136 Hits in 4.1 sec

A Comparative Analysis of Knowledge-Intensive and Data-Intensive Semantic Parsers [article]

Junjie Cao, Zi Lin, Weiwei Sun, Xiaojun Wan
2020 arXiv   pre-print
We then show that, in spite of comparable performance overall, knowledge- and data-intensive models produce different types of errors, in a way that can be explained by their theoretical properties.  ...  This analysis leads to new directions for parser development.  ...  MWEs cover a wide range of linguistic phenomena, including fixed and semi-fixed expressions, phrasal verbs, named entities.  ... 
arXiv:1907.02298v3 fatcat:aoz6enyw5zaqvevhbn2p2dhwwe

Comparing Knowledge-Intensive and Data-Intensive Models for English Resource Semantic Parsing

Junjie Cao, Zi Lin, Weiwei Sun, Xiaojun Wan
2021 Computational Linguistics  
We conduct a suite of tests for different linguistic phenomena to analyze the grammatical competence of different parsers, where we show that, despite comparable performance overall, knowledge-and data-intensive  ...  models produce different types of errors, in a way that can be explained by their theoretical properties.  ...  MWEs cover a wide range of linguistic phenomena, including fixed and semi-fixed expressions, phrasal verbs, and named entities.  ... 
doi:10.1162/coli_a_00395 dblp:journals/coling/CaoLSW21 fatcat:fiwdenhi4rcdrfa22ucodal664

Musical training shapes neural responses to melodic and prosodic expectation

Ioanna Zioga, Caroline Di Bernardi Luft, Joydeep Bhattacharya
2016 Brain Research  
Participants were faster for simultaneous expectancy violations in the melodic and linguistic stimuli.  ...  Further, musicians performed better than nonmusicians, which may be related to their increased pitch tracking ability.  ...  Acknowledgements The authors are supported by the CREAM project that has been funded by the European Commission under Grant Agreement no 612022.  ... 
doi:10.1016/j.brainres.2016.09.015 pmid:27622645 pmcid:PMC5069926 fatcat:nks6jwkdqbapjczg2sefmmfk64

Lombard Speech Synthesis Using Transfer Learning in a Tacotron Text-to-Speech System

Bajibabu Bollepalli, Lauri Juvela, Paavo Alku
2019 Interspeech 2019  
However, for high-pitched speech, the formant estimates given by LP might be biased by the harmonic peaks. To address this problem, approaches such as time-weighted LP (WLP) have been proposed.  ...  The proposed GAN method performed significantly better than 66 A summary of the publications the DNN-based approach.  ... 
doi:10.21437/interspeech.2019-1333 dblp:conf/interspeech/BollepalliJA19 fatcat:5uz43svog5erzev5nzakdnc4qe

Message from the general chair

Benjamin C. Lee
2015 2015 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)  
Our end system outperforms the state-of-the-art baseline by 2 B 3 F1 points on non-transcript portion of the ACE 2004 dataset.  ...  We explore ways of using the resulting grounding to boost the performance of a state-of-the-art co-reference resolution system.  ...  I intend to extend this system to other languages, genres and domains and to improve it's performance using deeper linguistic analysis.  ... 
doi:10.1109/ispass.2015.7095776 dblp:conf/ispass/Lee15 fatcat:ehbed6nl6barfgs6pzwcvwxria

English Sentiment Classification using Only the Sentiment Lexicons with a JOHNSON Coefficient in a Parallel Network Environment

Vo Ngoc Phu, Vo Thi Ngoc Tran
2018 American Journal of Engineering and Applied Sciences  
One term (a word or a phrase in English) is clustered into either the positive polarity or the negative polarity if this term is very close to either the positive or the negative by using many similarity  ...  The based Semi-supervised PageRank score can improve the authors consider such elaborated Learning Methods performance.  ...  In summary, by using Equation 8 to 10, we identify the valence and the polarity of one word (or one phrase) in English by using the SC through the Google search engine with AND operator and OR operator  ... 
doi:10.3844/ajeassp.2018.38.65 fatcat:p5ac55ogpbd7blkbaxqw2wzyea

Evaluation of CIM technologies in Saudi industries using AHP

A. M. A. Al-Ahmari
2006 The International Journal of Advanced Manufacturing Technology  
Here, a brief summary of the results is given.  ...  The proposed DSS enables the decisionmakers to perform sensitivity analyses by allowing consideration of various scenarios and different levels of several inputs.  ... 
doi:10.1007/s00170-006-0643-y fatcat:rbcd5hgmnfc7fped2ak2vxw54m

Automatic Text Document Summarization using Semantic-based Analysis [article]

Chandra Shekhar Yadav
2018 arXiv   pre-print
As defined by (Mani & Maybury, 1999) semantic summary generation may be done using shallow level analysis and deep level analysis.  ...  They have proposed a semi-supervised bootstrapping approach to identify relevant 5 components for an abstractive summary generation.  ... 
arXiv:1811.06567v1 fatcat:puqnurg3d5gvbb3ywdoohey76u

The Analysis of Implementation and Scoring for KSSM Oral Assessment Among the Lower Secondary Teachers

Rozita Radhiah Said, Halimah Jamil
2021 International Journal of Academic Research in Progressive Education and Development  
The research data were collected by triangulation, through the interview method, observation on the implementation of oral assessment for teaching and learning (T&L) in the classroom, and document analysis  ...  This article is published under the Creative Commons Attribution (CC BY 4.0) license.  ...  The findings of this research support the studies by Suseela & Sim (2010) ; Kağan Bűyűkkarcı (2014) ; LPM (2015) ; Wan Omar (2019) .  ... 
doi:10.6007/ijarped/v10-i2/10497 fatcat:dev3j4bfvjdfhbdsh7l2m6yiae

Recent Advances for Quantum Neural Networks in Generative Learning [article]

Jinkai Tian, Xiaoyu Sun, Yuxuan Du, Shanshan Zhao, Qing Liu, Kaining Zhang, Wei Yi, Wanrong Huang, Chaoyue Wang, Xingyao Wu, Min-Hsiu Hsieh, Tongliang Liu (+2 others)
2022 arXiv   pre-print
Quantum computers are next-generation devices that hold promise to perform calculations beyond the reach of classical computers.  ...  QBM semi-RQBM formulation of MLP yields Table 5 A 5 summary of open source codes for QGLMs.  ...  analysis.  ... 
arXiv:2206.03066v1 fatcat:ykeh3j2t45dwvbutwwe3flvaoq

Studies in African Linguistics, Full issue (Vol. 29, No. 1)

Editors Editors
2000 Studies in African Linguistics  
This is followed by discussion of tonal phenomena in the noun phrase. No evidence for lexical stress is found.  ...  Endangered languages Njerep: A postcard from the edge 91 93 95 Upcoming meetings on African languagesllinguistics 127 131 Guidelines for contributors inside back cover Studies Kunama has been reported by  ...  d. koe ma 63 a nde a lfl-l 6akia na wan-slla, wan-yere ka dUl]-u g:5.  ... 
doi:10.32473/sal.v29i1.107583 fatcat:yvq4eixngjbanpcwnuqwirtbfu

Prosumer in smart grids based on intelligent edge computing: A review on Artificial Intelligence Scheduling Techniques

Sami Ben Slama
2021 Ain Shams Engineering Journal  
Published by Elsevier BV on behalf of Faculty of Engineering, Ain Shams University. This is an open access article under the CC BY-NC-ND license (  ...  For efficient real-time data analysis and decision-making, the Internet of Things will incorporate various communication systems seamlessly.  ...  crossing the entire WAN; perform data analysis widely, smoothly and accurately; serve a large number of real-time analyzes based on Edge platforms.  ... 
doi:10.1016/j.asej.2021.05.018 fatcat:k4n5li6fvjg2dedrjksybk3jh4

A possibilistic programming approach for biomass supply chain network design under hesitant fuzzy membership function estimation

Hossein Gitinavard, Mohsen Akbarpour Shirazi, Mohammad Hossein Fazel Zarandi
2021 Scientia Iranica. International Journal of Science and Technology  
The recognition of membership function by knowledge acquisition from experts is an important factor for many fuzzy mathematical programming models.  ...  After that, the efficiency and applicability of the proposed approach is checked by proposing a novel mathematical model for biomass supply chain network design problem.  ...  [27] extended an integer mathematical programming approach based on additive consistency to predict missing values of incomplete hesitant fuzzy linguistic preference relations. Wan et al.  ... 
doi:10.24200/sci.2021.55021.4035 fatcat:visspdn6bbbyzke5ptogsp2ldu

Towards "On the Go" Matching of Linked Open Data Ontologies

Isabel F. Cruz, Matteo Palmonari, Federico Caimi, Cosmin Stroe
2011 International Joint Conference on Artificial Intelligence  
To achieve semantic interoperability, geo-spatial applications need to be equipped with tools able to understand user terminology that is typically different from the one enforced by standards.  ...  Acknowledgments This work has been supported by the TasLab network project funded by the European Social Fund under the act n° 1637 (30.06.2008) Acknowledgments This work is funded by the Search Computing  ...  A linguistic pre-processor is used to perform tokenization, morphological analysis, part of speech tagging, gazetteer lookup and generic dictionary lookup on the text corpus.  ... 
dblp:conf/ijcai/CruzPCS11 fatcat:62apmemu2zgirduzh6zomuw7wi

Anthropogenic marine debris and its dynamics across peri-urban and urban mangroves on Penang Island, Malaysia [article]

Su Yin Chee, John Barry Gallagher, Jean Chai Yee, Danielle Carey, Yusri Yusup
2019 biorxiv/medrxiv   pre-print
Two urban and two peri-urban mangroves were sampled at different periods over 2 months, with differences constrained by possible changes in their wind fields, and neap-spring tidal development.  ...  Accounting Accounting Management Accounting Accounting Marketing Counselling Accounting Management and Performing Arts Education and Linguistics Curriculum and Arabic Linguistics My research  ...  I also interested in comparing linguistic politeness strategies used by different languages, through the study of contrastive analysis of verbal politeness in Malay and Spanish in minimizing face threats  ... 
doi:10.1101/756106 fatcat:m6oy4besircffmdhmffppw6yra
« Previous Showing results 1 — 15 out of 136 results