Filters








164 Hits in 7.3 sec

Is getting the right answer just about choosing the right words? The role of syntactically-informed features in short answer scoring [article]

Derrick Higgins, Chris Brew, Michael Heilman, Ramon Ziai, Lei Chen, Aoife Cahill, Michael Flor, Nitin Madnani, Joel Tetreault, Daniel Blanchard, Diane Napolitano, Chong Min Lee, John Blackmore
2014 arXiv   pre-print
A recent shared task on this topic revealed a fundamental divide in the modeling approaches that have been applied to this problem, with the best-performing systems split between those that employ a knowledge  ...  This paper aims to introduce the NLP community to the largest corpus currently available for short-answer scoring, provide an overview of methods used in the shared task using this data, and explore the  ...  Previous Work Like the field of automated essay scoring, research on methods for automated scoring of short answer questions has a history that spans multiple decades.  ... 
arXiv:1403.0801v2 fatcat:xq47syhu3vhhniadqyyu2qvqgi

Content Importance Models for Scoring Writing From Sources

Beata Beigman Klebanov, Nitin Madnani, Jill Burstein, Swapna Somasundaran
2014 Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)  
We evaluate a variety of content importance models that help predict which parts of the source material should be selected by the test-taker in order to succeed on this task.  ...  We address an integrative summarization task used in an assessment of English proficiency for nonnative speakers applying to higher education institutions in the USA.  ...  These models are sensitive to data sparsity not only when matching essays to the lecture (this problem is common to all models) but also during model building.  ... 
doi:10.3115/v1/p14-2041 dblp:conf/acl/KlebanovMBS14 fatcat:bdaozzaz7vcyrhv54yubeehlcy

A New Approach to Automated Text Readability Classification based on Concept Indexing with Integrated Part-of-Speech n-gram Features

Abigail R. Razon, John A. Barnden
2015 Recent Advances in Natural Language Processing  
This study is about the development of a learner-focused text readability indexing tool for second language learners (L2) of English.  ...  Student essays are used to calibrate the system, making it capable of providing realistic approximation of L2s' actual reading ability spectrum.  ...  We would also like to thank the University of the Philippines Integrated School (UPIS) for giving us permission to use their essay samples and reading materials as data.  ... 
dblp:conf/ranlp/RazonB15 fatcat:ffqfqh7qr5cibmj35a7y6ytpca

Evaluation Metrics for Inferring Personality from Text

David N. Chin, William R. Wright
2016 User Modeling, Adaptation, and Personalization  
Those who disregard this and choose to perform automated feature selection and train classifiers on the same observations should consider that massive overfitting will likely occur.  ...  Features of interest Some studies focus on building a classifier, but not on identifying which features were useful for classification.  ... 
dblp:conf/um/ChinW16 fatcat:vw3btaazrfb7bexqgpbbb6w4pi

EVALUATING THE CONSTRUCT-COVERAGE OF THE E-RATER® SCORING ENGINE

Thomas Quinlan, Derrick Higgins, Susanne Wolff
2009 ETS Research Report Series  
Originally, the e-rater engine consisted of a large set of components with a proven ability to predict human holistic scores.  ...  Some traits of essay quality cut across different methods for scoring essay quality, such as the rubrics employed by the GRE ® and TOEFL ® assessments, as well as the 6-trait scoring model.  ...  For example, one reader may focus on the major points of an essay, and skim over minor inconsistencies, while another reader may be highly sensitive to mechanical errors.  ... 
doi:10.1002/j.2333-8504.2009.tb02158.x fatcat:ej6xblz66rgmvg7mk23h6aiyrm

Automated scholarly paper review: Technologies and challenges [article]

Jialiang Lin, Jiaxin Song, Zhangping Zhou, Yidong Chen, Xiaodong Shi
2022 arXiv   pre-print
Peer review is a widely accepted mechanism for research evaluation, playing a pivotal role in scholarly publishing.  ...  In the foreseeable future, ASPR and peer review will coexist in a reinforcing manner before ASPR is able to fully undertake the reviewing workload from humans.  ...  Special and heartfelt gratitude goes to the first author's wife Fenmei Zhou, for her understanding and love. Her unwavering support and continuous encouragement enable this research to be possible.  ... 
arXiv:2111.07533v2 fatcat:oicz75mudvambimx24q7z63h2e

Automated Assessment of Language Proficiency on German Data

Edit Szügyi, Sören Etler, Andrew Beaton, Manfred Stede
2019 Conference on Natural Language Processing  
Working on a combined data set of previously-used corpora, we use both data-and theory-driven feature sets, and determine the best-performing features.  ...  Reference for Languages), based on linguistic features extracted from the texts.  ...  Introduction An important concept in the field of educational systems is Automatic Text Scoring (ATS), which automates the process of scoring texts by using NLP techniques.  ... 
dblp:conf/konvens/SzugyiEBS19 fatcat:l3yytfhggna6zfwuckt4onb2ya

Authenticating the writings of Julius Caesar

Mike Kestemont, Justin Stover, Moshe Koppel, Folgert Karsdorp, Walter Daelemans
2016 Expert systems with applications  
While Caesar himself has authored at least part of these commentaries, the authorship of the rest of the texts remains a puzzle that has persisted for nineteen centuries.  ...  We describe two state-of-the-art authorship verification systems and benchmark them on 6 present-day evaluation corpora, as well as a Latin benchmark dataset.  ...  While it is not consistently the best performing metric, it produced highly 340 stable results for the PAN data (and to a lesser extent for the Latin data).  ... 
doi:10.1016/j.eswa.2016.06.029 fatcat:7xktqsgxcze2pf65plk4qzzcv4

Catching Idiomatic Expressions in EFL Essays

Michael Flor, Beata Beigman Klebanov
2018 Proceedings of the Workshop on Figurative Language Processing  
The study used a corpus of essays written during a standardized examination of English language proficiency. Automatically-flagged candidate expressions were manually annotated for idiomaticity.  ...  This paper presents an exploratory study on large-scale detection of idiomatic expressions in essays written by non-native speakers of English.  ...  Data and annotation We conducted a study in which our flexible algorithm was applied to a large set of essays written by EFL students.  ... 
doi:10.18653/v1/w18-0905 dblp:conf/acl-figlang/FlorK18 fatcat:qxu3voxoifc2fe3vsemjpag3qi

Multi-domain and multi-task prediction of extraversion and leadership from meeting videos

Ahmet Alp Kindiroglu, Lale Akarun, Oya Aran
2017 EURASIP Journal on Image and Video Processing  
Prediction of emergent leadership, on the other hand, is of great importance for the business community.  ...  Prediction of extraversion has attracted the attention of psychologists as it is able to explain a wide range of behaviors, predict performance, and assess risk.  ...  Availability of data and materials The datasets supporting the conclusions of this article are available for download from IDIAP dataset access pages at "https://www.idiap.ch/dataset/ youtube-personality  ... 
doi:10.1186/s13640-017-0224-z fatcat:enzkhmqambbgjikukndstnf7hm

Discourse Connective Argument Identification with Connective Specific Rankers

Robert Elwell, Jason Baldridge
2008 2008 IEEE International Conference on Semantic Computing  
Here, we show that using models for specific connectives and types of connectives and interpolating them with a general model improves performance.  ...  We also describe additional features that provide greater sensitivity to morphological, syntactic, and discourse patterns, and less sensitivity to parse quality.  ...  Acknowledgments The authors would like to thank Ben Wellner for providing feedback and data that helped replicate his results.  ... 
doi:10.1109/icsc.2008.50 dblp:conf/semco/ElwellB08 fatcat:34bvb4kt2rd6hlbr6rq6j35m2y

Using Named Entities for Computer-Automated Verbal Deception Detection

Bennett Kleinberg, Maximilian Mozes, Arnoud Arntz, Bruno Verschuere
2017 Journal of Forensic Sciences  
The emerging body of computer-automated verbal deception research indicates that computer automation not only performs equal to human-annotated statements (12, 13) , but it also allows for a finer level  ...  s studies were not applying any coding strategy (e.g., scoring the plausibility or richness of detail), a direct comparison of trained human annotation and automated analysis is needed to examine the human  ... 
doi:10.1111/1556-4029.13645 pmid:28940300 fatcat:gbm76zrdtvg4da64hx3jb34jbq

A knowledge-tracing model of learning from a social tagging system

Peter Pirolli, Sanjay Kairam
2012 User modeling and user-adapted interaction  
We validate this knowledge tracing approach against data from a social tagging study.  ...  That corpus can be fed to an automated process that distills a topic model representation characteristic of the domain.  ...  We would also like to acknowledge Gregorio Convertino, Lichan Hong, Les Nelson, and the rest of the Augmented Social Cognition Group at PARC for their contributions to this research.  ... 
doi:10.1007/s11257-012-9132-1 fatcat:gmiirtdbz5ah7licjpwp6hg3xq

Algorithmic Fairness Datasets: the Story so Far [article]

Alessandro Fabris, Stefano Messina, Gianmaria Silvello, Gian Antonio Susto
2022 arXiv   pre-print
Data-driven algorithms are studied in diverse domains to support critical decisions, directly impacting people's well-being.  ...  As a result, a growing community of researchers has been investigating the equity of existing algorithms and proposing novel ones, advancing the understanding of risks and opportunities of automated decision-making  ...  Acknowledgements The authors would like to thank the following researchers and dataset creators for the useful feedback on the data briefs: Alain Barrat, Luc Behaghel, Asia Biega, Marko Bohanec, Chris  ... 
arXiv:2202.01711v3 fatcat:kd546yklwjhvtkrbhtzgbzb2xm

Multi-Task Learning for Argumentation Mining [article]

Tobias Kahse
2019 arXiv   pre-print
for a potential multi-task learning success and that multi-task learning is particularly useful if the task at hand suffers from data sparsity, i.e. a lack of training data.  ...  In contrast to learning a single task in isolation, multiple tasks are learned at the same time, thereby utilizing the training signal of related tasks to improve the performance on the respective machine  ...  In difference to the PE dataset used for AM, prediction is performed on the essay level in PE:ACS.  ... 
arXiv:1904.10162v1 fatcat:jnken6fikzdr5csdtoejxfpcfu
« Previous Showing results 1 — 15 out of 164 results