Filters








58,772 Hits in 4.7 sec

Head, modifier, and constraint detection in short texts

Zhongyuan Wang, Haixun Wang, Zhirui Hu
2014 2014 IEEE 30th International Conference on Data Engineering  
In many cases, short texts such as search queries do not follow grammar rules, and existing approaches for head and modifier detection are coarse-grained, domain specific, and/or require labeling of large  ...  Head and modifier detection is an important problem for applications that handle short texts such as search queries, ads keywords, titles, captions, etc.  ...  In this paper, we focus on head, modifier, and constraint detection for short texts.  ... 
doi:10.1109/icde.2014.6816658 dblp:conf/icde/WangWH14 fatcat:xjh5vpij4vcvlodiuezruxckxq

Unsupervised Head--Modifier Detection in Search Queries

Zhongyuan Wang, Fang Wang, Haixun Wang, Zhirui Hu, Jun Yan, Fangtao Li, Ji-Rong Wen, Zhoujun Li
2016 ACM Transactions on Knowledge Discovery from Data  
Finally, we derive weighted concept patterns that are concise, accurate, and have strong generalization power in head-modifier detection.  ...  Query head-modifier detection can help search engines to obtain particularly relevant content, which is also important for applications such as ads matching and query recommendation.  ...  Also, the knowledge of heads and modifiers can be used for short text matching applications such as advertisement matching in search engines.  ... 
doi:10.1145/2988235 fatcat:wtz2jxcn5jhgzlcixbl2sys2f4

The head-modifier principle and multilingual term extraction

ANDREW HIPPISLEY, DAVID CHENG, KHURSHID AHMAD
2005 Natural Language Engineering  
The theoretical claims revolve around the head-modifier principle which determines the formation of a major class of compounds.  ...  language users, and therefore has great significance for the development of language engineering technologies.  ...  For some of the definitions the constraint on suitable material is partially based on the head-modifier principle, as shown in for Prepositional Phrase constraint in (8).  ... 
doi:10.1017/s1351324904003535 fatcat:2wfqbt46nbbbdb7bh224wkexyu

Publicly detectable techniques for the protection virtual components

Gang Qu
2001 Proceedings of the 38th conference on Design automation - DAC '01  
In this paper, we propose a new watermarking method which (i) allows the watermark to be public detected without forensic experts, (ii) gives little advantage to attackers for forgery, and (iii) does not  ...  However, the trade-off between hard-to-attack and easy-to-detect and the lack of efficient detection schemes are the major obstacles for digital signatures to thrive.  ...  The ASCII code of this short text is put as the header for the public 3 We refer here IP library as both the internal IPs and external IPs in the public domain where watermarks may not be imposed. watermark  ... 
doi:10.1145/378239.378565 dblp:conf/dac/Qu01 fatcat:renkhzk7jbehdfmrrya3be2yoy

Modeling Document-level Causal Structures for Event Causal Relation Identification

Lei Gao, Prafulla Kumar Choubey, Ruihong Huang
2019 Proceedings of the 2019 Conference of the North  
The causal structures include heavy involvements of document-level main events in causal relations as well as several types of finegrained constraints that capture implications from certain sentential  ...  We aim to comprehensively identify all the event causal relations in a document, both within a sentence and across sentences, which is important for reconstructing pivotal event structures.  ...  Disclaimer: the views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied  ... 
doi:10.18653/v1/n19-1179 dblp:conf/naacl/GaoCH19 fatcat:lhdvgucoffaztgu7c3kcdqcnhu

Inducing Terminology for Lexical Acquisition

Roberto Basili, Gianluca De Rossi, Maria Teresa Pazienza
1997 Conference on Empirical Methods in Natural Language Processing  
The problem of detecting terms in textual corpora has been approached in a complex framework.  ...  This has useful implications on more complex text processing tasks (e.g. information extraction). An hybrid symbolic and probabilistic approach to terminology extraction has been defined.  ...  It is a concept, as it requires a larger number of constraints on the information to be searched for in texts.  ... 
dblp:conf/emnlp/BasiliRP97 fatcat:rtms7gvnfrcj5ltbtsmih7xrdu

The time-course of morphological constraints: Evidence from eye-movements during reading

I CUNNINGS, H CLAHSEN
2007 Cognition  
We found that the morphological constraint affected both early and late eye-movement measures, whereas the semantic constraint for singular non-heads only affected late measures of processing.  ...  Lexical compounds in English are constrained in that the non-head noun can be an irregular but not a regular plural (e.g. mice eater vs.  ...  We are grateful to Keith Rayner, one additional anonymous Cognition reviewer, and the members of the Psycholinguistics Research Group at our department for comments and helpful discussion.  ... 
doi:10.1016/j.cognition.2006.07.010 pmid:16934793 fatcat:m3tjk2ek5beltdoptynaocixpu

Midge: Generating Image Descriptions From Computer Vision Detections

Margaret Mitchell, Jesse Dodge, Amit Goyal, Kota Yamaguchi, Karl Stratos, Xufeng Han, Alyssa C. Mensch, Alexander C. Berg, Tamara L. Berg, Hal Daumé III
2012 Conference of the European Chapter of the Association for Computational Linguistics  
By leveraging syntactically informed word co-occurrence statistics, the generator filters and constrains the noisy detections output from a vision system to generate syntactic trees that detail what the  ...  This paper introduces a novel generation system that composes humanlike descriptions of images from computer vision detections.  ...  This work is supported in part by Michael Collins and by NSF Faculty Early Career Development (CA-REER) Award #1054133.  ... 
dblp:conf/eacl/MitchellDGYSHMBBD12 fatcat:jvdwaz75tvhazm2y5tvvfdjy6a

Adapting Coreference Resolution for Narrative Processing

Quynh Ngoc Thi Do, Steven Bethard, Marie-Francine Moens
2015 Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing  
The idea is to perform inference via an Integer Linear Programming (ILP) formulation with the features of narratives adopted as soft constraints.  ...  We present a novel method to adapt a supervised coreference resolution system trained on newswire to short narrative stories without retraining the system.  ...  Acknowledgment This work acknowledges the financial support of the Future and Emerging Technologies (FET) programme within the Seventh Framework Programme for Research of the European Commission, under  ... 
doi:10.18653/v1/d15-1271 dblp:conf/emnlp/DoBM15 fatcat:kb5iio6tdrd2xpfdg75ivsldne

Rumor Detection on Social Media with Graph Structured Adversarial Learning

Xiaoyu Yang, Yuefei Lyu, Tian Tian, Yifei Liu, Yudong Liu, Xi Zhang
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
In addition to text information, recent detection methods began to exploit the graph structure in the propagation network.  ...  We first build a heterogeneous information network to model the rich information among users, posts, and user comments for detection.  ...  ., 2019] , they perform general attacks without considering the heterogeneity and domain constraints that exist in real-world applications such as rumor detection.  ... 
doi:10.24963/ijcai.2020/197 dblp:conf/ijcai/YangLTLLZ20 fatcat:p7tnn3mkkfby3oc4c5dowyplta

Reflections of accomplishments in natural language based detection and summarization

Susan R. Viscuso
1996 Proceedings of a workshop on held at Baltimore, Maryland October 13-15, 1998 -  
The processing and indexing steps include a part-of-speech tagger, a phrase extractor, a proper name extractor, and a fast syntactic parser that extracts concept like head-modifier relations from the text  ...  INTRODUCTION 1 In Phase III, the GE team focused on accurate context indexing of text documents, generation of effective search queries, extended statistical retrieval with constraints, and document abstracting  ... 
doi:10.3115/1119089.1119101 dblp:conf/tipster/Viscuso98 fatcat:budfpqpssncujeb6r5mi2p7oxm

Building a Lightweight Semantic Model for Unsupervised Information Extraction on Short Listings

Doo Soon Kim, Kunal Verma, Peter Z. Yeh
2012 Conference on Empirical Methods in Natural Language Processing  
Short listings are, however, challenging to process due to their informal styles. In this paper, we present an unsupervised information extraction system for short listings.  ...  Given a corpus of listings, the system builds a semantic model that represents typical objects and their attributes in the domain of the corpus, and then uses the model to extract information.  ...  Acknowledgements We would like to thank Colin Puri and Rey Vasquez for their contribution to this work.  ... 
dblp:conf/emnlp/KimVY12 fatcat:yscbkhpplnbmld3itj64ls6hpm

DASE: Document-Assisted Symbolic Execution for Improving Automated Software Testing

Edmund Wong, Lei Zhang, Song Wang, Taiyue Liu, Lin Tan
2015 2015 IEEE/ACM 37th IEEE International Conference on Software Engineering  
DASE detected 12 previously unknown bugs that symbolic execution without input constraints failed to detect, 6 of which have already been confirmed by the developers.  ...  We propose and implement a new approach, Document-Assisted Symbolic Execution (DASE), to improve automated test generation and bug detection.  ...  This research is supported by the Natural Sciences and Engineering Research Council of Canada, a Google Faculty Research Award, and Ontario Ministry of Research and Innovation.  ... 
doi:10.1109/icse.2015.78 dblp:conf/icse/WongZWLT15 fatcat:pcfxcedk6ne4rnzk6hmmgb2bwy

Broad-coverage biomedical relation extraction with SemRep

Halil Kilicoglu, Graciela Rosemblat, Marcelo Fiszman, Dongwook Shin
2020 BMC Bioinformatics  
In ongoing development, we are redesigning SemRep to increase its modularity and flexibility, and addressing weaknesses identified in the error analysis.  ...  An error analysis reveals named entity recognition/normalization as the largest source of errors (26.9%), followed by argument identification (14%) and trigger detection errors (12.5%).  ...  Rindflesch for his design and development of early SemRep iterations and his supervision until his retirement and François-Michel Lang for his contributions to various aspects of SemRep.  ... 
doi:10.1186/s12859-020-3517-7 pmid:32410573 fatcat:2rsnzh7q4nghjdeh2kpqsxozyy

Improved Sequential Dependency Analysis Integrating Labeling-Based Sentence Boundary Detection

Takanobu OBA, Takaaki HORI, Atsushi NAKAMURA
2010 IEICE transactions on information and systems  
In the new method, we use CRF for soft decision of sentence boundaries and combine it with SDA to retain its online framework.  ...  In this paper, we propose an improved SDA integrating a labeling-based sentence boundary detection (SntBD) technique based on Conditional Random Fields (CRFs).  ...  The bunsetsu that does not modify any bunsetsus in a sentence is called the sentence head. " " and " " are the sentence heads in this figure.  ... 
doi:10.1587/transinf.e93.d.1272 fatcat:bvskoqzwwff5tdymrctlf4yjzu
« Previous Showing results 1 — 15 out of 58,772 results