Filters








19 Hits in 8.3 sec

A Hybrid Tweet Contextualization System using IR and Summarization

Pinaki Bhaskar, Somnath Banerjee, Sivaji Bandyopadhyay
2012 Conference and Labs of the Evaluation Forum  
The INEX TC task has two main sub tasks, Focused IR and Automatic Summarization. In the Focused IR system, we first preprocess the Wikipedia documents and then index them using Nutch with NE field.  ...  Each retrieved sentence is assigned a ranking score in the Automatic Summarization system. The answer passage includes the top ranked retrieved sentences with a limit of 500 words.  ...  We acknowledge the support of the IFCPAR funded Indo-French project "An Advanced Platform for Question Answering Systems" and the DIT, Government of India funded project "Development of Cross Lingual Information  ... 
dblp:conf/clef/BhaskarBB12 fatcat:d7sbdp2v6jedbil4iohgenpjmm

Answering Questions from Multiple Documents - the Role of Multi-Document Summarization

Pinaki Bhaskar
2013 Recent Advances in Natural Language Processing  
The system is tested on data set of INEX QA track from 2011 to 2013 and best readability score was achieved.  ...  The system clusters similar texts from the graph using this edge score. Each cluster gets a weight and has a cluster center.  ...  Acknowledgments We acknowledge the support of the DeitY, MCIT, Govt. of India funded project "Development of Cross Lingual Information Access (CLIA) System Phase II".  ... 
dblp:conf/ranlp/Bhaskar13 fatcat:mjw255widrfkxct2diozlxro2y

Tweet Contextualization (Answering Tweet Question) - the Role of Multi-document Summarization

Pinaki Bhaskar, Somnath Banerjee, Sivaji Bandyopadhyay
2013 Conference and Labs of the Evaluation Forum  
In our system there are three major sub-systems; i) Offline multi-document summarization, ii) Focused IR and iii) online multi-document Summarization.  ...  The Offline multi-document summarization system is based on document graph, clustering and sentence compression. In the Focused IR system, Wikipedia documents are indexed using Lucene with NE field.  ...  of Cross Lingual Information Access (CLIA) System Phase II".  ... 
dblp:conf/clef/BhaskarBB13 fatcat:bdhrsixvhjft3jcitffjjad2f4

BooksOnline'11

Gabriella Kazai, Carsten Eickhoff, Peter Brusilovsky
2011 Proceedings of the 20th ACM international conference on Information and knowledge management - CIKM '11  
From the accepted papers two main themes became salient: 1) Information retrieval and information extraction methods focused on enhancing digital libraries, and 2) Studies and analyses of reading experience  ...  The workshop boasts a high quality program, including keynote addresses by Ville Miettinnen, CEO of Microtask and Adam Farquhar, Head of Digital Library Technology at The British Library.  ...  The author motivates the need for a hybrid system that exploits the benefits of large scale document archives and human computing.  ... 
doi:10.1145/2063576.2064042 dblp:conf/cikm/KazaiEB11 fatcat:45py6hnn2rbqfioqi3i3rxfsmm

When time meets information retrieval: Past proposals, current plans and future trends

Bilel Moulahi, Lynda Tamine, Sadok Ben Yahia
2016 Journal of information science  
With the advent of Web search and the large amount of data published on the Web sphere, a tremendous amount of documents become strongly time-dependent.  ...  First, we attempt to motivate the importance of temporal signals, whenever combined with other relevance features, in accounting for document relevance.  ...  For instance, the ROUGE measure which is used for the automatic evaluation of summaries is found to be unable to distinguish between automatic and human summaries.  ... 
doi:10.1177/0165551515607277 fatcat:c7zu437drreq5dqlbka646qnby

Excavating the mother lode of human-generated text: A systematic review of research that uses the wikipedia corpus

Mohamad Mehdi, Chitu Okoli, Mostafa Mesgari, Finn Årup Nielsen, Arto Lanamäki
2017 Information Processing & Management  
[26] , discusses the use of Wikipedia at the TREC QA track and is summarized by Medelyan et al. [78] .  ...  [123] described TopX, a system that intends to merge two points of view for processing top-k query for semi-structured data, database systems and IR.  ... 
doi:10.1016/j.ipm.2016.07.003 fatcat:qgjeatizfzbyjkbo4rsuxea76y

Frontiers, challenges, and opportunities for information retrieval

James Allan, Bruce Croft, Alistair Moffat, Mark Sanderson
2012 SIGIR Forum  
Effectively integrating human computation in IR systems represents a broad interdisciplinary challenge, spanning information and computer science, psychology, sociology, and economics.  ...  : (i) user's education level and background knowledge: in particular, illiterate users and children (IR for education); (ii) people with impaired physical abilities -vision, hand movement, etc.; (iii)  ...  The following list summarizes the characteristics (and differences) of current IR and QA systems along three dimensions: the question, the dialogue, and the answer. o QA: Questions are natural language  ... 
doi:10.1145/2215676.2215678 fatcat:mo7fz7o5vzdrfkiisn2rdttg6y

Neural Information Retrieval: A Literature Review [article]

Ye Zhang, Md Mustafizur Rahman, Alex Braylan, Brandon Dang, Heng-Lu Chang, Henna Kim, Quinten McNamara, Aaron Angert, Edward Banner, Vivek Khetan, Tyler McDonnell, An Thanh Nguyen (+3 others)
2017 arXiv   pre-print
While deep NNs have yet to achieve the same level of success in IR as seen in other areas, the recent surge of interest and work in NNs for IR suggest that this state of affairs may be quickly changing  ...  We highlight the successes of neural IR thus far, catalog obstacles to its wider adoption, and suggest potentially promising directions for future research.  ...  Kunal Lad, Yang Liu, Amanda Lucio, Kristen Moor, Daniel Nelson, Geoffrey Potter, Harshal Priyadarshi, Vedhapriya Raman, Eric Roquemore, Juliette Seive, Abhishek Sinha, Ashwini Venkatesh, Yuxuan Wang, and  ... 
arXiv:1611.06792v3 fatcat:i2eqfj5l25epjcytgvifta4y4i

Term-Based Models for Entity Ranking [chapter]

Krisztian Balog
2018 Advanced Topics in Information Retrieval  
We will also introduce an extension to multiple document fields, as a mechanism for preserving some of the structure associated with entities.  ...  To recap, according to our working definition, an entity is a uniquely identifiable "thing," a typed object, with name(s), attributes, and relationships to other entities.  ...  Table 3 .8 shows, for each QALD edition, the total number of questions for all tasks (including hybrid QA), where DBpedia is used as the underlying knowledge base.  ... 
doi:10.1007/978-3-319-93935-3_3 fatcat:dtyxpoiqsbfhtm6m5q24oxp5ii

Rachel Mor-ton, and Hartmut Wick

Renlong Ai, Maria Bissiri, Hartmut Pfitzinger, Hans
2013 References Eric Atwell   unpublished
This survey examines the feedback in current Computer Assisted Pronunciation Training (CAPT) systems and focus on perceptual feedback.  ...  This is followed by a suggestion of possible directions of future work.  ...  Conclusions This paper presents preliminary results on the automatic compilation of comparable corpora with respect to their usage in translator's work.  ... 
fatcat:jiw36rob5nhlhd3zeknq2ohate

Artificial Intelligence and Law

ANTONIO A. MARTINO
1994 International Journal of Law and Information Technology  
Focusing on a single methodology when coupled with automated systems hampers recall -IBM's Watson and Intelligence organizations prove that hybridized multimodal search and brute force NLP based directed  ...  Standardizing Artificial, Computational and Hybrid Intelligence Systems is no different.  ...  user could have made while interacting with the system.  ... 
doi:10.1093/ijlit/2.2.154 fatcat:ff7kwvvn3vcbblhlkf63oqntyu

Artificial Intelligence and the Law

Charlotte Walker-Osborn, Christopher Chan
2017 ITNOW  
Focusing on a single methodology when coupled with automated systems hampers recall -IBM's Watson and Intelligence organizations prove that hybridized multimodal search and brute force NLP based directed  ...  Standardizing Artificial, Computational and Hybrid Intelligence Systems is no different.  ...  user could have made while interacting with the system.  ... 
doi:10.1093/itnow/bwx017 fatcat:62ezubai3fcwlpie35xjq3iyem

Entity Centric Information Retrieval

Xitong Liu
2016 SIGIR Forum  
Although users could use existing IR systems to find relevant entities by going through every returned document and a supporting document collection.  ...  Documents in the same hour are stored in the same batch with a total of 4,973 hours, ranging from October 2011 to April 2012.  ... 
doi:10.1145/2964797.2964815 fatcat:qdmhwfminnaefonienqyggckbm

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.  ...  We researched and developed methods to extract, retrieve and predict entity-centric information spread across the Web.  ...  Entity Retrieval is closely connected with Question answering (QA) though, QA systems focus on understanding the semantic intent of a natural language query and deciding which sentences represent the answer  ... 
arXiv:1801.07743v1 fatcat:f56lljaavnd6zm4vnngs2m3tga

Frontiers, Challenges, and Opportunities for Information Retrieval

Figshare Admin Nsf
2018
, enable retrieval of a wide range of structured and unstructured content, and develop new evaluation methodologies.  ...  Key themes include the need to: move beyond ranked lists of documents to support richer dialog and presentation, represent the context of search and searchers, provide richer support for information seeking  ...  The following list summarizes the characteristics (and differences) of current IR and QA systems along three dimensions: the question, the dialogue, and the answer. o QA: Questions are natural language  ... 
doi:10.25391/nsf.6814988 fatcat:yk4qflro25eghibsp5eyhcpgxe
« Previous Showing results 1 — 15 out of 19 results