Filters








1,140 Hits in 8.4 sec

THE STATE OF THE ART IN PROVIDING AUTOMATED FEEDBACK TO OPEN-ENDED STUDENT WORK

Paula Larrondo, Brian Frank, Julián Ortiz
2021 Proceedings of the Canadian Engineering Education Association (CEEA)  
It includes a description of the nature of complex problems and elements of effective feedback in the context of engineering education.  ...  This article provides a review of the state of the art of technologies in providing automated feedback toopen-ended student work on complex problems.  ...  Natural Language Process (NLP) techniques.  ... 
doi:10.24908/pceea.vi0.14854 fatcat:r4sexe5srrbvvdku5b5522bhry

Mining Large-scale Event Knowledge from Web Text

Ya-nan Cao, Peng Zhang, Jing Guo, Li Guo
2014 Procedia Computer Science  
Motivated by this limitation, we develop a three-phased approach that acquires causality from the Web text.  ...  The results of our empirical evaluations on a large-scale Web text corpus show that (a) the use of local dependency tree extensively improves both the accuracy and recall of event-arguments extraction  ...  Identifying Causal Relations from the Web From a linguistic aspect, causality in natural language is expressed either implicitly or explicitly.  ... 
doi:10.1016/j.procs.2014.05.043 fatcat:ednjfs6k6fhpppbckivcynxrya

Distilling Knowledge Learned in BERT for Text Generation [article]

Yen-Chun Chen, Zhe Gan, Yu Cheng, Jingzhou Liu, Jingjing Liu
2020 arXiv   pre-print
The finetuned BERT (teacher) is exploited as extra supervision to improve conventional Seq2Seq models (student) for better text generation performance.  ...  By leveraging BERT's idiosyncratic bidirectional nature, distilling knowledge learned in BERT can encourage auto-regressive Seq2Seq models to plan ahead, imposing global sequence-level supervision for  ...  Specifically, Lample and Conneau (2019) trained cross-lingual MLM and demonstrated promising results for cross-lingual natural language inference and unsupervised neural machine translation (NMT) .  ... 
arXiv:1911.03829v3 fatcat:w7lykkdp2rd63dz4qx24fwg7dm

Knowledge-guided Unsupervised Rhetorical Parsing for Text Summarization [article]

Shengluan Hou, Ruqian Lu
2019 arXiv   pre-print
Domain knowledge can be effectively used for unsupervised rhetorical parsing thus rhetorical structure trees for each document can be derived.  ...  for text summarization.  ...  The data-oriented channel is used to learn other important features of causal relation from the data. Lu et al.  ... 
arXiv:1910.05915v1 fatcat:fbylzfirhzdvjosixhcxpmvoyq

The NLP Cookbook: Modern Recipes for Transformer Based Deep Learning Architectures

Sushant Singh, Ausif Mahmood
2021 IEEE Access  
Additionally, to mitigate the data size challenge raised by language models from a knowledge extraction perspective, Knowledge Retrievers have been built to extricate explicit data documents from a large  ...  retrieval via Natural Language Understanding (NLU), and Natural Language Generation (NLG).  ...  These tasks include but are not limited to language modeling, sentiment analysis, question answering, and natural language inference.  ... 
doi:10.1109/access.2021.3077350 fatcat:gchmms4m2ndvzdowgrvro3w6z4

The NLP Cookbook: Modern Recipes for Transformer based Deep Learning Architectures [article]

Sushant Singh, Ausif Mahmood
2021 arXiv   pre-print
Additionally, to mitigate the data size challenge raised by language models from a knowledge extraction perspective, Knowledge Retrievers have been built to extricate explicit data documents from a large  ...  retrieval via Natural Language Understanding (NLU), and Natural Language Generation (NLG).  ...  These tasks include but are not limited to language modeling, sentiment analysis, question answering, and natural language inference.  ... 
arXiv:2104.10640v3 fatcat:ctuyddhm3baajk5uqrynwdap44

Application of Public Knowledge Discovery Tool (PKDE4J) to Represent Biomedical Scientific Knowledge

Min Song, Munui Kim, Keunyoung Kang, Yong Hwan Kim, Sieun Jeon
2018 Frontiers in Research Metrics and Analytics  
“Learning protein protein interaction extraction using distant supervision,” in Proceedings of Robust Unsupervised and Semi-Supervised Methods in Natural Language Processing (Workshop at International  ...  PPInterFinder—a mining tool for extracting causal relations on human proteins from literature.  ... 
doi:10.3389/frma.2018.00007 fatcat:ypnjhygle5ec5edk7xsxe5kcra

A Survey on Contextual Embeddings [article]

Qi Liu, Matt J. Kusner, Phil Blunsom
2020 arXiv   pre-print
Contextual embeddings assign each word a representation based on its context, thereby capturing uses of words across varied contexts and encoding knowledge that transfers across languages.  ...  Contextual embeddings, such as ELMo and BERT, move beyond global word representations like Word2Vec and achieve ground-breaking performance on a wide range of natural language processing tasks.  ...  parsing, and natural language inference.  ... 
arXiv:2003.07278v2 fatcat:ehdbsy5rezfdplv4z3mb4xta4y

Identifying Causal Relations Using Parallel Wikipedia Articles

Christopher Hidey, Kathy McKeown
2016 Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
The automatic detection of causal relationships in text is important for natural language understanding.  ...  We also train a causal classifier using features from the open class markers and semantic features providing contextual information.  ...  We hypothesize that these semantic features provide context not present in the text; from these we are able to infer causal and anti-causal properties.  ... 
doi:10.18653/v1/p16-1135 dblp:conf/acl/HideyM16 fatcat:jvv43r2wybgg7djjjro3c2qofi

A New Statistical and Verbal-Semantic Approach to Pattern Extraction in Text Mining Applications

Dildre Georgiana Vasques, Paulo Sérgio Martins, Solange Oliveira Rezende
2019 CLEI Electronic Journal  
new useful knowledge.  ...  To this end, this work proposes a hybridapproach for the discovery of implicit knowledge present in a text corpus, using analysis based onassociation rules together with metrics from complex networks and  ...  [69] developed a type of automatic extraction of information from and made from texts. For this, they used linguistic clues without the use of any domain knowledge.  ... 
doi:10.19153/cleiej.22.3.5 fatcat:qbivqzou4ras7mpad7vncoyqle

Information Extraction: The Power of Words and Pictures

Marie-Francine Moens
2007 Journal of Computing and Information Technology  
The sources that we process here are very different from well-formed natural language texts.  ...  Then follows a section on extraction from blogs, community texts and other natural utterances.  ... 
doi:10.2498/cit.1001136 fatcat:tfpcm22xdranzmo6uo2sdlk7ya

Information Extraction: The Power of Words and Pictures

Marie-Francine Moens
2007 Information Technology Interfaces  
The sources that we process here are very different from well-formed natural language texts.  ...  Then follows a section on extraction from blogs, community texts and other natural utterances.  ... 
doi:10.1109/iti.2007.4283737 fatcat:2ajmmbxndfe5vlm6ppgbeinkqi

Adaptive Ensembling: Unsupervised Domain Adaptation for Political Document Analysis

Shrey Desai, Barea Sinno, Alex Rosenfeld, Junyi Jessy Li
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)  
., from a single source or era), preventing their use for political science research.  ...  To bridge this gap, we present adaptive ensembling, an unsupervised domain adaptation framework, equipped with a novel text classification model and time-aware training to ensure our methods work well  ...  Acknowledgments The authors acknowledge the Texas Advanced Computing Center (TACC) at The University of Texas at Austin for providing HPC resources used to conduct this research.  ... 
doi:10.18653/v1/d19-1478 dblp:conf/emnlp/DesaiSRL19 fatcat:hhqzsequhbfezecnu62frzinsu

A scoping review on the use of machine learning in research on social determinants of health: Trends and research prospects

Shiho Kino, Yu-Tien Hsu, Koichiro Shiba, Yung-Shin Chien, Carol Mita, Ichiro Kawachi, Adel Daoud
2021 SSM: Population Health  
Although the number of studies in ML and SDH is growing rapidly, only a few studies used ML to improve causal inference, curate data, or identify social bias in predictions (i.e., algorithmic fairness)  ...  While ML equips researchers with new ways to measure health outcomes and their determinants from non-conventional sources such as text, audio, and image data, most studies still rely on traditional surveys  ...  One study used ML to extract information from a clinical natural language processing system to identify sensitive attributes such as race, sex, and age (Conway et al., 2019) .  ... 
doi:10.1016/j.ssmph.2021.100836 pmid:34169138 pmcid:PMC8207228 fatcat:azq5223ylzcbzjuccsfdnfo23u

Message from the general chair

Benjamin C. Lee
2015 2015 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)  
To inject knowledge, we use a state-of-the-art system which cross-links (or "grounds") expressions in free text to Wikipedia.  ...  methods as an isolated inference procedure at the end.  ...  Human readers naturally use common sense knowledge to infer such implicit information from the explicitly stated facts.  ... 
doi:10.1109/ispass.2015.7095776 dblp:conf/ispass/Lee15 fatcat:ehbed6nl6barfgs6pzwcvwxria
« Previous Showing results 1 — 15 out of 1,140 results