Filters








36,100 Hits in 8.7 sec

Inferring Discourse Relations from PDTB-style Discourse Labels for Argumentative Revision Classification

Fan Zhang, Diane J. Litman, Katherine Forbes-Riley
2016 International Conference on Computational Linguistics  
In this paper we propose two approaches to infer discourse relations in a paragraph-level context from annotated PDTB labels.  ...  Penn Discourse Treebank (PDTB)-style annotation focuses on labeling local discourse relations between text spans and typically ignores larger discourse contexts.  ...  Acknowledgments We want to thank the members of the SWoRD and ITSPOKE groups for their helpful feedback and all the anonymous reviewers for their suggestions.  ... 
dblp:conf/coling/ZhangLF16 fatcat:bacmtgmdhrdktefjmi74yfz72y

Relation Alignment for Textual Entailment Recognition

Mark Sammons, V. G. Vinod Vydiswaran, Tim Vieira, Nikhil Johri, Ming-Wei Chang, Dan Goldwasser, Vivek Srikumar, Gourab Kundu, Yuancheng Tu, Kevin Small, Joshua Rule, Quang Do (+1 others)
2009 Text Analysis Conference  
We present an approach to textual entailment recognition, in which inference is based on a shallow semantic representation of relations (predicates and their arguments) in the text and hypothesis of the  ...  We clarify the purpose of alignment in the RTE task, identifying two distinct alignment models, each of which leads to a different type of entailment system.  ...  Acknowledgments This work is funded by a grant from Boeing; by MIAS, a DHS-IDS Center for Multimodal Information Access and Synthesis at UIUC; and with support from DARPA under the Machine Reading program  ... 
dblp:conf/tac/SammonsVVJCGSKT09 fatcat:vjqw4q6kfjfv5nktg5ltqxgnve

Surface Realisation from Knowledge-Bases

Bikash Gyawali, Claire Gardent
2014 Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
A key feature of this approach is that grammar induction is driven by the extended domain of locality principle of TAG (Tree Adjoining Grammar); and that it takes into account both syntactic and semantic  ...  We present a simple, data-driven approach to generation from knowledge bases (KB).  ...  This procedure extracts the subtrees relating the argument variables of a semantic functors such as an event or a role e.g., a tree describing a verb and its arguments as shown in the top Variable names  ... 
doi:10.3115/v1/p14-1040 dblp:conf/acl/GyawaliG14 fatcat:ngc4hhfnknfbhmhyx2imco4gbm

Reading Comprehension with Graph-based Temporal-Casual Reasoning

Yawei Sun, Gong Cheng, Yuzhong Qu
2018 International Conference on Computational Linguistics  
In this work, to answer such questions involving temporal and causal relations, we generate event graphs from text based on dependencies, and rank answers by aligning event graphs.  ...  Experiments on RACE and MCTest show that state-of-the-art methods are notably improved by using our approach as an add-on.  ...  Acknowledgments This work was supported in part by the NSFC under Grants 61772264 and 61572247, and in part by the Qing Lan and Six Talent Peaks Programs of Jiangsu Province.  ... 
dblp:conf/coling/SunCQ18 fatcat:vqqtnk5terf5bdrd5agzbmekum

Mining Semantic Descriptions of Bioinformatics Web Resources from the Literature [chapter]

Hammad Afzal, Robert Stevens, Goran Nenadic
2009 Lecture Notes in Computer Science  
They can be used to facilitate subsequent manual description of services, but also for providing a semantic synopsis of a service that can be used to locate related services.  ...  The method combines terminological processing and dependency parsing of journal articles, and applies information extraction techniques to profile Web services using informative textual passages, related  ...  Acknowledgements We are grateful to Franck Tanoh for the evaluation of the extracted service descriptions.  ... 
doi:10.1007/978-3-642-02121-3_40 fatcat:dtpm6iflsrcgbdn74lt2rnu6py

PyCogent: a toolkit for making sense from sequence

Rob Knight, Peter Maxwell, Amanda Birmingham, Jason Carnes, J Gregory Caporaso, Brett C Easton, Michael Eaton, Micah Hamady, Helen Lindsay, Zongzhi Liu, Catherine Lozupone, Daniel McDonald (+9 others)
2007 Genome Biology  
The toolkit takes advantage of parallel architectures and runs on a range of hardware and operating systems, and is available under the general public license from http://sourceforge.net/projects/pycogent  ...  We have implemented in Python the COmparative GENomic Toolkit, a fully integrated and thoroughly tested framework for novel probabilistic analyses of biological sequences, devising workflows, and generating  ...  Acknowledgements This project used facilities and/or funding provided to GA Huttley by the Australian Partnership for Advanced Computing, Cray Australia Pty.  ... 
doi:10.1186/gb-2007-8-8-r171 pmid:17708774 pmcid:PMC2375001 fatcat:ddz4rlgda5drrflrqmbb3tucxe

Enriching Large-Scale Eventuality Knowledge Graph with Entailment Relations [article]

Changlong Yu, Hongming Zhang, Yangqiu Song, Wilfred Ng, Lifeng Shang
2020 arXiv   pre-print
In this paper, we propose a scalable approach to model the entailment relations between eventualities ("eat an apple" entails "eat fruit").  ...  Detailed experiments and analysis demonstrate the effectiveness of the proposed approach and quality of the resulting knowledge graph.  ...  Eventuality Pre-processing For each eventuality E i , as the verb can be connected to multiple arguments, it has a multiway tree structure rather than a binary tree structure like typed predicates or propositions  ... 
arXiv:2006.11824v1 fatcat:2bgl2kjiejb2ldzljfr6ui4si4

Measuring evolutionary rates of proteins in a structural context

Dariya K. Sydykova, Benjamin R. Jack, Stephanie J. Spielman, Claus O. Wilke
2017 F1000Research  
Katoh K, Standley DM: MAFFT multiple sequence alignment software version 7: improvements in performance and usability. Mol Biol Evol. 2013; 30(4): 772-780.  ...  Joosten RP, te Beek TA, Krieger E, et al.: A series of PDB related databases for everyday needs. Nucleic Acids Res. 2011; 39(Database issue): D411-D419.  ...  Grant information The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.  ... 
doi:10.12688/f1000research.12874.1 pmid:29167739 pmcid:PMC5676193 fatcat:7bau5df6ojam7l2zbnudo34tme

Automatically Extracting Action Graphs from Materials Science Synthesis Procedures [article]

Sheshera Mysore, Edward Kim, Emma Strubell, Ao Liu, Haw-Shiuan Chang, Srikrishna Kompella, Kevin Huang, Andrew McCallum, Elsa Olivetti
2017 arXiv   pre-print
We define the structured representation as a set of linked events made up of extracted scientific entities and evaluate two unsupervised approaches for extracting these structures on expert-annotated articles  ...  We also evaluate a variety of supervised models for extracting scientific entities.  ...  The authors would also like to acknowledge funding from the National Science Foundation Awards 1534340 (DMREF) and IIS-1514053, support from the Office of Naval Research (ONR) under Contract N00014-16-  ... 
arXiv:1711.06872v2 fatcat:3ay7u2zulvcknfov3to5f4ddzu

Learning to Identify Sentence Parallelism in Student Essays

Wei Song, Tong Liu, Ruiji Fu, Lizhen Liu, Hanshi Wang, Ting Liu
2016 International Conference on Computational Linguistics  
Based on this approach, we automatically identify sentence parallelism in more than 2000 student essays and study the correlation between the use of sentence parallelism and the types and quality of essays  ...  We propose a machine learning approach for automated sentence parallelism identification in student essays. We build an essay dataset with sentence level parallelism annotated.  ...  Longest Common Subsequence(LCSeq) Longest Common Subsequence algorithm is a commonly used approach to compare multiple sequences (Hirschberg, 1977) .  ... 
dblp:conf/coling/SongLFLWL16 fatcat:efbc7ocbrfayfg37geljzxijte

Measuring evolutionary rates of proteins in a structural context

Dariya K. Sydykova, Benjamin R. Jack, Stephanie J. Spielman, Claus O. Wilke
2018 F1000Research  
In addition to describing the dN/dS specific analysis protocols we recommend, we also provide a code repository containing scripts to facilitate these kinds of analyses. Claus O.  ...  .: The conservation profile of a protein bears the imprint of the molecule that is evolutionarily coupled to the protein. Proteins. 2015; 83(8): 1407-1413. PubMed Abstract | Publisher Full Text 7.  ...  Generate sequence alignment map (see Note 3) To map site specific evolutionary rates to residues in a PDB structure, we first align the sequence of amino acids extracted from the PDB structure to the multiple  ... 
doi:10.12688/f1000research.12874.2 fatcat:yrrgfga4kzgaddztokn32slsem

Semantic Role Labeling for Knowledge Graph Extraction from Text [article]

Mehwish Alam, Aldo Gangemi, Valentina Presutti, Diego Reforgiato Recupero
2018 arXiv   pre-print
We finally discuss how to combine TakeFive and FRED, obtaining higher values of precision, recall and F1.  ...  This paper introduces TakeFive, a new semantic role labeling method that transforms a text into a frame-oriented knowledge graph.  ...  We also want to use ensemble learning approaches by combining multiple methods, and feeding/controlling the ensemble pipeline by using existing linguistic resources for SRL, and heuristical methods.  ... 
arXiv:1811.01409v1 fatcat:ftgawt7kojbajab7lfvxi6nopu

Generative Alignment and Semantic Parsing for Learning from Ambiguous Supervision

Joohyun Kim, Raymond J. Mooney
2010 International Conference on Computational Linguistics  
Compared to a previous generative model for semantic alignment, it also supports full semantic parsing.  ...  Our approach learns from natural language sentences paired with world states consisting of multiple potential logical meaning representations.  ...  stuck in local optima when running EM across these multiple steps.  ... 
dblp:conf/coling/KimM10 fatcat:pwvuic4brzdgbldyoxw2pv4huq

Genome-wide signatures of plastid-nuclear coevolution point to repeated perturbations of plastid proteostasis systems across angiosperms

Evan S Forsythe, Alissa M Williams, Daniel B Sloan
2021 The Plant Cell  
Functionally related proteins often show correlated changes in rates of sequence evolution across a phylogeny (evolutionary rate covariation or ERC), offering a means to detect previously unidentified  ...  suites of coevolving and cofunctional genes.  ...  Acknowledgements This work was supported by a National Science Foundation (NSF) grant (MCB-1733227) and graduate fellowships from NSF (DGE-1321845) and the National Institutes of Health (T32-GM132057).  ... 
doi:10.1093/plcell/koab021 pmid:33764472 pmcid:PMC8226287 fatcat:gonyl3b3qfajrii7zstkkn4wv4

Recognizing Textual Entailment [chapter]

Mark Sammons
2015 The Handbook of Contemporary Semantic Theory  
In the inference step, the system extracts features based on entity and argument matches, and a decision-tree classifier is used to decide if a commitment pair represents a valid entailment instance.  ...  The Semantic Role Labeling view contains predicate (P) and argument (A) constituents; these are joined by relations representing the roles of the arguments related to the predicate (A0 is "agent", or semantic  ... 
doi:10.1002/9781118882139.ch17 fatcat:h5hpwxywa5gc7nyenwmsq3wlay
« Previous Showing results 1 — 15 out of 36,100 results