Filters








19,535 Hits in 5.5 sec

Textual Complexity and Discourse Structure in Computer-Supported Collaborative Learning [chapter]

Stefan Trausan-Matu, Mihai Dascalu, Philippe Dessus
2012 Lecture Notes in Computer Science  
Computer-Supported Collaborative Learning (CSCL) technologies play an increasing role simultaneously with the appearance of the Social Web.  ...  We propose the extension of the model and the previous applications of the polyphonic method to both collaborative CSCL chats and individual metacognitive essays performed by the same learners.  ...  Futur utterance based on the cohe of concept repetition, an Meanwhile, thread cohesio previously stated and pro perpetuated through the ent From a completely diff applying social network a importance in  ... 
doi:10.1007/978-3-642-30950-2_46 fatcat:xoq3rnanw5agflb5lffuut5yli

Joint Emoji Classification and Embedding Learning [chapter]

Xiang Li, Rui Yan, Ming Zhang
2017 Lecture Notes in Computer Science  
In particular, we use a convolutional neural network to get the embedding of the utterance and match it with the embedding of the corresponding emoji, to obtain its best classification, and otherwise also  ...  Plentiful utterances with emoji are produced by humans manually in social media platforms every day, which make emoji great influence on the human life.  ...  in human-human conversation on social network platforms, emoji is often used as a part of humans' utterances to indicate their current emotion.  ... 
doi:10.1007/978-3-319-63564-4_4 fatcat:ueirrievdnec7ek2tsi44pqkxu

Filling Conversation Ellipsis for Better Social Dialog Understanding

Xiyuan Zhang, Chengxi Li, Dian Yu, Samuel Davidson, Zhou Yu
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
The phenomenon of ellipsis is prevalent in social conversations.  ...  Specifically, we first complete user utterances to resolve ellipsis using an end-to-end pointer network model.  ...  Our hybrid model will utilize the SRL prediction of the ellipsis utterance and provide correct output. Case Study Conclusion Ellipsis frequently occurs in social conversations.  ... 
doi:10.1609/aaai.v34i05.6505 fatcat:awvy7th4gzdofmu4vevrfpagye

Filling Conversation Ellipsis for Better Social Dialog Understanding [article]

Xiyuan Zhang, Chengxi Li, Dian Yu, Samuel Davidson, Zhou Yu
2019 arXiv   pre-print
The phenomenon of ellipsis is prevalent in social conversations.  ...  Specifically, we first complete user utterances to resolve ellipsis using an end-to-end pointer network model.  ...  Our hybrid model will utilize the SRL prediction of the ellipsis utterance and provide correct output. Case Study Conclusion Ellipsis frequently occurs in social conversations.  ... 
arXiv:1911.10776v1 fatcat:ahfxhqyvebdgbjyzjh2gmmhlue

A First Look at Developers' Live Chat on Gitter [article]

Lin Shi, Xiao Chen, Ye Yang, Hanzhi Jiang, Ziyou Jiang, Nan Niu, Qing Wang
2021 arXiv   pre-print
We believe that the findings and insights will enable a better understanding of developers' live chat, pave the way for other researchers, as well as a better utilization and mining of knowledge embedded  ...  We manually analyze 749 dialogs in the first phase, followed by an automated analysis of over 173K dialogs in the second phase.  ...  Properties of social networks. Table 3 shows the social network properties of the eight communities.  ... 
arXiv:2107.05823v1 fatcat:xegbwmhwmzal7juru3gba447gq

Speech interaction strategies for a humanoid assistant

Sebastian Stüker, Stefan Constantin, Jan Niehues, Thai-Son Nguyen, Markus Müller, Ngoc Quan Pham, Robin Rüde, Alex Waibel, A. Ronzhin, V. Shishlakov
2018 MATEC Web of Conferences  
In order to meet these demands, we are developing low-latency streaming based automatic speech recognition systems in combination with recurrent neural network based Natural Language Understanding systems  ...  The robot is to act as a second pair of hands that can assist the technician when he is in need of help.  ...  This work has been conducted in the SecondHands project which has received funding from the European Union's Horizon 2020 Research and Innovation programme (call:H2020-ICT-2014-1, RIA) under grant agreement  ... 
doi:10.1051/matecconf/201816101002 fatcat:m7d6p6zgujbezl452zqmgux2qi

A review of evaluation techniques for social dialogue systems

Amanda Cercas Curry, Helen Hastie, Verena Rieser
2017 Proceedings of the 1st ACM SIGCHI International Workshop on Investigating Social Interactions with Artificial Agents - ISIAA 2017  
In contrast with goal-oriented dialogue, social dialogue has no clear measure of task success. Consequently, evaluation of these systems is notoriously hard.  ...  In this paper, we review current evaluation methods, focusing on automatic metrics.  ...  Acknowledgements This research is supported by Rieser's EPSRC projects DILiGENt (EP/M005429/1) and MaDrIgAL (EP/N017536/1); and from the RAEng/Leverhulme Trust Senior Research Fellowship Scheme (Hastie  ... 
doi:10.1145/3139491.3139504 dblp:conf/icmi/CurryHR17 fatcat:vlfnq26nyre57d6kllraeztrym

The mad hatter's cocktail party

Paul M. Aoki, Matthew Romaine, Margaret H. Szymanski, James D. Thornton, Daniel Wilson, Allison Woodruff
2003 Proceedings of the conference on Human factors in computing systems - CHI '03  
In face-to-face interactions in such social groups, conversational floors change frequently, e.g., two participants split off to form a new conversational floor, a participant moves from one conversational  ...  This paper presents a mobile audio space intended for use by gelled social groups.  ...  (A time correction is applied to account for network delays.) We then enumerate the valid configurations of disjoint subsets of users.  ... 
doi:10.1145/642611.642686 dblp:conf/chi/AokiRSTWW03 fatcat:ntufbvhembanvn3gng6pztpzsy

Semi-Automated Dialogue Act Classification for Situated Social Agents in Games [chapter]

Jeff Orkin, Deb Roy
2011 Lecture Notes in Computer Science  
As a step toward simulating dynamic dialogue between agents and humans in virtual environments, we describe learning a model of social behavior composed of interleaved utterances and physical actions.  ...  A quantitative evaluation of statistical models learned from the gameplay logs demonstrates that semi-automatically classified dialogue acts yield significantly more predictive power than automatically  ...  For each game log in the test set, we slide a window of size n over the entire log and count correct predictions of the next utterance or action.  ... 
doi:10.1007/978-3-642-18181-8_11 fatcat:mkegsppwr5hqhpzrxpxiwve2uq

The mad hatter's cocktail party

Paul M. Aoki, Matthew Romaine, Margaret H. Szymanski, James D. Thornton, Daniel Wilson, Allison Woodruff
2003 Proceedings of the conference on Human factors in computing systems - CHI '03  
In face-to-face interactions in such social groups, conversational floors change frequently, e.g., two participants split off to form a new conversational floor, a participant moves from one conversational  ...  This paper presents a mobile audio space intended for use by gelled social groups.  ...  On a more basic level, we believe that automatic techniques of the kind reported here can form the basis for the lightweight, attentionally undemanding interfaces needed to support "always on," social  ... 
doi:10.1145/642685.642686 fatcat:tggy6dk6rjf33h6vaw266o5cc4

A Taxonomy of Empathetic Response Intents in Human Social Conversations [article]

Anuradha Welivita, Pearl Pu
2020 arXiv   pre-print
Furthermore, using lexical and machine learning methods, we automatically analysed both speaker and listener utterances of the entire dataset with identified response intents and 32 emotion categories.  ...  This approach can produce socially unacceptable responses due to the lack of large-scale quality data used to train the neural models.  ...  Conclusion In this paper, we introduced a taxonomy of empathetic response intents capable of supporting automatic empathetic communication in social chitchat.  ... 
arXiv:2012.04080v1 fatcat:ausl4dkajrdvvhww6p6mxhvyoe

Real-time Automatic Word Segmentation for User-generated Text [article]

Won Ik Cho, Sung Jun Cheon, Woo Hyun Kang, Ji Won Kim, Nam Soo Kim
2019 arXiv   pre-print
In this paper, we propose a real-time assistive technology that utilizes an automatic segmentation.  ...  The training scheme is fully neural network-based and straightforward. Besides, we show how the proposed system can be utilized in a web-based real-time revision for a user-generated text.  ...  Acknowledgments This work was supported by the Technology Innovation Program (10076583, Development of freerunning speech recognition technologies for embedded robot system) funded By the Ministry of Trade  ... 
arXiv:1810.13113v2 fatcat:3xejhykzuva5fjfrtjprv7rqg4

Assessing Effectiveness: Ways of Seeing Impact

Maggie Gregson, Lawrence Nixon
2009 International Journal of Interdisciplinary Social Sciences  
This paper presents experiments aiming at improving the automatic transcription of oral presentations through the inclusion of the slides in the recognition process.  ...  and the content of the slides.  ...  The Oracle is implemented by forcing the confusion networks to allocate a slot for each H S content word uttered by the speakers and by using the correct transcription as the only hypothesis for such slots  ... 
doi:10.18848/1833-1882/cgp/v03i12/52776 fatcat:2fa6rj2r7vdbdkrg6apia52boi

Yeah, Right, Uh-Huh: A Deep Learning Backchannel Predictor [article]

Robin Ruede, Markus Müller, Sebastian Stüker, Alex Waibel
2017 arXiv   pre-print
They are capable of deriving higher order features from input features themselves.  ...  Using supporting backchannel (BC) cues can make human-computer interaction more social. BCs provide a feedback from the listener to the speaker indicating to the speaker that he is still listened to.  ...  Acknowledgements This work has been conducted in the SecondHands project which has received funding from the European Union's Horizon 2020 Research and Innovation programme (call:H2020-ICT-2014-1, RIA)  ... 
arXiv:1706.01340v1 fatcat:g5yf5cjgwnfg3d3r7ypwggw2b4

Modeling Interaction Structure for Robot Imitation Learning of Human Social Behavior

Malcolm Doering, Dylan F. Glas, Hiroshi Ishiguro
2019 IEEE Transactions on Human-Machine Systems  
This study presents a learning-by-imitation technique that learns social robot interaction behaviors from natural humanhuman interaction data and requires minimum input from a designer.  ...  The technique is demonstrated in a scenario where the robot learns to play the role of a travel agent.  ...  Conclusion This study presented a technique for automatically learning social robot interaction behaviors, in the form of humanreadable rules, from unannotated human-human interaction examples that are  ... 
doi:10.1109/thms.2019.2895753 fatcat:g7yomv3qrrfgxjbfkylg3cgjy4
« Previous Showing results 1 — 15 out of 19,535 results