Filters








511 Hits in 8.6 sec

Unsupervised Timeline Generation for Wikipedia History Articles

Sandro Bauer, Simone Teufel
2016 Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing  
This paper presents a generic approach to content selection for creating timelines from individual history articles for which no external information about the same topic is available.  ...  This scenario is in contrast to existing works on timeline generation, which require the presence of a large corpus of news articles.  ...  Conclusion We have introduced an unsupervised method for the challenging problem of timeline generation from single history articles, a scenario where parallel texts cannot be assumed to exist.  ... 
doi:10.18653/v1/d16-1259 dblp:conf/emnlp/BauerT16 fatcat:z6oscy4vkfhznbffydvi6srgxq

Placing (Historical) Facts on a Timeline: A Classification cum Coref Resolution Approach [article]

Sayantan Adak, Altaf Ahmad, Aditya Basu, Animesh Mukherjee
2022 arXiv   pre-print
two staged system for event timeline generation from multiple (historical) text documents.  ...  By leveraging generative adversarial learning for important sentence classification and by assimilating knowledge based tags for improving the performance of event coreference resolution we introduce a  ...  Timeline of historical facts: [5] proposed an unsupervised generative model to construct the timeline of biographical life-facts leveraging encyclopaedic resources such as Wikipedia. [3] also uses Wikipedia  ... 
arXiv:2206.14089v1 fatcat:n6hwvwzb6fggpbnm64klo5pjzq

Discovering Latent Threads in Entity Histories

Yijun Duan, Adam Jatowt, Katsumi Tanaka
2019 Data Science and Engineering  
Next, we generate comparative timelines for each determined group allowing users to elucidate similarities and differences in the histories of entities.  ...  Knowledge of entity histories is often necessary for comprehensive understanding and characterization of entities.  ...  Open Access This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creat iveco mmons .org/licen ses/by/4.0/), which permits unrestricted use,  ... 
doi:10.1007/s41019-019-00108-x fatcat:zkneuatoi5atrafmv25tu6kj2u

A Bag-of-entities Approach to Document Focus Time Estimation

Christian Morbidoni, Alessandro Cucchiarelli
2017 International Workshop on Knowledge Discovery on the Web  
Our method does not rely on explicit temporal expressions in the documents, so it is therefore applicable to a general context.  ...  We leverage state of the art Named Entity Extraction tools and exploit links to Wikipedia and DBpedia to derive temporal information relevant to entities, namely years and intervals of years.  ...  We collected text paragraphs from the two digital history books used in D2: Timeline of World History (Kerr, 2011) and Timelines of History (Ratnikas, 2012), following the procedure described in [11]  ... 
dblp:conf/kdweb/MorbidoniC17 fatcat:uvc3ezgoe5hw5kjuckedpflhhe

From Standard Summarization to New Tasks and Beyond: Summarization with Manifold Information [article]

Shen Gao, Xiuying Chen, Zhaochun Ren, Dongyan Zhao, Rui Yan
2020 arXiv   pre-print
Instead, there is much manifold information to be summarized, such as the summary for a web page based on a query in the search engine, extreme long document (e.g., academic paper), dialog history and  ...  In general, text summarization algorithms aim at using a plain text document as input and then output a summary. However, in real-world applications, most of the data is not in a plain text format.  ...  Acknowledgements We would like to thank the anonymous reviewers for their constructive comments.  ... 
arXiv:2005.04684v1 fatcat:35ub2qoaezdq7fw7ptbvrbj37i

Event Digest

Arunav Mishra, Klaus Berberich
2016 Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval - SIGIR '16  
Using Wikipedia articles as gold standard summaries in our evaluation, we find that the most holistic digest of an event is generated with our method that integrates all event dimensions.  ...  For a general user, easy access to vast amounts of online information available on past events has made retrospection much harder.  ...  Test Queries are generated from the timeline of modern history 2 in Wikipedia that contains the most prominent news events in the past.  ... 
doi:10.1145/2911451.2911526 dblp:conf/sigir/MishraB16 fatcat:vxehlab6sfho5nhewgxo2jzpoe

Incorporating Extra Knowledge to Enhance Word Embedding

Arpita Roy, Shimei Pan
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
traditional word embeddings are mainly designed to capture the semantic relatedness between co-occurred words in a predefined context, it may not be effective in encoding other information that is important for  ...  Acknowledgments We would like to thank the anonymous reviewers for their constructive comments.  ...  article, and then use the reader focused article information to guide the summary generation process.  ... 
doi:10.24963/ijcai.2020/676 dblp:conf/ijcai/GaoCR0020 fatcat:n3hj4lad2vcphpmzdnwgflp7x4

Timeline Generation: Tracking individuals on Twitter [article]

Jiwei Li, Claire Cardie
2014 arXiv   pre-print
In this paper, we propose a unsupervised framework to reconstruct a person's life history by creating a chronological list for personal important events (PIE) of individuals based on the tweets they published  ...  For evaluation, we have built a new golden standard Timelines based on Twitter and Wikipedia that contain PIE related events from 20 ordinary twitter users and 20 celebrities.  ...  ACKNOWLEDGEMENT We thank Myle Ott, Sujian Li, Alan Ritter, Wenjie Li and Chris Dyer for their insightful discussions and suggestions.  ... 
arXiv:1309.7313v3 fatcat:rt3mrsyrbbefvasbzoqhf4mzzu

Wikipedia graph mining: dynamic structure of collective memory [article]

Volodymyr Miz, Kirell Benzi, Benjamin Ricaud, Pierre Vandergheynst
2018 arXiv   pre-print
Collective user activity on its pages leaves publicly available footprints of human behavior, making Wikipedia an excellent source for analysis of collective behavior.  ...  We extract dynamical patterns of collective activity and demonstrate that they correspond to meaningful clusters of associated events, reflected in the Wikipedia articles.  ...  ACKNOWLEDGMENTS We would like to thank Michaël Defferrard and Andreas Loukas for fruitful discussions and useful suggestions.  ... 
arXiv:1710.00398v5 fatcat:5uxdqk52ifbs7g67rn47ypijwq

Digital History Meets Wikipedia

Adam Jatowt, Daisuke Kawai, Katsumi Tanaka
2016 Proceedings of the 16th ACM/IEEE-CS on Joint Conference on Digital Libraries - JCDL '16  
In particular, we study Wikipedia articles on historical persons.  ...  Wikipedia is the result of a collaborative effort aiming to represent human knowledge and to make it accessible for everyone.  ...  Knowledge Extraction from Historical Documents" and by Grant-in-Aid for Scientific Research (No. 15H01718) from MEXT of Japan.  ... 
doi:10.1145/2910896.2910911 dblp:conf/jcdl/JatowtKT16 fatcat:5eibvly2trcgxc6gvgovdf7oc4

Anomaly detection in the dynamics of web and social networks [article]

Volodymyr Miz, Benjamin Ricaud, Kirell Benzi, Pierre Vandergheynst
2019 arXiv   pre-print
To demonstrate its efficiency, we apply it to two datasets: Enron Email dataset and Wikipedia page views.  ...  In this work, we propose a new, fast and scalable method for anomaly detection in large time-evolving graphs.  ...  ACKNOWLEDGMENTS We would like to thank Michaël Defferrard and Andreas Loukas for fruitful discussions and useful suggestions.  ... 
arXiv:1901.09688v1 fatcat:2wddpbjo3jfnbharvstd4r46gq

Summary Markov Models for Event Sequences [article]

Debarun Bhattacharjya, Saurabh Sihag, Oktie Hassanzadeh, Liza Bialik
2022 arXiv   pre-print
We show that a unique minimal influencing set exists for any set of event types of interest and choice of summary function, formulate two novel models from the general family that represent specific sequence  ...  dynamics, and propose a greedy search algorithm for learning them from event sequence data.  ...  Acknowledgments We thank the anonymous reviewers for helpful feedback. This research is based upon work supported in part by U.S. DARPA KAIROS Program No. FA8750-19-C-0206.  ... 
arXiv:2205.03375v1 fatcat:h6i3cqdvxbfh7hyyrgpa3sb4vi

EventNarrative: A large-scale Event-centric Dataset for Knowledge Graph-to-Text Generation [article]

Anthony Colas, Ali Sadeghian, Yue Wang, Daisy Zhe Wang
2022 arXiv   pre-print
The datasets that have a paired KG and text, are small scale and manually generated or generated without a rich ontology, making the corresponding graphs sparse.  ...  However, our data generation system can still be adapted to other other types of KG data.  ...  In order to construct an exhaustive search algorithm for in-text Wikipedia dates, we refer to the Wikipedia Style Manual 2 which defines acceptable date formats when editing Wikipedia articles.  ... 
arXiv:2111.00276v2 fatcat:fo7clqopkzfd7mvpi5oy3g5wvy

Answering Definition Questions via Temporally-Anchored Text Snippets

Marius Pasca
2008 International Joint Conference on Natural Language Processing  
need for complex lexical resources, or specialized processing modules dedicated to finding definitions.  ...  Experiments on standard test question sets show that temporally-anchored text snippets allow for efficiently answering definition questions at accuracy levels comparable to the best systems, without any  ...  The source of the reference timelines is the condensed history article that is part of the main description page of each country in Wikipedia.  ... 
dblp:conf/ijcnlp/Pasca08 fatcat:yq6hgbox45gixkv3ydj4bkatuy

Enriching Taxonomies With Functional Domain Knowledge

Nikhita Vedula, Patrick K. Nicholson, Deepak Ajwani, Sourav Dutta, Alessandra Sala, Srinivasan Parthasarathy
2018 The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval - SIGIR '18  
Our approach learns a high-dimensional embedding for the existing concepts of the taxonomy, as well as for the new concepts.  ...  To this end we propose a novel framework, ETF, to enrich large-scale, generic taxonomies with new concepts from resources such as news and research publications.  ...  We infer the embedding for each new concept as in Section 4.2, from the doc2vec model trained on Wikipedia articles, after making sure that any article pages on the new concepts, and pages that link to  ... 
doi:10.1145/3209978.3210000 dblp:conf/sigir/VedulaNADS018 fatcat:bhauejtucze4lozvpfitlwxcxy
« Previous Showing results 1 — 15 out of 511 results