entries  ... 
arXiv:2109.01839v1 fatcat:p2zd2drhcrfcrlmw23nka7jt3m

Adaptive Query Recommendation Techniques for Log Files Mining to Analysis User's Session Pattern

Durga Choudhary, Subhash Chandra
2016 International Journal of Computer Applications  
Generally, IP, date and time of the request, result for the request (with code), transaction size, protocol, request description, browser and operating system used by the user are some of the important  ...  There is a wide variety of logs to stock knowledge about the search patterns of the users.  ...  Science And Engineering, R.C.E.W Bankrota, and Jaipur for providing necessary support and lab facility.  ... 
doi:10.5120/ijca2016908085 fatcat:ugjknb7vnfcrrjgusfpoqz553e

Impact of TNF inhibitor therapy on joint replacement rates in rheumatoid arthritis: a matched cohort analysis of BSRBR-RA UK registry data

Samuel Hawley, M Sanni Ali, René Cordtz, Lene Dreyer, Christopher J Edwards, Nigel K Arden, Cyrus Cooper, Andrew Judge, Kimme Hyrich, Daniel Prieto-Alhambra
2019 Rheumatology  
Previous ecological data suggest a decline in the need for joint replacements in RA patients following the introduction of TNF inhibitor (TNFi) therapy, although patient-level data are lacking.  ...  Our primary aim was to estimate the association between TNFi use and subsequent incidence of total hip replacement (THR) and total knee replacement.  ...  license for the current study, and so are not publicly available.  ... 
doi:10.1093/rheumatology/key424 pmid:30649521 pmcid:PMC6587915 fatcat:xy2b7xr4izb4xcz2ibchehzzy4

TOD-DA: Towards Boosting the Robustness of Task-oriented Dialogue Modeling on Spoken Conversations [article]

Xin Tian, Xinxian Huang, Dongfeng He, Yingzhan Lin, Siqi Bao, Huang He, Liankai Huang, Qiang Ju, Xiyuan Zhang, Jian Xie, Shuqi Sun, Fan Wang (+2 others)
2021 arXiv   pre-print
With such designs, our approach ranked first in both tasks of DSTC10 Track2, a benchmark for task-oriented dialogue modeling on spoken conversations, demonstrating the superiority and effectiveness of  ...  and speech recognition errors in diverse granularities for bridging the gap between written and spoken conversations.  ...  Joint Goal Value Prediction None Prediction Rank Team ID Entry ID Slot Accuracy  ... 
arXiv:2112.12441v1 fatcat:bj5wpbulkva43h3tx5wnwhxnee

Open social learning communities

Ashwin Ram, Hua Ai, Preetha Ram, Saurav Sahay
2011 Proceedings of the International Conference on Web Intelligence, Mining and Semantics - WIMS '11  
With the advent of open education resources, social networking technologies and new pedagogies for online and blended learning, we are in the early stages of a significant disruption in current models  ...  of education.  ...  Advice: Users seek advice on several topics, mostly college entry, essays, career advice, course advice, and seek mentoring TECHNICAL SOLUTIONS 4.1 Real-time Conversation OpenStudy supports real-time  ... 
doi:10.1145/1988688.1988691 dblp:conf/wims/RamARS11 fatcat:bi6j33anrvcutgmi3d47v3qjoy
« Previous Showing results 1 — 15 out of 15,164 results