Filters








16 Hits in 7.4 sec

A Pipeline Tweet Contextualization System at INEX 2013

Khaled Hossain Ansary, Anh Tuan Tran, Nam Khanh Tran
2013 Conference and Labs of the Evaluation Forum  
This article describes a pipeline system and preliminary results for Tweet Contextualization at INEX 2013. The system consists of three steps: tweet analysis, passage retrieval and summarization.  ...  Finally, a multi-document summarization system (MEAD) is used to generate the output document with a limit of 500 words.  ...  developed as part of the participation in the Tweet Contextualization track of INEX 2013.  ... 
dblp:conf/clef/AnsaryTT13 fatcat:nwsmll5hbfde7cheeud3kkwbmi

Statistical and Semantic Approaches for Tweet Contextualization

Meriem Amina Zingla, Latiri Chiraz, Yahya Slimani, Catherine Berrut
2015 Procedia Computer Science  
The effectiveness of our approaches is proved through an experimental study conducted on the INEX 2013 collection.  ...  The task of tweet contextualization was organized around these issues. It aims to provide an automatic readable context explaining a given tweet, in order to help the reader understand this latter.  ...  Thus, the INEX 2013 tweet contextualization track proposed to answer questions of the form "What is this tweet about?"  ... 
doi:10.1016/j.procs.2015.08.171 fatcat:3kveavukxvebphlq5yrxumjw7q

Towards Events Tweet Contextualization Using Social Influence Model and Users Conversations

Rami Belkaroui, Rim Faiz
2015 Proceedings of the 5th International Conference on Web Intelligence, Mining and Semantics - WIMS '15  
To evaluate our approach, we construct a reference summary by asking assessors to manually select the most informative tweets as a summary.  ...  In order, to make tweet understandable to a reader, it is therefore necessary to know their context.  ...  This motivated the proposal in 2011 of a new track at Clef INEX lab of Tweet Contextualization.  ... 
doi:10.1145/2797115.2797134 dblp:conf/wims/BelkarouiF15 fatcat:dwmuauybhzgw5f56wq4647kl4m

User-Tweet Interaction Model and Social Users Interactions for Tweet Contextualization [chapter]

Rami Belkaroui, Rim Faiz, Pascale Kuntz
2015 Lecture Notes in Computer Science  
To evaluate our approach, we construct a reference summary by asking assessors to manually select the most informative tweets as a summary.  ...  In this paper, we propose an approach for tweet contextualization task which combines different types of signals from social users interactions to provide automatically information that explains the tweet  ...  Recently, [10] modified the method presented at INEX 2011, 2012 and 2013 [12, 13] by adding the influence of topic-comment relationship on contextualization.  ... 
doi:10.1007/978-3-319-24069-5_14 fatcat:g5ptv6pqcrgxtglvjuzxim6fbu

Time-aware topic-based contextualization

Nam Khanh Tran
2014 Proceedings of the 23rd International Conference on World Wide Web - WWW '14 Companion  
In this PhD proposal, we address three novel research questions: detecting uninterpretable pieces in documents, retrieving contextual information and constructing compact context for the documents, then  ...  Tweet Contextualization This section describes our initial work [2] for the Tweet Contextualization track at INEX 2013. 1 Given a new tweet and a recent dump of the Wikipedia, the system is required  ...  We conducted a pipeline system based on the following process: tweet analysis, context retrieval and construction of the answer.  ... 
doi:10.1145/2567948.2567957 dblp:conf/www/Tran14 fatcat:ho6r3rszlrfh7hzjleplrczqha

Entity Retrieval and Text Mining for Online Reputation Monitoring [article]

Pedro Saleiro
2018 arXiv   pre-print
This is a challenging problem which traditional entity search systems cannot cope with.  ...  As such, we propose the inclusion of entity retrieval capabilities as a first step towards the extension of current ORM capabilities.  ...  We start by describing our participation at the Filtering task of RepLab 2013 [32] . We developed a supervised method to classify tweets as relevant or non-relevant to given target entity.  ... 
arXiv:1801.07743v1 fatcat:f56lljaavnd6zm4vnngs2m3tga

Learning from User Interactions in Personal Search via Attribute Parameterization

Michael Bendersky, Xuanhui Wang, Donald Metzler, Marc Najork
2017 Proceedings of the Tenth ACM International Conference on Web Search and Data Mining - WSDM '17  
Given an event entity, we propose a graphbased framework for retrieving a ranked list of related events that a user is likely to be interested in attending.  ...  the challenge of feature sparseness and noisiness, and (b) the semantic mismatch problem in a self-contained and principled manner.  ...  In contrast, events are described by a short title, typically not stored in a knowledge base, and are present only at one, or at most a handful of web pages.  ... 
doi:10.1145/3018661.3018712 dblp:conf/wsdm/BenderskyWMN17 fatcat:vkfkqj4spjdtpe2cuuhm62kl5y

Automated Fact-Checking for Assisting Human Fact-Checkers

Preslav Nakov, David Corney, Maram Hasanain, Firoj Alam, Tamer Elsayed, Alberto Barrón-Cedeño, Paolo Papotti, Shaden Shaar, Giovanni Da San Martino
2021 Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence   unpublished
These include identifying claims worth fact-checking, detecting relevant previously fact-checked claims, retrieving relevant evidence to fact-check a claim, and actually verifying a claim.  ...  These phenomena have led to the modern incarnation of the fact-checker --- a professional whose main aim is to examine claims using available evidence and to assess their veracity.  ...  Acknowledgments This work was made possible in part by grant# NPRP 7-1330-2-483 from the Qatar National Research Fund (a member of Qatar Foundation). Partial support also comes from a Google gift.  ... 
doi:10.24963/ijcai.2021/619 fatcat:nfqws64wgzdadi7w6mkgvvychm

Reliable and low-cost test collections construction using machine learning [article]

Rahman, Md Mustafizur (Ph. D. In Information Studies), Austin, The University Of Texas At, Matthew A. Lease, Mucahid Kutlu
2022
I present my work in four directions: i) understanding the effects of the participating systems on the qualities of a test collection, ii) modeling a machine learning system to reduce the human annotation  ...  In the first direction, I investigate how the number of participating systems impacts the qualities of a test collection.  ...  While experimenting using the INEX test collections, Pal et al. [2011] also find that to build a reliable test collection at minimal cost, WaS judging is better than NaD judging.  ... 
doi:10.26153/tsw/36072 fatcat:5nuuuzjs6ze4pnq4sq66pvb4qi

Discovering and disambiguating named entities in text

Johannes Hoffart
2013 Proceedings of the 2013 Sigmod/PODS Ph.D. symposium on PhD symposium - SIGMOD'13 PhD Symposium  
The first contribution is a robust disambiguation method using a graph algorithm that makes use of the coherence among entities in the input.  ...  A key challenge is the ambiguity of entity names, requiring robust methods to disambiguate names to canonical entities registered in a knowledge base.  ...  INEX Link-the-Wiki The initial challenge has been held as part of the INEX in 2008 [HGT08] , where the goal was to recreate Wikipedia links on a per-mention basis.  ... 
doi:10.1145/2483574.2483582 dblp:conf/sigmod/Hoffart13 fatcat:bjqq5uusrragdm7ewraf63of4e

Rachel Mor-ton, and Hartmut Wick

Renlong Ai, Maria Bissiri, Hartmut Pfitzinger, Hans
2013 References Eric Atwell   unpublished
This is followed by a suggestion of possible directions of future work.  ...  This survey examines the feedback in current Computer Assisted Pronunciation Training (CAPT) systems and focus on perceptual feedback.  ...  This research is still at the preliminary stage, therefore any feedback or advice is much appreciated.  ... 
fatcat:jiw36rob5nhlhd3zeknq2ohate

Scalable Text Mining with Sparse Generative Models [article]

Antti Puurula
2016 arXiv   pre-print
This thesis proposes a solution to scalable text mining: generative models combined with sparse computation.  ...  order of magnitude decrease in classification times for Wikipedia article categorization with a million classes.  ...  Acknowledgements We'd like to thank Kaggle and the LSHTC organizers for their work in making the competition a success, and the machine learning group at the University of Waikato for the computers we  ... 
arXiv:1602.02332v1 fatcat:2urzib3btveslj5ggie55irxwq

Joint Discourse-aware Concept Disambiguation and Clustering

Angela Petra Fahrni
2016
Concept disambiguation is the task of linking common nouns and proper names in a text -henceforth called mentions -to their corresponding concepts in a predefined inventory.  ...  We approach the question which context is relevant to disambiguate a mention from a discourse perspective and state that different mentions require different notions of contexts.  ...  , we report the results for the best system at TAC 2013 (Best), the median performance of all systems that participated at TAC 2013 (Median) and the results of closely related approaches.  ... 
doi:10.11588/heidok.00020737 fatcat:vhljgiqbrbcwtpjxce6k4vcp2a

Question answering and query processing for extended knowledge graphs [article]

Mohamed Yahya, Universität Des Saarlandes, Universität Des Saarlandes
2016
I also thank Shady Elbassiouni for his help at the start of my PhD.  ...  Gerhard is a brilliant scientist and leader. The breadth and depth of his knowledge is impressive and he has a keen eye for detail. I hope to be like him one day.  ...  This work is an extension of Sawant and Chakrabarti (2013) , which mapped segments onto semantic types or considered them as contextual segments.  ... 
doi:10.22028/d291-25428 fatcat:ronhjub3pbachaineag5i6n3py

When in doubt ask the crowd : leveraging collective intelligence for improving event detection and machine learning [article]

Mihai Georgescu, University, My
2019
An online system and a video tutorial have been made available at http://www. l3s.de/wiki-events.  ...  While integrated in the overall system, sign + DS/o shows a perfect precision at the cost of recall.  ... 
doi:10.15488/8457 fatcat:ikul6z5pijej7lixobizpb3zvq
« Previous Showing results 1 — 15 out of 16 results