Filters








5,080 Hits in 6.2 sec

Interactive Dictionary Expansion using Neural Language Models

Alfredo Alba, Daniel Gruhl, Petar Ristoski, Steve Welch
2018 International Semantic Web Conference  
In this paper, we propose a human-in-the-loop (HumL) dictionary expansion approach that employs a lightweight neural language model coupled with tight HumL supervision to assist the user in building and  ...  The evaluation shows that using our approach the user can easily extend the input dictionary, where tight human-in-the-loop integration results in a 216% improvement in effectiveness.  ...  Conclusions and future work This paper proposes an interactive dictionary expansion tool using a lightweight neural language model.  ... 
dblp:conf/semweb/AlbaGRW18 fatcat:dci5mvin7zhghk7ci6regnff6a

Page 2624 of Linguistics and Language Behavior Abstracts: LLBA Vol. 28, Issue 5 [page]

1994 Linguistics and Language Behavior Abstracts: LLBA  
tests development/use/reliability; 9409917 Neural Networks aphasia model, underlying neuronal mechanisms, neural network simu- lations; 9409733 authorship determination system, letter pair frequencies  ...  classroom use, Dutch teachers’ discussion; 9409779 dictionary familiarity/use, Rotterdam high school students; 9410019 dictionary use training, Dutch-English university-level translation course components  ... 

Page 2322 of Linguistics and Language Behavior Abstracts: LLBA Vol. 27, Issue 4 [page]

1993 Linguistics and Language Behavior Abstracts: LLBA  
9308424 second-language instruction, The Netherlands, speaking/writing/ learning to learn, critique; 9308380 Neural Networks automatic speech recognition models comparison, hidden Markov model vs neural  ...  ordinary language, quantum physics use, N.  ... 

Sentiment Classification for Chinese Text Based on Interactive Multitask Learning

Han Zhang, Shaoqi Sun, Yongjin Hu, Junxiu Liu, Yuanbo Guo
2020 IEEE Access  
Here, the classic BiLSTM + attention + CRF model is used to obtain full use of the interaction relationship between tasks, and it simultaneously solves the two tasks of emotional dictionary expansion and  ...  INDEX TERMS Multitask learning, information interaction mechanism, emotion classification, emotional dictionary expansion, ERNIE.  ...  In this paper, an interactive multitask learning model is proposed to integrate emotional dictionary expansion with text sentiment classification.  ... 
doi:10.1109/access.2020.3007889 fatcat:syhi27a6qrg2dc6z4asnpnlcky

Generating Politically-Relevant Event Data [article]

John Beieler
2016 arXiv   pre-print
This paper presents an overview of political event data, including methods and ontologies, and a set of experiments to determine the applicability of deep neural networks to the extraction of political  ...  This means that the data can be used to examine interactions below the usual monthly or yearly levels of aggregation.  ...  To accomplish this, this paper makes use of convolutional neural nets. This paper considers two neural architectures to classify a political event.  ... 
arXiv:1609.06239v1 fatcat:c2dpag74c5da5l75aamyvruabe

The TALP–UPC Spanish–English WMT Biomedical Task: Bilingual Embeddings and Char-based Neural Language Model Rescoring in a Phrase-based System

Marta R. Costa-jussà, Cristina España-Bonet, Pranava Madhyastha, Carlos Escolano, José A. R. Fonollosa
2016 Proceedings of the First Conference on Machine Translation: Volume 2, Shared Task Papers  
Our system is a standard phrase-based system enhanced with vocabulary expansion using bilingual word embeddings and a characterbased neural language model with rescoring.  ...  Since we are only dealing with OOVs, the new options do not interact with the other phrase pairs in the translation table, but there is interaction with the language model. Re-ranking.  ...  For example, neural feed-forward language models (Schwenk et al., 2006) have been used to rescore both n-gram-based and phrase-based systems.  ... 
doi:10.18653/v1/w16-2336 dblp:conf/wmt/Costa-JussaEMEF16 fatcat:3y2iin2zczevrdp6obfqclbzd4

Generating Politically-Relevant Event Data

John Beieler
2016 Proceedings of the First Workshop on NLP and Computational Social Science  
This paper presents an overview of political event data, including methods and ontologies, and a set of experiments to determine the applicability of deep neural networks to the extraction of political  ...  To accomplish this, this paper makes use of convolutional neural nets. This paper considers two neural architectures to classify a political event.  ...  For Arabic-language inputs, however, the difference is striking. The character model is over 20% more accurate than the word-based model.  ... 
doi:10.18653/v1/w16-5605 dblp:conf/acl-nlpcss/Beieler16 fatcat:ng24fxnwqnfbhpnt53nckg6hvm

Corpus based Machine Translation System with Deep Neural Network for Sanskrit to Hindi Translation

Muskaan Singh, Ravinder Kumar, Inderveer Chana
2020 Procedia Computer Science  
In this work, Deep neural network is used for training where input data is passed to neural network after data analysis and processing which then performs auto-tuning that help to make this model better  ...  In this work, Deep neural network is used for training where input data is passed to neural network after data analysis and processing which then performs auto-tuning that help to make this model better  ...  and lastly final generation of target text using Deep Neural network.  ... 
doi:10.1016/j.procs.2020.03.306 fatcat:kh4bubanl5h35gjf4ocojojt5a

Stanza: A Python Natural Language Processing Toolkit for Many Human Languages [article]

Peng Qi, Yuhao Zhang, Yuhui Zhang, Jason Bolton, Christopher D. Manning
2020 arXiv   pre-print
Compared to existing widely used toolkits, Stanza features a language-agnostic fully neural pipeline for text analysis, including tokenization, multi-word token expansion, lemmatization, part-of-speech  ...  Source code, documentation, and pretrained models for 66 languages are available at https://stanfordnlp.github.io/stanza.  ...  would like to thank the anonymous reviewers for their comments, Arun Chaganty for his early contribution to this toolkit, Tim Dozat for his design of the original architectures of the tagger and parser models  ... 
arXiv:2003.07082v2 fatcat:td6gnn4sdrc7bgcstxaojys6j4

sj-pdf-1-jmx-10.1177_00222429211045687 - Supplemental material for Blame the Bot: Anthropomorphism and Anger in Customer–Chatbot Interactions

Cammy Crolic, Felipe Thomaz, Rhonda Hadi, Andrew T. Stephen
2022 Figshare  
Supplemental material, sj-pdf-1-jmx-10.1177_00222429211045687 for Blame the Bot: Anthropomorphism and Anger in Customer–Chatbot Interactions by Cammy Crolic, Felipe Thomaz, Rhonda Hadi and Andrew T.  ...  To further simplify the process, we use Deepset.ai's Framework for Adapting Representation Models (FARM), which provides a neural network design we will use in the classification of text.  ...  First, our data on consumer-chatbot interactions has no labels for emotion, which is what motivated the bag-of-words approach for data expansion.  ... 
doi:10.25384/sage.20038428.v1 fatcat:7lbqrsre7vb2lfxowqfvpaxwj4

Page 824 of Linguistics and Language Behavior Abstracts: LLBA Vol. 28, Issue 2 [page]

1994 Linguistics and Language Behavior Abstracts: LLBA  
Johnson’s dictionary compilation/ Shakespearean scholarship interaction; 9403365 Picardy (France) domestic furniture lexicon; 9403396 political diglossia, social attitudes expression, Poland; 9403536 pragmatic  ...  /structural interchange, illocution lexification/other process- es; 9403177 pronunciation modeling, automatic speech recognition systems use, new speaker adaptation approach; 9403706 Proto-Indo-European  ... 

Communicative-Associative Development of Smart Artificial Intelligence by Criteria with Help of Ensembles of Diversified Agents

Evgeniy Bryndin
2020 International Journal of Intelligent Information Systems  
At the present stage of the development of information technologies, cognitive robotization, digital doubles and artificial intelligence systems, their synergy allows us to begin to form rational smart  ...  Bagging and Boosting techniques are used to form ensembles. Bagging is a combination of independent diversifiable agents by averaging patterns (weighted average, majority vote, or normal average).  ...  Meeting KPI requirements is condition of development 3 Execution Model and Technology Tooling Interaction Activization of Model Completion of interaction 4 Retraining Retrain a model with  ... 
doi:10.11648/j.ijiis.20200904.11 fatcat:ebhvei3nmrbq7lppnkcjksltsu

MeSHx-Notes: web-system for clinical notes information extraction

Henrique D. P. dos Santos, Rafael O. Nunes, João E. Soares, Renata Vieira
2018 International Joint Conference on Artificial Intelligence  
Since MeSH is available for 15 languages, MeSHx-Notes is easily extendable by replacing the MeSH thesaurus with the target language. In this demo, we show examples with Portuguese and English.  ...  We present MeSHx-Notes, MeSH eXtended for clinical notes, a multi-language web system based on the Django framework to present information selected in clinical notes.  ...  This training resulted in 63 thousand word vectors used as a semantic model in the neural network below.  ... 
dblp:conf/ijcai/SantosNSV18 fatcat:r3ogetdrlfgaph3chmbopbfxge

Increase of Safety Use Robots in Industry 4.0 by Developing Sensitivity and Professional Behavioral Skills

Evgeniy Bryndin
2020 American Journal of Mechanical and Industrial Engineering  
Adaptive behavior is guided by imitative thinking on a human task and is carried out by models of environment and behavior.  ...  Communicative-associative symbolic-language thinking logic allows the creation of cognitive adaptive robots for different spheres of life.  ...  The ALisp language represents expansion of the Lisp language. The ALisp language allows programmers to set the nondeterministic points of the choice similar to choice points in the Golog language.  ... 
doi:10.11648/j.ajmie.20200501.12 fatcat:uqlyz2mzf5ddpc67phga4chh6a

Increased Sensitivity and Safety of Cognitive Robot by Developing Professional and Behavioral Skills

Evgeniy Bryndin
2020 Saudi Journal of Engineering and Technology  
Adaptive behavior is guided by imitative thinking on a human task and is carried out by models of environment and behavior.  ...  Communicative-associative symbolic-language thinking logic allows the creation of cognitive adaptive robots for different spheres of life.  ...  The ALisp language represents expansion of the Lisp language. The ALisp language allows programmers to set the nondeterministic points of the choice similar to choice points in the Golog language.  ... 
doi:10.36348/sjet.2020.v05i05.001 fatcat:5m3cl36rczfqrcp2bnvuaz4lpi
« Previous Showing results 1 — 15 out of 5,080 results