11,529 Hits in 6.0 sec

Entity Linking and Slot Filling through Statistical Processing and Inference Rules

Daniel M. Bikel, Vittorio Castelli, Radu Florian, Ding-Jung Han
2009 Text Analysis Conference  
This paper presents the design and implementation of the hybrid statistical/rule-based IBM system that performs these two tasks.  ...  The latest such evaluation, the Knowledge Base Population (KBP) part of the Text Analysis Conference 2009, is focusing on two aspects: entity linking and slot filling.  ...  The slots that do not map to relations are filled through an inference engine described in §4.  ... 
dblp:conf/tac/BikelCFH09 fatcat:r7cysf3blngsje67m2zlgby6gm

A generic information extraction architecture for financial applications

L.K.A Wee, L.C Tong, C.L Tan
1999 Expert systems with applications  
It analyzes the input text into a graph structure and subsequently unifies the graph and the ontology for extraction of relevant information, driven by the frame structure during a template filling process  ...  The GIE system is able to extract information from free-form text, further infer and derive new information.  ...  The template filling process will go through each FEIM slot within a template and attempt to fill up the value for the CONTENT attribute of the slot.  ... 
doi:10.1016/s0957-4174(99)00010-x fatcat:k64gvldgfbhwpmmttgepvlychm

University of Florida Knowledge Base Acceleration

Morteza Shahriari Nia, Christan Earl Grant, Yang Peng, Daisy Zhe Wang, Milenko Petrovic
2013 Text Retrieval Conference  
In this paper we will present the system design and algorithm adopted by the GatorDSR team, University of Florida to efficiently process TREC KBA 2013 -SSF track.  ...  Here we will describe the system as well as the details the algorithms used to extract slot values for the given slot name.  ...  The file is processed in time order, in a tuple-at-a-time fashion to minimize the impact on accuracy. We define two classes of rules deduplication rules and inference rules.  ... 
dblp:conf/trec/NiaGPWP13 fatcat:iquzxmk2l5e75flfwn7byencie

English Slot Filling with the Knowledge Resolver System

Hans Chalupsky
2013 Text Analysis Conference  
This paper describes the Knowledge Resolver system (KRes) and its performance on the TAC-KBP 2013 English Slot Filling task.  ...  KRes is a logic-based inference system aimed at improving statistical relation extraction by deduction and abduction inference towards the best document-level interpretation.  ...  KRes is a logic-based inference system based on the Power-Loom knowledge representation and reasoning system, 3 aimed at improving statistical relation extraction through story-level inference.  ... 
dblp:conf/tac/Chalupsky13 fatcat:zj2ywk3abja7fjjpyggmx5ywpm

DRAFT – Cold Start Knowledge Base Population with the Knowledge Resolver System for TAC-KBP 2015 – DRAFT

Hans Chalupsky
2015 Text Analysis Conference  
KRes is a logic-based inference system aimed at improving statistical relation extraction by deduction and abduction inference towards the best document-level interpretation.  ...  Our 2015 system has some slightly improved slot-filling coverage of 22 slots (as compared to 19 from last year, not counting inverses), and an improved f 1=0.24 measured on a 50 query slot filling test  ...  The views and conclusions contained herein are those of the author and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of DARPA  ... 
dblp:conf/tac/Chalupsky15 fatcat:afgvt5fnhvftpkujhnu3pzedau

Personal Attributes Extraction in Chinese Text Bakeoff in CLP 2014: Overview

Ruifeng Xu, Shuai Wang, Feng Shi, Jian Xu
2014 Proceedings of The Third CIPS-SIGHAN Joint Conference on Chinese Language Processing  
This task is designed to evaluate the techniques for extracting person specific attributes from unstructured Chinese texts, which is similar to slot filling, but focuses on person attributes.  ...  The task organizer manually constructs the query names and corresponding documents.  ...  Generally speaking, the mainstream techniques for slot filling and person attributes extraction may be camped into two major approaches, namely: Rule-based approach and statistics-based ones [2, 3, 4]  ... 
doi:10.3115/v1/w14-6817 dblp:conf/acl-sighan/XuWSX14 fatcat:h2uvyjnbinec7gstl57mfuy5pa

Stanford at TAC KBP 2016: Sealing Pipeline Leaks and Understanding Chinese

Yuhao Zhang, Arun Tejasvi Chaganty, Ashwin Paranjape, Danqi Chen, Jason Bolton, Peng Qi, Christopher D. Manning
2016 Text Analysis Conference  
We describe Stanford's entries in the TAC KBP 2016 Cold Start Slot Filling and Knowledge Base Population challenge.  ...  mentions and inferred relations.  ...  Acknowledgments The Stanford KBP 2016 team would like to acknowledge Gabor Angeli and Victor Zhong for their useful discussions about the 2016 system and great efforts in the development of Stanford's  ... 
dblp:conf/tac/ZhangCPCBQM16 fatcat:lp4pg2qn5fdnjbeewyzna6dlzq

A fully statistical approach to natural language interfaces

Scott Miller, David Stallard, Robert Bobrow, Richard Schwartz
1996 Proceedings of the 34th annual meeting on Association for Computational Linguistics -  
The system consists of three stages of processing: parsing, semantic interpretation, and discourse. Each of these stages is modeled as a statistical process.  ...  We present a natural language interface system which is based entirely on trained statistical models.  ...  not in Ms REITERATE -slot filled in both Me and Ms; value the same CHANGE -slot filled in both Me and Ms; value different IRRELEVANT -slot not filled in either Me or Ms This work was supported by the  ... 
doi:10.3115/981863.981871 dblp:conf/acl/MillerSBS96 fatcat:3dnbexazlrhztokyuefx35w4va

GLUCOSE: GeneraLized and COntextualized Story Explanations [article]

Nasrin Mostafazadeh, Aditya Kalyanpur, Lori Moon, David Buchanan, Lauren Berkowitz, Or Biran, Jennifer Chu-Carroll
2020 arXiv   pre-print
When humans read or listen, they make implicit commonsense inferences that frame their understanding of what happened and why.  ...  Each GLUCOSE entry includes a story-specific causal statement paired with an inference rule generalized from the statement. This paper details two concrete contributions.  ...  We thank David Ferrucci for his valuable insights and support throughout the GLUCOSE project.  ... 
arXiv:2009.07758v2 fatcat:gwyqq5dkybbo5hzciuvhryxmue

A rule-based simulation system for discrete event systems

1988 Journal of Chemical Engineering of Japan  
To prevent the model from being incomplete, the simulation system clarifies the causal relationship between rules and frames and detects the rules which are never executed or which have possibilities of  ...  pG,pL = densities of gas and liquid respectively tw = shear stress exerted by a columnwall [kg-nr3] [kg-m Literature Cited 1) Akita, K. and F. Yoshida: Ind. Eng. Chem. Process Des.  ...  The purpose of simulation is to study how batches flow through processes under various process configurations and operational policies. For simplicity, the following is assumed.  ... 
doi:10.1252/jcej.21.482 fatcat:o77xyobc7fdcfc2qokoa3o42oi

Protein Structures and Information Extraction from Biological Texts: The PASTA System

R. Gaizauskas, G. Demetriou, P. J. Artymiuk, P. Willett
2003 Bioinformatics  
Motivation: The rapid increase in volume of protein structure literature means useful information may be hidden or lost in the published literature and the process of finding relevant material, sometimes  ...  The evaluation resources (manually annotated corpora) are also available through the website: http://  ...  The authors would like to thank Ruth Spriggs and Darren South for their expert assistance in tagging terminology and filling templates.  ... 
doi:10.1093/bioinformatics/19.1.135 pmid:12499303 fatcat:oynciggvina5pkpwzhzm55yil4

DIRT @SBT@discovery of inference rules from text

Dekang Lin, Patrick Pantel
2001 Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '01  
Inference rules are extremely important in many fields such as natural language processing, information retrieval, and artificial intelligence in general.  ...  In this paper, we propose an unsupervised method for discovering inference rules from text, such as "X is author of Y ≈ X wrote Y", "X solved Y ≈ X found a solution to Y", and "X caused Y ≈ Y is triggered  ...  This research was partly supported by Natural Sciences and Engineering Research Council of Canada grant OGP121338 and scholarship PGSB207797.  ... 
doi:10.1145/502512.502559 fatcat:p4bywzdfgrg2laryvoj2ibjsfm

Automatic knowledge extraction from documents

J. Fan, A. Kalyanpur, D. C. Gondek, D. A. Ferrucci
2012 IBM Journal of Research and Development  
Second, additional semantics are inferred from aggregate statistics of the automatically extracted shallow knowledge.  ...  In this paper, we describe in detail what kind of shallow knowledge is extracted, how it is automatically done from a large corpus, and how additional semantics are inferred from aggregate statistics.  ...  Relation detectors are also applied during the corpus processing phase to fill frame slots not captured by ESG (e.g., isa slot).  ... 
doi:10.1147/jrd.2012.2186519 fatcat:tlmlkjsxgjelpk45s3tvsvhcpu

Rationally Reappraising ATIS-based Dialogue Systems

Jingcheng Niu, Gerald Penn
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
This paper presents a detailed account of these shortcomings, our proposed repairs, our rulebased grammar and the neural slot-filling architectures associated with ATIS.  ...  Recent state-of-the-art neural models have obtained F1-scores near 98% on the task of slot filling.  ...  direction of further research for slot filling, in our view.  ... 
doi:10.18653/v1/p19-1550 dblp:conf/acl/NiuP19 fatcat:2nav3c6ucjd57jk3bn4wyy2iyu

Bridging the Gap Between Clean Data Training and Real-World Inference for Spoken Language Understanding [article]

Di Wu, Yiren Chen, Liang Ding, Dacheng Tao
2021 arXiv   pre-print
For example, Intent detection (ID), and slot filling (SF) require its upstream automatic speech recognition (ASR) to transform the voice into text. In this case, the upstream perturbations, e.g.  ...  However, existing models are trained on clean data, which causes a gap between clean data training and real-world inference.  ...  There are 65 slot labels and 48K distinct words in this corpus. The detailed statistic can be found in Table-2 .  ... 
arXiv:2104.06393v1 fatcat:ys42ghohjrgy5a7fmo2ordpjgi
« Previous Showing results 1 — 15 out of 11,529 results