Filters








2,323 Hits in 4.1 sec

Computational Methods for Text Analysis and Text Classification [chapter]

Hercules Dalianis
2018 Clinical Text Mining  
Active learning is used for selecting the optimal data to be annotated. Different machine learning approaches such as topic modelling, distributional semantics and clustering will be presented.  ...  Ready computational linguistic modules for English clinical text mining, such as MedLEE and cTakes will also be presented, as well as some basic tools such as NLTK and GATE, which need to be adapted to  ...  PAL, https://github.com/mariask2/PAL-A-tool-for-Pre-annotation-and-Active-Learning. Accessed 2018-01-11.  ... 
doi:10.1007/978-3-319-78503-5_8 fatcat:mrsk7xytujefxj4xfahkc5vco4

Assisted Text Annotation Using Active Learning to Achieve High Quality with Little Effort [article]

Franziska Weeber and Felix Hamborg and Karsten Donnay and Bela Gipp
2021 arXiv   pre-print
For this purpose, we combine an active learning (AL) approach with a pre-trained language model to semi-automatically identify annotation categories in the given text documents.  ...  We propose a tool that enables researchers to create large, high-quality, annotated datasets with only a few manual annotations, thus strongly reducing annotation cost and effort.  ...  Kerren, “PAL, a tool for Pre- annotation and Active Learning,” Journal for Language Technology and  ... 
arXiv:2112.11914v1 fatcat:hjoltpz27jfhjn7dhcybivw26m

Emotion Classification in a Resource Constrained Language Using Transformer-based Approach [article]

Avishek Das, Omar Sharif, Mohammed Moshiul Hoque, Iqbal H. Sarker
2021 arXiv   pre-print
A Bengali emotion corpus consists of 6243 texts is developed for the classification task.  ...  However, unavailability of necessary language processing tools and deficiency of benchmark corpora makes the emotion classification task in Bengali more challenging and complicated.  ...  Acknowledgements We sincerely acknowledge the anonymous reviewers and pre-submission mentor for their insightful suggestions, which help improve the work.  ... 
arXiv:2104.08613v1 fatcat:k6p4wflxhrflpl7zwqhmbxp4ey

Reducing systematic review workload through certainty-based screening

Makoto Miwa, James Thomas, Alison O'Mara-Eves, Sophia Ananiadou
2014 Journal of Biomedical Informatics  
Active learning is a promising approach to reduce the workload by automating some of the screening decisions, but it has been evaluated for a limited number of disciplines.  ...  The most promising criterion and weighting method are the same regardless of the review topic, and unsupervised techniques like LDA have a possibility to boost the performance of active learning without  ...  PAL WITH AU performs best for the earlier steps of active learning, similarly to AU with Uncertainty as in Fig. 4(a) , while other methods show similar performance and achieve better Utility scores.  ... 
doi:10.1016/j.jbi.2014.06.005 pmid:24954015 pmcid:PMC4199186 fatcat:5jr3hfyclrenvbhtdce5fjiflu

Opinion aspect extraction in Dutch childrens diary entries [article]

Hella Haanstra, Maaike H. T. de Boer
2019 arXiv   pre-print
The aim of this study is three-fold: 1. create a new annotated dataset for both aspect extraction and opinion words for Dutch childrens language, 2. acquire aspect extraction results for this task and  ...  Expressing an empathetic reaction to an opinion can strengthen the bond between a human and, for example, a robot.  ...  and was collected for the PAL project.  ... 
arXiv:1910.10502v1 fatcat:ctcvw2vsevhxdfyws3vksa66cq

DR 4.4: Natural Multimodal Interaction Final Pro- totype

Bernd Kiefer, Ivana Kruijff-Korbayova, Anna Welker, Rifca Peters, Sarah McLeod
2019 Zenodo  
For less experienced users, a graphical editor and compiler for hierarchical state machines has been implemented and is now ready for use.  ...  In addition, some new functionalities were at the core of human-system interaction, namely a new module for rst time use of the system, and an integrated Off-Activity-Talk prototype, consisting of robot  ...  Acknowledgements The research described in this paper has been funded by the Horizon 2020 Framework Programme of the European Union within the project PAL (Personal Assistant for healthy Lifestyle) under  ... 
doi:10.5281/zenodo.3443669 fatcat:ez7jk76vmncshlzoivgqftx4ji

Supervising Unsupervised Open Information Extraction Models

Arpita Roy, Youngja Park, Taesung Lee, Shimei Pan
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
By employing multiple unsupervised Open IE systems, our system learns to combine the strength and avoid the weakness in each individual Open IE system.  ...  structure as its input features and produces a sequence of word labels indicating whether the word belongs to a relation, the arguments of the relation or irrelevant.  ...  Acknowledgment We gratefully acknowledge IBM for supporting this work. References  ... 
doi:10.18653/v1/d19-1067 dblp:conf/emnlp/RoyPLP19 fatcat:4ziwkrxwyfaelh75u447ymy2qy

The Five Key Practices of Constructed Responses for Learning [chapter]

2016 Constructed Responses for Learning  
Acknowledgments In creating a robust instructional routine of constructed responses for learning, I recognize my debt to my wife and fellow educator, Arnelle, who reviews everything I write before it goes  ...  My three adult children, Cortney, Erin, and Taylor, benefitted from the strategies in grades K-12 then helped me improve them to impact other students even more dramatically.  ...  And, unfortunately, writing about what teachers who are in pre-service training are learning is not a required practice in new teacher preparation.  ... 
doi:10.4324/9781315679983-10 fatcat:q7u67entxvdedf5ujgrzmh4pvq

PAL DRs 6.4, 6.8, 6.12: Y4 Dissemination Report [article]

Michela Severgnini
2019 Zenodo  
The present report describes the work carried out during the last project year regarding PAL's Dissemination and Communication activities.  ...  It is the summary of three different WP6 Deliverables: Deliverable 6.4 "Website y4", Deliverable 6.8 "Publications and proceedings report y4" and Deliverable 6.12 "Dissemination events promoted y4"  ...  , learning and adaptation for personalized assistance, analysis and recognition of daily living activities.  ... 
doi:10.5281/zenodo.4632882 fatcat:rsjdrbpxvjdoffumtwf2o3pmaq

DRs 6.4, 6.8, 6.12: Y4 Dissemination Report

Michela Severgnini, Elettra Oleari
2019 Zenodo  
The present report describes the work carried out during the last project year regarding PAL's Dissemination and Communication activities.  ...  It is the summary of three different WP6 Deliverables: Deliverable 6.4 "Website y4", Deliverable 6.8 "Publications and proceedings report y4" and Deliverable 6.12 "Dissemination events promoted y4"  ...  , learning and adaptation for personalized assistance, analysis and recognition of daily living activities.  ... 
doi:10.5281/zenodo.3443714 fatcat:477acn7fpzem7fue453gl35t7a

Book Reviews

Marika Asimakopulos, Barbara Hiron, Joan S. Segal, Anne M. Galler, David S. Webster, Margaret Sheremata, Susan Tee
2017 Education Libraries  
They stress the importance of teachers' attitudes, and willingness to seek advice and new ideas on how to adapt curriculum and activities for students with learning difficulties.  ...  Karp has compiled a useful reference tool for professionals responsible for the coordination of service to the disabled library user.  ... 
doi:10.26443/el.v18i1.64 fatcat:gjt6kkroura45ftcnnyjsnj2lq

Peer Teaching to Foster Learning in Physiology

Tripti K Srivastava
2015 Journal of Clinical and Diagnostic Research  
Hence, while designing and implementing learning activities, focus should be diverted towards Peer assisted learning (PAL) activities.  ...  To compare learning outcomes by peer teaching, a student led activity and tutorials, a teacher led activity. 5.  ... 
doi:10.7860/jcdr/2015/15018.6323 pmid:26435969 pmcid:PMC4576561 fatcat:mwz52pb46zbsfd3eltrkggmet4

Comparative Study of Human Age Estimation Based on Hand-Crafted and Deep Face Features [chapter]

C. Belver, I. Arganda-Carreras, F. Dornaika
2017 Lecture Notes in Computer Science  
, security control and surveillance, biometrics, human-computer interaction (HCI) and social robotics.  ...  In the past few years, human facial age estimation has drawn a lot of attention in the computer vision and pattern recognition communities because of its important applications in age-based image retrieval  ...  The age estimator can use a machine learning approach to train a model for extracted features and make age prediction for query faces with the trained model.  ... 
doi:10.1007/978-3-319-56687-0_9 fatcat:gyayysgmrfe37noo6f7stakeki

Study of Factors Influencing the Adoption of Agile Processes When Using Wikis

Alberto Heredia, Javier Garcia-Guzman, Antonio Amescua-Seco, Alan Serrano
2014 International journal of software engineering and knowledge engineering  
We propose a framework based on social software to support the collaborative learning, adoption and improvement of SE processes through the exchange of experiences among individuals.  ...  Social software can support and enhance this adoption process, so research needs to focus on how the exchange of knowledge among software engineers using these tools can help to perform training more effectively  ...  [27] developed a PAL using a wiki as a lightweight repository of knowledge about agile software development, providing a more specific process structure for the PAL creation and management.  ... 
doi:10.1142/s0218194014400014 fatcat:3g3q75kxn5dvtenf6bidp5isaa

Tag Me a Label with Multi-arm: Active Learning for Telugu Sentiment Analysis [chapter]

Sandeep Sricharan Mukku, Subba Reddy Oota, Radhika Mamidi
2017 Lecture Notes in Computer Science  
To address this issue, in this paper the practicality of active learning for Telugu sentiment analysis is investigated.  ...  Sentiment Analysis is one of the most active research areas in natural language processing and an extensively studied problem in data mining, web mining and text mining for English language.  ...  Dataset Generation Unlike English, Telugu has neither a large annotated dataset and tools nor any pre-trained models.  ... 
doi:10.1007/978-3-319-64283-3_26 fatcat:qqps4slohnbzlbjptyvp7u5a74
« Previous Showing results 1 — 15 out of 2,323 results