Filters








293 Hits in 14.3 sec

Don't get Lost in Negation: An Effective Negation Handled Dialogue Acts Prediction Algorithm for Twitter Customer Service Conversations [article]

Mansurul Bhuiyan, Amita Misra, Saurabh Tripathy, Jalal Mahmud, Rama Akkiraju
2018 arXiv   pre-print
In this work, we developed an SVM-based dialogue acts prediction algorithm for Twitter customer service conversations where negation handling is an integral part of the end-to-end solution.  ...  In the last several years, Twitter is being adopted by the companies as an alternative platform to interact with the customers to address their concerns.  ...  CONCLUSION In this work, we study effectiveness of handling negation in dialogue acts prediction task in twitter based customer care conversation.  ... 
arXiv:1807.06107v1 fatcat:wc3jp7qayrhtdmzzgyfv2j7rxi

Beneath the Tip of the Iceberg: Current Challenges and New Directions in Sentiment Analysis Research [article]

Soujanya Poria, Devamanyu Hazarika, Navonil Majumder, Rada Mihalcea
2020 arXiv   pre-print
Given its saturation in specific subtasks -- such as sentiment polarity classification -- and datasets, there is an underlying perception that this field has reached its maturity.  ...  We analyze the significant leaps responsible for its current relevance. Further, we attempt to chart a possible course for this field that covers many overlooked and unanswered questions.  ...  -A19E2b0098, Project name -K-EMERGE: Knowledge Extraction, Modelling, and Explainable Reasoning for General Expertise.  ... 
arXiv:2005.00357v5 fatcat:gjzglyhtvvc3xnuaeqjocbp57u

Neural Approaches to Conversational AI [article]

Jianfeng Gao, Michel Galley, Lihong Li
2019 arXiv   pre-print
The present paper surveys neural approaches to conversational AI that have been developed in the last few years.  ...  We group conversational systems into three categories: (1) question answering agents, (2) task-oriented dialogue agents, and (3) chatbots.  ...  Anecdotally, the authors ofLi et al. (2016a, pc) found that a Twitter dataset from 2013 had lost about 25% of its tweets by 2015 due to retracted tweets and Twitter account suspensions.9 For example,  ... 
arXiv:1809.08267v3 fatcat:j57xlm4ogferdnrpfs4f2jporq

Content Moderation Remedies

Eric Goldman
2021 Michigan Technology Law Review  
It then provides a normative framework to help Internet services and regulators navigate these remedial options to address the many difficult tradeoffs involved in content moderation.  ...  This Article addresses a critical but underexplored aspect of content moderation: if a user's online content or actions violate an Internet service's rules, what should happen next?  ...  Internet services may not invest adequately in determining an appropriate remedy because customized/"artisanal" remedies may be cost-and time-prohibitive.  ... 
doi:10.36645/mtlr.28.1.content fatcat:ploqm52es5hklfcd4m7tajiywa

Detecting influencers in social media discussions

Sara Rosenthal
2014 XRDS Crossroads The ACM Magazine for Students  
The contributions of this thesis include a system for predicting who the influencers are in online discussion forums. We provide an evaluation of a rich set of features inspired by social science.  ...  The online genres we explore are Wikipedia Talk Pages, LiveJournal weblogs, Political Forum discussions, Create Debate debate discussions, and Twitter microblog conversations.  ...  Ritchie, The Development of the C Language " Design and programming are human activities; forget that and all is lost. " Bjarne Stroustrup, The C++ Programming Language " We don't get a chance to do that  ... 
doi:10.1145/2659889 fatcat:zmrceftbbbbidh3yoru3w3i3ra

Detecting the scope of negations in clinical notes [chapter]

Giuseppe Attardi, Vittoria Cozza, Daniele Sartiano
Proceedings of the Second Italian Conference on Computational Linguistics CLiC-it 2015  
MF would also like to thank the EPSRC for its support in the form of a doctoral training grant.  ...  Acknowledgments We would like to thank the headmaster of the primary school "Vasco Morroni" of Ghezzano (Pisa), the teachers and all the children taking part in the survey for their contribution in this  ...  The final dialogue act label set we used is reported in Table dialogue act labels between 2 non-expert labelers is k = 0.595 (Fleiss et al., 1981) .  ... 
doi:10.4000/books.aaccademia.1286 fatcat:taln6o5hlvdbnhccdfh6blpb4y

A Multi-Lingually Applicable Journalist Toolset For The Big-Data Era

G. Kiomourtzis, G. Giannakopoulos, V. Karkaletsis, A. Kosmopoulos
2016 Zenodo  
In IJCAI proceedings. Workshop: Natural Language Processing meets Journalism  ...  This research was supported in part by a Discovery and Innovation Research Seed award from the Office of the Vice Provost for Research at Cornell.  ...  Acknowledgments We thank the anonymous reviewers and the participants in the Fall 2015 edition of the course "Natural Language Processing and Social Interaction" for helpful comments and discussion.  ... 
doi:10.5281/zenodo.1242850 fatcat:nfkqg7jhjffdvgezdjzc6xxppa

The EVALITA Dependency Parsing Task: From 2007 to 2011 [chapter]

Cristina Bosco, Alessandro Mazzei
2013 Lecture Notes in Computer Science  
Established in 2007, EVALITA (http://www.evalita.it) is the evaluation campaign of Natural Language Processing and Speech Technologies for the Italian language, organized around shared tasks focusing on  ...  In this EVALITA edition, we received 30 expressions of interest, 55 registrations and 43 actual submissions to 8 proposed tasks distributed as follows:  ...  sharing of knowledge in health care).  ... 
doi:10.1007/978-3-642-35828-9_1 fatcat:p6dyjaxm4zbitfajtciwclwipu

The State of AI Ethics Report (June 2020) [article]

Abhishek Gupta
2020 arXiv   pre-print
Artificial intelligence has become the byword for technological progress and is being used in everything from helping us combat the COVID-19 pandemic to nudging our attention in different directions as  ...  These past few months have been especially challenging, and the deployment of technology in ways hitherto untested at an unrivalled pace has left the internet and technology watchers aghast.  ...  In the same vein, the backfire effect demonstrates how people who are presented with such contrary evidence further harden their views and get even more polarized thus negating the intention of presenting  ... 
arXiv:2006.14662v1 fatcat:q76dnqzh4ja5pofurjmpmyeyey

The Democratization of Artificial Intelligence [chapter]

Andreas Sudmann
2019 The Democratization of Artificial Intelligence  
Stokel-Walker, Chris (2019): Feeding algorithms is a full-time job. BBC (http:// www.bbc.com/capital/story/20190307-the-hidden-armies-that-power-the-in ternets-new-stars) [Last access 24.4.2019].  ...  Lecture held at the Barnard College for Women. (https://www.youtube. com/watch?v=ps8J6a7g_BA) [Last access 24.4.2019].  ...  Many of these scholars have also written an essay for this volume.  ... 
doi:10.1515/9783839447192-001 fatcat:7yjb2m5p7jdt7dvkpzsuttbvf4

NICHIZATION IN DIGITIZATION ERA: IMPLICATIONS FOR FINANCIAL SERVICES

Tevfik Dalgic
2018 Journal of Marketing and Strategic Management  
I am thankful to them for their unpaid and demanding voluntary works.  ...  This issue has an additional part as working paper. We tried to have a balanced combination of marketing and strategy related papers.  ...  The next opportunity for future research in this area of study involves examining the relationship strength among stakeholders of an organization.  ... 
doi:10.21607/jmsm.2018.007 fatcat:6drnurtcvzckbllx4c63pzasea

Digital Objects, Digital Subjects: Interdisciplinary Perspectives on Capitalism, Labour and Politics in the Age of Big Data

Antal Wozniak
2019 European Journal of Communication  
One respondent in the second interviews indicated frustration: I don't get any answers, I just fill in my things, but I don't get an answer if it is good or not, I just want to know if I [am] good and  ...  The two act as dialectical conversational poles.  ...  Is Qiu perhaps sacrificing some important analytical rigour for undoubted -and welcome -polemical effect?  ... 
doi:10.1177/0267323119873743 fatcat:aofc4pbkljckfc6i52jecqv5pi

State of AI Ethics Report (Volume 6, February 2022) [article]

Abhishek Gupta
2022 arXiv   pre-print
and Imagination for Preventing AI Harms".  ...  It is a resource for researchers and practitioners alike in the field to set their research and development agendas to make contributions to the field of AI ethics.  ...  The Digital Services Act in Europe is currently ill-equipped to handle this. Why it matters : This goes against laws in several countries in Europe that prohibit the use of race in hiring decisions.  ... 
arXiv:2202.07435v1 fatcat:wbalu3j3ynelfim7eqvxcpwu3q

The [R]evolution of Open Science

Jonathan Tennant
2020 Zenodo  
This book is an anthology all of the texts I have written or contributed to in a significant way over the last 9 years on the topic of Open Science.  ...  And now the whole book is available online for free here. All funds raised from the sale of this book will be invested in furthering the mission of creating a healthier global research culture.  ...  Don't pay $5000 for something that you can get for $99. It's simple.  ... 
doi:10.5281/zenodo.3700645 fatcat:kfoyv4cup5gc3oegmoajs77jxe

Which Open Internet Framework is Best for Mobile App innovation? [article]

Roslyn Layton
2017 Ph.d.-serien for Det Teknisk-Naturvidenskabelige Fakultet, Aalborg Universitet  
Indeed the insistence that every plan must access every point on the Internet is in fact "pure bundling" 670 , an act of obliging people to pay for data they don't want.  ...  they should get this service for free.  ...  The OECD itself notes that "RIA within an appropriate systematic framework can underpin the capacity of governments to ensure that regulations are efficient and effective in a changing and complex world  ... 
doi:10.5278/vbn.phd.engsci.00181 fatcat:kz5jx2gnvnbthjklxy7gp7jzke
« Previous Showing results 1 — 15 out of 293 results