Filters








289 Hits in 3.4 sec

Commonsense Properties from Query Logs and Question Answering Forums [article]

Julien Romero, Simon Razniewski, Koninika Pal, Jeff Z. Pan, Archit Sakhadeo, Gerhard Weikum
2021 arXiv   pre-print
We devise novel ways of tapping into search-engine query logs and QA forums, and combining the resulting candidate assertions with statistical cues from encyclopedias, books and image tags in a corroboration  ...  This paper presents Quasimodo, a methodology and tool suite for distilling commonsense properties from non-standard web sources.  ...  We thank the anonymous reviewers and Niket Tandon for helpful comments.  ... 
arXiv:1905.10989v4 fatcat:h2iuxuc7nvfudkycgvbqx5kxqy

Commonsense Properties from Query Logs and Question Answering Forums

Julien Romero, Simon Razniewski, Koninika Pal, Jeff Z. Pan, Archit Sakhadeo, Gerhard Weikum
2019 Proceedings of the 28th ACM International Conference on Information and Knowledge Management - CIKM '19  
We devise novel ways of tapping into search-engine query logs and QA forums, and combining the resulting candidate assertions with statistical cues from encyclopedias, books and image tags in a corroboration  ...  This paper presents Quasimodo, a methodology and tool suite for distilling commonsense properties from non-standard web sources.  ...  We thank the anonymous reviewers and Niket Tandon for helpful comments.  ... 
doi:10.1145/3357384.3357955 dblp:conf/cikm/RomeroRPPSW19 fatcat:idb3jc75gjc7tjpvog5zj3qoqm

True Knowledge: Open-Domain Question Answering Using Structured Knowledge and Inference

William Tunstall-Pedoe
2010 The AI Magazine  
queries and an inference system that can answer those queries using both directly represented and inferred knowledge.  ...  The system is live and answers millions of questions per month asked by internet users.  ...  At the other extreme are questions sourced from discussion forums or other sources where the person asking the question was expecting a person to answer, and consequently there is no incentive to phrase  ... 
doi:10.1609/aimag.v31i3.2298 fatcat:6amwxs7xmffehmr3p4jafnmrki

Advanced Semantics for Commonsense Knowledge Extraction [article]

Tuan-Phong Nguyen, Simon Razniewski, Gerhard Weikum
2021 arXiv   pre-print
Commonsense knowledge (CSK) about concepts and their properties is useful for AI applications such as robust chatbots.  ...  strings for P and O.  ...  Query auto-completion and question-answering forums were tapped by Quasimodo [46] .  ... 
arXiv:2011.00905v2 fatcat:ue2t2nbzbrfprctwtlfgzmzlmi

Unsupervised Commonsense Question Answering with Self-Talk [article]

Vered Shwartz, Peter West, Ronan Le Bras, Chandra Bhagavatula, Yejin Choi
2020 arXiv   pre-print
that obtain knowledge from external KBs.  ...  While our approach improves performance on several benchmarks, the self-talk induced knowledge even when leading to correct answers is not always seen as useful by human judges, raising interesting questions  ...  CommonSenseQA: commonsense Question Answering (Talmor et al., 2019) : General questions about concepts from ConceptNet.  ... 
arXiv:2004.05483v2 fatcat:5hffd6s35vfslgbwrwo4rmo25e

GPU-based Commonsense Paradigms Reasoning for Real-Time Query Answering and Multimodal Analysis [article]

Nguyen Ha Tran, Erik Cambria
2018 arXiv   pre-print
In addition, in order to ex- tract important textual features from multimodal sources we generate domain-specific graphs based on commonsense knowledge and apply GPU-based graph traversal for fast feature  ...  ., speech and video, for emotion and polarity detection.  ...  the query plan based on the properties of commonsense queries.  ... 
arXiv:1807.08804v1 fatcat:xu5m2oh55ndahct7rtrbecjz3m

Identifying Sources of Disagreement: Generalizability Theory in Manual Annotation Studies

Petra Saskia Bayerl, Karsten Ingmar Paul
2007 Computational Linguistics  
He co-founded iAskWeb, a company that provides question-answering services involving commonsense reasoning online, and authored a book on that topic (Natural Lan- guage Question Answering: Technique of  ...  in question answering, annota- tion, information extraction, and machine translation systems.  ... 
doi:10.1162/coli.2007.33.1.3 fatcat:xlxgwfiuo5cohh37izbhnpwmvm

Dimensions of Commonsense Knowledge [article]

Filip Ilievski, Alessandro Oltramari, Kaixin Ma, Bin Zhang, Deborah L. McGuinness, Pedro Szekely
2021 arXiv   pre-print
Consequently, many sources that include commonsense knowledge have been designed and constructed over the past decades.  ...  Commonsense knowledge is essential for many AI applications, including those in natural language processing, visual processing, and planning.  ...  Its nodes and relations are initially lexical and extracted automatically from search logs and forums, after which a notable subset of them has been clustered into WordNet domains.  ... 
arXiv:2101.04640v2 fatcat:ehkp23l2cfelrm6urgmyiyyix4

Multitask Prompted Training Enables Zero-Shot Task Generalization [article]

Victor Sanh, Albert Webson, Colin Raffel, Stephen H. Bach, Lintang Sutawika, Zaid Alyafeai, Antoine Chaffin, Arnaud Stiegler, Teven Le Scao, Arun Raja, Manan Dey, M Saiful Bari (+29 others)
2022 arXiv   pre-print
To test this question at scale, we develop a system for easily mapping any natural language tasks into a human-readable prompted form.  ...  Further, our approach attains strong performance on a subset of tasks from the BIG-bench benchmark, outperforming models up to 6x its size.  ...  The project has 600 researchers from 50 countries and more than 250 institutions.  ... 
arXiv:2110.08207v3 fatcat:vvacmc2phfg7dpmdqiebyvxvei

An exploration of the principles underlying redundancy-based factoid question answering

Jimmy Lin
2007 ACM Transactions on Information Systems  
The so-called "redundancy-based" approach to question answering represents a successful strategy for mining answers to factoid questions such as "Who shot Abraham Lincoln?" from the World Wide Web.  ...  Overall, this work attempts to address the broader question of "what really matters" and to provide guidance for future researchers.  ...  Analyses of question logs from the Start system (Katz, 1997) , which has answered millions of questions over the last decade, and query logs from commercial search engines (Lowe, 2000) lead to the same  ... 
doi:10.1145/1229179.1229180 fatcat:l2pwnam7qvh6xbp6a3krpoidpq

Spatial Dataset Search: Building a dedicated Knowledge Graph

Mehdi Zrhal, Bénédicte Bucher, Marie-Dominique Van Damme, Fayçal Hamdi
2021 AGILE: GIScience Series  
These can usually be found in dedicated web portals with different structures and specificities.  ...  In this article, we present the problem of spatial dataset search and how the use of a geographic Knowledge Graph could improve it.  ...  in question.  ... 
doi:10.5194/agile-giss-2-43-2021 fatcat:vmijz4wpx5dxppldjdt3glqr6y

Joint Reasoning for Multi-Faceted Commonsense Knowledge [article]

Yohan Chalier, Simon Razniewski, Gerhard Weikum
2020 arXiv   pre-print
Commonsense knowledge (CSK) supports a variety of AI applications, from visual understanding to chatbots.  ...  Each concept is treated in isolation from other concepts, and the only quantitative measure (or ranking) of properties is a confidence score that the statement is valid.  ...  QA forums and web query logs, with about 4.6 million statements.  ... 
arXiv:2001.04170v2 fatcat:wlih2w4wl5cr5okfimh7l5zwoe

Knowledge-based Conversational Search [article]

Svitlana Vakulenko
2019 arXiv   pre-print
In the third research chapter, we propose a novel approach for complex question answering from a knowledge graph that surpasses the current state-of-the-art results in terms of both efficacy and efficiency  ...  We show that this approach helps users to discover relevant items that are difficult to retrieve using only question answering due to the vocabulary mismatch problem.  ...  The former is used to extract a process model from an event log, and the latter to verify the model against the event log, i.e., whether the patterns evident from the event log correspond to the structure  ... 
arXiv:1912.06859v1 fatcat:rab6kemqujflrobib7lvvy6hue

ASER: Towards Large-scale Commonsense Knowledge Acquisition via Higher-order Selectional Preference over Eventualities [article]

Hongming Zhang, Xin Liu, Haojie Pan, Haowen Ke, Jiefu Ou, Tianqing Fang, Yangqiu Song
2022 arXiv   pre-print
Commonsense knowledge acquisition and reasoning have long been a core artificial intelligence problem.  ...  acquired from the unlabeled corpus with modern tools.  ...  Acknowledgements This paper was supported by the GRF (16211520) and the RIF (R6020-19 and R6021-20) from RGC of Hong Kong, the NSFC Fund (U20B2053) from the NSFC of China, the MHKJFS (MHP/001/19) from  ... 
arXiv:2104.02137v2 fatcat:dmb2dhqzevc2pd2vef4n5ds5ei

Delphi: Towards Machine Ethics and Norms [article]

Liwei Jiang, Jena D. Hwang, Chandra Bhagavatula, Ronan Le Bras, Maxwell Forbes, Jon Borchardt, Jenny Liang, Oren Etzioni, Maarten Sap, Yejin Choi
2021 arXiv   pre-print
In addition to the new resources and baseline performances for future research, our study provides new insights that lead to several important open research questions: differentiating between universal  ...  Our paper begins to address these questions within the deep learning paradigm.  ...  ACKNOWLEDGEMENTS The authors thank Yoav Goldberg and Peter Clark for helpful discussions, and Sam Stuesser from the REVIZ team at AI2 for designing the logo of the Ask Delphi demo.  ... 
arXiv:2110.07574v1 fatcat:yi4kplseqfanfccina227nx2zi
« Previous Showing results 1 — 15 out of 289 results