6,757 Hits in 6.6 sec

Prompt-based Generative Approach towards Multi-Hierarchical Medical Dialogue State Tracking [article]

Jun Liu, Tong Ruan, Haofen Wang, Huanhuan Zhang
2022 arXiv   pre-print
Then we propose a Prompt-based Generative Approach which can generate slot values with multi-hierarchies incrementally using a top-down approach.  ...  Therefore, we first define a multi-hierarchical state structure. We annotate and publish a medical dialogue dataset in Chinese.  ...  The task of defining, extracting, and maintaining such a structure is called Dialogue State Tracking (DST) in task-oriented dialogue systems.  ... 
arXiv:2203.09946v1 fatcat:ngcpxn43eravxeox3lvozgd7u4

Pretrained Language Models for Text Generation: A Survey [article]

Junyi Li, Tianyi Tang, Wayne Xin Zhao, Jian-Yun Nie, Ji-Rong Wen
2022 arXiv   pre-print
Text generation based on PLMs is viewed as a promising approach in both academia and industry. In this paper, we provide a survey on the utilization of PLMs in text generation.  ...  We also include a summary of various useful resources and typical text generation applications based on PLMs.  ...  Generally, task-oriented dialogue system was divided into four modules, i.e., natural language understanding, dialogue state tracking, dialogue policy learning and natural language generation [220] .  ... 
arXiv:2201.05273v4 fatcat:pnffabspsnbhvo44gbaorhxc3a

Annotation of Tutorial Dialogue Goals for Natural Language Generation

Jung Hee Kim, Reva Freedman, Michael Glass, Martha W. Evens
2006 Discourse Processes  
We annotated transcripts of human tutoring dialogue for the purpose of constructing a dialogue-based intelligent tutoring system, CIRCSIM-Tutor.  ...  In this article, we describe our model of hierarchical goal structure for tutorial dialogues.  ...  Stanford University as well as Grants N00014-94-1-0338 and N00014-02-1-0442 to Illinois Institute of Technology, N00014-03-1-0037 to Valparaiso University, and N00014-02-1-0164 to North Carolina A & T State  ... 
doi:10.1207/s15326950dp4201_2 fatcat:tx3wkaafdfcszm2c3z73bodvfm

Context-Awareness in a Persistent Hospital Companion Agent [chapter]

Timothy Bickmore, Reza Asadi, Aida Ehyaei, Harriet Fell, Lori Henault, Stephen Intille, Lisa Quintiliani, Ameneh Shamekhi, Ha Trinh, Katherine Waite, Christopher Shanahan, Michael K. Paasche-Orlow
2015 Lecture Notes in Computer Science  
Agent dialogues are scripted, using a custom hierarchical transition network-based scripting language.  ...  Agent utterances can be tailored at runtime through the inclusion of phrases derived from information in the database or other sources, using template-based text generation.  ... 
doi:10.1007/978-3-319-21996-7_35 fatcat:t4fo3tdj2rfipnpgpcyw2rxmp4

MEDCOD: A Medically-Accurate, Emotive, Diverse, and Controllable Dialog System [article]

Rhys Compton, Ilya Valmianski, Li Deng, Costa Huang, Namit Katariya, Xavier Amatriain, Anitha Kannan
2021 arXiv   pre-print
Experimental results demonstrate the effectiveness of our approach in creating a human-like medical dialogue system.  ...  We present MEDCOD, a Medically-Accurate, Emotive, Diverse, and Controllable Dialog system with a unique approach to the natural language generator module.  ...  In the area of mapping extracted medical concepts in conversations to a knowledge base, (Du et al., 2019a,b) introduced a hierarchical two-stage approach to infer clinical entities (e.g., symptoms),  ... 
arXiv:2111.09381v1 fatcat:ysqczzqksfcmdpaqkhho42ysve

Speech-gesture driven multimodal interfaces for crisis management

R. Sharma, M. Yeasin, N. Krahntoever, I. Rauschert, Guoray Cai, I. Brewer, A.M. Maceachren, K. Sengupta
2003 Proceedings of the IEEE  
Dialogue-enabled devices, based on natural, multimodal interfaces have the potential of making a variety of information technology tools accessible during crisis management.  ...  The third part discusses the state of the art in both the theories and practices involving these human-computer interfaces.  ...  Finite-state based method and frame-based method can not support mixed initiative dialogue due to their fixed dialogue control structures.  ... 
doi:10.1109/jproc.2003.817145 fatcat:flbaisvreresla7wufztzpnvfq

Conversational Agents: Goals, Technologies, Vision and Challenges

Merav Allouch, Amos Azaria, Rina Azoulay
2021 Sensors  
In addition, several areas for future research are identified to address moral and security issues, given the current state of CA-related technological developments.  ...  [71] present a word-based approach to dialogue state tracking using recurrent neural networks (RNNs). The model is capable of generalizing to unseen dialogue states' hypotheses.  ...  SGD can test state tracking as well as intent prediction, slot filling, and language generation.  ... 
doi:10.3390/s21248448 pmid:34960538 pmcid:PMC8704682 fatcat:vhylbunhwbbhfa65bdqmnqpi5q

Human-computer interface development: concepts and systems for its management

H. Rex Hartson, Deborah Hix
1989 ACM Computing Surveys  
The role of a dialogue developer, whose main purpxe is to create quality interfaces, is a direct result of the dialogue independence concept.  ...  Numerous kinds of interactive tools fw human-computer interface development free the dialogue developer from much of the tedium of "coding" dialogue.  ...  The shift in emphasis toward asynchronism, concurrency, and multi-thread dialogue will continue.  ... 
doi:10.1145/62029.62031 fatcat:7ojynadcn5e6rjwe2t7l3ovlvm

Health dialog systems for patients and consumers

Timothy Bickmore, Toni Giorgino
2006 Journal of Biomedical Informatics  
The strengths and weaknesses of these approaches are also discussed, and the needs for future work in the field are delineated.  ...  State transition networks can be defined hierarchically, resulting in sub-dialogs that can be factored out and re-used like subroutines: a modeling approach known as hierarchical state transition networks  ...  Current state Very short series of questions (e.g., screening) State transition network Current state Brief dialog with some branching Hierarchical state transition network Stack of states Partitioning  ... 
doi:10.1016/j.jbi.2005.12.004 pmid:16464643 fatcat:tldcbvrllbhwro7t4ag3ekj6uq

Why is constrained neural language generation particularly challenging? [article]

Cristina Garbacea, Qiaozhu Mei
2022 arXiv   pre-print
Our aim is to highlight recent progress and trends in this emerging field, informing on the most promising directions and limitations towards advancing the state-of-the-art of constrained neural language  ...  generation research.  ...  Story-telling methods commonly use a hierarchical approach to thematically consistent story generation, by first generating a prompt describing the topic for the story, and then constraining on the prompt  ... 
arXiv:2206.05395v1 fatcat:nnoqdgda4be45lj5tjo3xt7kbe

CASIE – Computing affect and social intelligence for healthcare in an ethical and trustworthy manner

Laurentiu Vasiliu, Keith Cortis, Ross McDermott, Aphra Kerr, Arne Peters, Marc Hesse, Jens Hagemeyer, Tony Belpaeme, John McDonald, Rudi Villing, Alessandra Mileo, Annalina Capulto (+4 others)
2021 Paladyn: Journal of Behavioral Robotics  
utilised to better assist human users' needs by enabling the robot to sense, adapt, and respond appropriately to their requirements while taking into consideration their wider affective, motivational states  ...  We propose an innovative approach to the difficult research challenge of endowing robots with social intelligence capabilities for human assistive interactions, going beyond the conventional robotic sense-think-act  ...  Conflict of interest: Authors state no conflict of interest.  ... 
doi:10.1515/pjbr-2021-0026 fatcat:h63j74p7rzh45eh4bw7quxovwu

Maintaining reality: Relational agents for antipsychotic medication adherence

Timothy W. Bickmore, Kathryn Puskar, Elizabeth A. Schlenk, Laura M. Pfeifer, Susan M. Sereika
2010 Interacting with computers  
We describe an animated, conversational computer agent designed to promote antipsychotic medication adherence among patients with Schizophrenia.  ...  In addition to medication adherence, the agent also promotes physical activity and system usage, and includes verbal and nonverbal behavior designed to foster a therapeutic alliance with patients.  ...  In this architecture, interaction dialogues are specified using a custom scripting language that uses hierarchical transition networks to model dialogue structure, template-based text generation for agent  ... 
doi:10.1016/j.intcom.2010.02.001 fatcat:fj42nnjutfhblgzjttzazttyhe

Response to a relational agent by hospital patients with depressive symptoms

Timothy W. Bickmore, Suzanne E. Mitchell, Brian W. Jack, Michael K. Paasche-Orlow, Laura M. Pfeifer, Julie O'Donnell
2010 Interacting with computers  
In the current study, we sought to evaluate how hospitalized medical patients would respond to a computer animated conversational agent that has been developed to provide information in an empathic fashion  ...  Thanks to the many members of the Re-Engineered Discharge project team at Boston Medical Center and the Relational Agents Group at Northeastern University for their contributions to this work.  ...  Dialogues are scripted, using a custom hierarchical transition network-based scripting language, and a visual dialogue design tool.  ... 
doi:10.1016/j.intcom.2009.12.001 pmid:20628581 pmcid:PMC2901553 fatcat:u4cg6kw5d5bvpiovuwj4oomozy

Robotic Assistance in Medication Intake: A Complete Pipeline

Ioannis Kostavelis, Andreas Kargakos, Evangelos Skartados, Georgia Peleka, Dimitrios Giakoumis, Iason Sarantopoulos, Ioannis Agriomallos, Zoe Doulgeri, Satoshi Endo, Heiko Stüber, Faris Janjoš, Sandra Hirche (+1 others)
2022 Applied Sciences  
The challenges tackled in this work comprise, among others, that the robot locates the medication box placed in challenging spots by applying vision based strategies, thus enabling robust grasping.  ...  of medication intake activity.  ...  The second one is a laser based human tracking mainly inspired by the work presented in [24] .  ... 
doi:10.3390/app12031379 fatcat:2toroyaimvdappjp46swhiwf4a

Counseling Summarization using Mental Health Knowledge Guided Utterance Filtering [article]

Aseem Srivastava, Tharun Suresh, Sarah Peregrine Lord, Md. Shad Akhtar, Tanmoy Chakraborty
2022 arXiv   pre-print
We create a new dataset after annotating 12.9K utterances of counseling components and reference summaries for each dialogue.  ...  We comprehensively analyze the generated summaries to investigate the capturing of psychotherapy elements. Human and clinical evaluations on the summary show that ConSum generates quality summary.  ...  medical health domain is discussed below, followed by a section on The state-of-the-art models are capable of generating semanti-  ... 
arXiv:2206.03886v1 fatcat:6uixxl4vp5gwzfq7zz4yb67twe
« Previous Showing results 1 — 15 out of 6,757 results