Filters








213 Hits in 9.1 sec

Human Evaluation of Spoken vs. Visual Explanations for Open-Domain QA [article]

Ana Valeria Gonzalez, Gagan Bansal, Angela Fan, Robin Jia, Yashar Mehdad, Srinivasan Iyer
2020 arXiv   pre-print
While research on explaining predictions of open-domain QA systems (ODQA) to users is gaining momentum, most works have failed to evaluate the extent to which explanations improve user trust.  ...  To alleviate these issues, we conduct user studies that measure whether explanations help users correctly decide when to accept or reject an ODQA system's answer.  ...  Our studies observed significant improvements from explanations for the end-task to help users decide whether to trust the prediction of an imperfect open-domain QA agent.  ... 
arXiv:2012.15075v1 fatcat:kbngatjdlfhhhod3on5cpiqnoq

Towards a Science of Human-AI Decision Making: A Survey of Empirical Studies [article]

Vivian Lai, Chacha Chen, Q. Vera Liao, Alison Smith-Renner, Chenhao Tan
2021 arXiv   pre-print
As AI systems demonstrate increasingly strong predictive performance, their adoption has grown in numerous domains.  ...  We summarize the study design choices made in over 100 papers in three important aspects: (1) decision tasks, (2) AI models and AI assistance elements, and (3) evaluation metrics.  ...  Human Evaluation of Spoken vs. Visual Explanations for Open-Domain QA. arXiv preprint arXiv:2012.15075 (2020). [53] Ben Green. 2021.  ... 
arXiv:2112.11471v1 fatcat:5hzeydmonvgkbnm7cq3zrdzvlm

Introduction [chapter]

Peter Spyns
2012 Essential Speech and Language Technology for Dutch  
The major scientific goals were to set up an effective digital language infrastructure for Dutch, and to carry out strategic research in the field of language and speech technology for Dutch. 1 Consortia  ...  STEVIN advocated an integrated approach: develop text and speech resources and tools, stimulate innovative strategic and application-oriented research, promote embedding of HLT in existing applications  ...  Open Access.  ... 
doi:10.1007/978-3-642-30910-6_1 dblp:series/tanlp/Spyns13 fatcat:x3hadalrirbvliitkmzj74xtqi

Automatic Summarization

Martha Larson
2012 Foundations and Trends in Information Retrieval  
This survey provides an overview of the field of SCR encompassing component technologies, the relationship of SCR to text IR and automatic speech recognition and user interaction issues.  ...  SCR research initially investigated planned speech structured in document-like units, but has subsequently shifted focus to more informal spoken content produced spontaneously, outside of the studio and  ...  In [21] , a user study is conducted for the domain of podcasts, and five different user goals in podcast search are identified and used as the basis for evaluation of an SCR system.  ... 
doi:10.1561/1500000020 fatcat:o424mjxnp5abbexhjsobtom2ry

Frontiers, challenges, and opportunities for information retrieval

James Allan, Bruce Croft, Alistair Moffat, Mark Sanderson
2012 SIGIR Forum  
How can we best address quality assurance issues in data collection, differentiating objective errors vs. legitimate data diversity?  ...  Besides relevance and authority, an essential factor is adequacy of the source to the user: a document suitable for an expert or an adult is possibly not suited for a child (particularly if engaged in  ...  Spoken Information Retrieval This project aims to extend IR systems such that they can accept spoken queries and generate spoken results, thereby helping the visually impaired as well as anyone in a setting  ... 
doi:10.1145/2215676.2215678 fatcat:mo7fz7o5vzdrfkiisn2rdttg6y

PhD thesis: SQL Comprehension and Synthesis [article]

George Obaido
2022 arXiv   pre-print
An ideal solution is to present these two audiences: undergraduate students and nontechnical end-users with learning and practice tools.  ...  Although SQL statements are English-like, the process of writing SQL queries is often problematic for nontechnical end-users in the industry.  ...  In the third study, an accuracy of 88% was reported as experimental evaluation and 96.9% out of 162 participants agreed that the tool would be helpful to industry users.  ... 
arXiv:2203.03469v1 fatcat:mutfduvr2jgezmaomd4otvcpje

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.  ...  For each category, we present a review of state-of-the-art neural approaches, draw the connection between them and traditional approaches, and discuss the progress that has been made and challenges still  ...  It Figure 4 . 2 : 42 An example user goal in the movie-ticket-booking domain ent dimensions to categorize a user simulator, such as deterministic vs. stochastic, content-based vs.  ... 
arXiv:1809.08267v3 fatcat:j57xlm4ogferdnrpfs4f2jporq

Neural Generation Meets Real People: Towards Emotionally Engaging Mixed-Initiative Conversations [article]

Ashwin Paranjape, Abigail See, Kathleen Kenealy, Haojun Li, Amelia Hardy, Peng Qi, Kaushik Ram Sadagopan, Nguyet Minh Phu, Dilara Soylu, Christopher D. Manning
2020 arXiv   pre-print
We present Chirpy Cardinal, an open-domain dialogue agent, as a research platform for the 2019 Alexa Prize competition.  ...  Building an open-domain socialbot that talks to real people is challenging - such a system must meet multiple user expectations such as broad world knowledge, conversational style, and emotional connection  ...  Abigail See's work was supported by an unrestricted gift from Google LLC. We thank Amazon.com, Inc. for a grant partially supporting the work of the rest of the team.  ... 
arXiv:2008.12348v2 fatcat:2vjg4zfrgffjzdpq7y764tf3v4

Ethics Sheet for Automatic Emotion Recognition and Sentiment Analysis [article]

Saif M. Mohammad
2022 arXiv   pre-print
Notably, the sheet fleshes out assumptions hidden in how AER is commonly framed, and in the choices often made regarding the data, method, and evaluation.  ...  The importance and pervasiveness of emotions in our lives makes affective computing a tremendously important and vibrant line of work.  ...  Acknowledgments I am grateful to Annika Schoene, Mallory Feldman, and Tara Small for their belief and encouragement in the early days of this project.  ... 
arXiv:2109.08256v3 fatcat:hnpzztguprccbmzoitpryfigoa

How Practitioners Perceive Automated Bug Report Management Techniques

Weiqin Zou, David Lo, Zhenyu Chen, Xin Xia, Yang Feng, Baowen Xu
2018 IEEE Transactions on Software Engineering  
Bug reports play an important role in the process of debugging and fixing bugs.  ...  However, the verdict is still open whether such techniques are actually required and applicable outside the domain of theoretical research.  ...  This research is partly supported by National Natural Science Foundation of China (Grant No. 61690201, 61373013) , the China Scholarship Council Scholarship.  ... 
doi:10.1109/tse.2018.2870414 fatcat:l5ivzcyw2rfabeigyy6unsv4qm

A Metaverse: taxonomy, components, applications, and open challenges

Sang-Min Park, Young-Gab Kim
2022 IEEE Access  
Furthermore, we describe essential methods based on three components and techniques to Metaverse's representative Ready Player One, Roblox, and Facebook research in the domain of films, games, and studies  ...  ., user interaction, implementation, and application) rather than marketing or hardware approach to conduct a comprehensive analysis.  ...  [324] provided a debug flow based on the root cause and classification error guidance within the CPU using case studies as an explanation of how to debug this class of errors.  ... 
doi:10.1109/access.2021.3140175 fatcat:fnraeaz74vh33knfvhzrynesli

MERLOT: Multimodal Neural Script Knowledge Models [article]

Rowan Zellers, Ximing Lu, Jack Hessel, Youngjae Yu, Jae Sung Park, Jize Cao, Ali Farhadi, Yejin Choi
2021 arXiv   pre-print
We introduce MERLOT, a model that learns multimodal script knowledge by watching millions of YouTube videos with transcribed speech -- in an entirely label-free, self-supervised manner.  ...  As humans, we understand events in the visual world contextually, performing multimodal reasoning across time to make inferences about the past, present, and future.  ...  While we do not claim that these attention weights provide a full explanation of the model behavior [43, 87], they do play some role in the model’s decision [103], and we find that our masking strategy  ... 
arXiv:2106.02636v3 fatcat:mrj2t3yuanbdzhsujshtky4enq

Modularized User Modeling in Conversational Recommender Systems [chapter]

Pontus Wärnestål
2005 Lecture Notes in Computer Science  
Study II is an end-user evaluation of the acorn system that implements the dialogue control strategy and results in a verification of the effectiveness and usability of the dialogue strategy.  ...  in domain items modeled in a system.  ...  On its own, the dialogue behavior of the conventional dbd does not do much to help a user with any task.  ... 
doi:10.1007/11527886_78 fatcat:c6lfkkv35vhppjqkuhialz5fla

On the Opportunities and Risks of Foundation Models [article]

Rishi Bommasani, Drew A. Hudson, Ehsan Adeli, Russ Altman, Simran Arora, Sydney von Arx, Michael S. Bernstein, Jeannette Bohg, Antoine Bosselut, Emma Brunskill, Erik Brynjolfsson, Shyamal Buch (+102 others)
2021 arXiv   pre-print
principles(e.g., model architectures, training procedures, data, systems, security, evaluation, theory) to their applications (e.g., law, healthcare, education) and societal impact (e.g., inequity, misuse  ...  Though foundation models are based on standard deep learning and transfer learning, their scale results in new emergent capabilities,and their effectiveness across so many tasks incentivizes homogenization  ...  In addition, we would like to especially thank Vanessa Parli for helping to organize this effort.  ... 
arXiv:2108.07258v2 fatcat:yktkv4diyrgzzfzqlpvaiabc2m

A Roadmap for Big Model [article]

Sha Yuan, Hanyu Zhao, Shuai Zhao, Jiahong Leng, Yangxiao Liang, Xiaozhi Wang, Jifan Yu, Xin Lv, Zhou Shao, Jiaao He, Yankai Lin, Xu Han (+88 others)
2022 arXiv   pre-print
Researchers have achieved various outcomes in the construction of BMs and the BM application in many fields.  ...  In each topic, we summarize clearly the current studies and propose some future research directions. At the end of this paper, we conclude the further development of BMs in a more general view.  ...  with users in open domains.  ... 
arXiv:2203.14101v4 fatcat:rdikzudoezak5b36cf6hhne5u4
« Previous Showing results 1 — 15 out of 213 results