東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Application of Neural Language Models for Research Article Classification into Sustainable Development Goals.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Application of Neural Language Models for Research Article Classification into Sustainable Development Goals./
作者:	Villanueva, Daniela Flores.
面頁冊數:	1 online resource (97 pages)
附註:	Source: Masters Abstracts International, Volume: 84-09.
Contained By:	Masters Abstracts International84-09.
標題:	Language. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30355358click for full text (PQDT)
ISBN:	9798374488807

Application of Neural Language Models for Research Article Classification into Sustainable Development Goals.
Villanueva, Daniela Flores.

Application of Neural Language Models for Research Article Classification into Sustainable Development Goals. - 1 online resource (97 pages)

Source: Masters Abstracts International, Volume: 84-09.

Thesis (M.Sc.)--Pontificia Universidad Catolica de Chile (Chile), 2022.

Includes bibliographical references

Sustainability has gained much attention in recent years when we have started to see the effects of climate change and environmental damage, and action needs to be taken to keep inhabiting planet Earth. In this thesis, we explore using state-of-the-art Transformerbased language models to develop a Sustainable Development Goals (SDGs) classifier for academic articles. This model could lead academic institutions to measure their contribution to Sustainability and promote collaboration between interdisciplinary researchers to tackle current world challenges using knowledge from different fields. We propose a finetuned RoBERTa model that reaches an f1-score of 73%. We also studied two Explainable Artificial Intelligence techniques to better understand the model predictions, Attention Mechanism and Integrated Gradients. Finally, we conducted a user study to discover the best explanation method between the two using text visualization techniques. We concluded that Attention Mechanism visualizations better help the users understand model predictions, even when said predictions are erroneous.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798374488807Subjects--Topical Terms:

643551
Language.
Index Terms--Genre/Form:

542853
Electronic books.

Application of Neural Language Models for Research Article Classification into Sustainable Development Goals.
LDR:03979nmm a2200409K 4500 001 2360744
005 20231015184511.5
006 m o d
007 cr mn ---uuuuu
008 241011s2022 xx obm 000 0 eng d
020 $a 9798374488807
035 $a (MiAaPQ)AAI30355358
035 $a (MiAaPQ)PontificiaChile_1153466404
035 $a AAI30355358
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Villanueva, Daniela Flores. $3 3701374
245 1 0 $a Application of Neural Language Models for Research Article Classification into Sustainable Development Goals.
264 0 $c 2022
300 $a 1 online resource (97 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 84-09.
500 $a Advisor: Santander, Denis Parra.
502 $a Thesis (M.Sc.)--Pontificia Universidad Catolica de Chile (Chile), 2022.
504 $a Includes bibliographical references
520 $a Sustainability has gained much attention in recent years when we have started to see the effects of climate change and environmental damage, and action needs to be taken to keep inhabiting planet Earth. In this thesis, we explore using state-of-the-art Transformerbased language models to develop a Sustainable Development Goals (SDGs) classifier for academic articles. This model could lead academic institutions to measure their contribution to Sustainability and promote collaboration between interdisciplinary researchers to tackle current world challenges using knowledge from different fields. We propose a finetuned RoBERTa model that reaches an f1-score of 73%. We also studied two Explainable Artificial Intelligence techniques to better understand the model predictions, Attention Mechanism and Integrated Gradients. Finally, we conducted a user study to discover the best explanation method between the two using text visualization techniques. We concluded that Attention Mechanism visualizations better help the users understand model predictions, even when said predictions are erroneous.
520 $a La sustentabilidad ha ganado mucha atencion recientemente, que se han empezado a ´ evidenciar los efectos del cambio climatico y da ´ no al medio ambiente. Esto ha hecho ˜ necesario tomar acciones urgentes para poder continuar habitando en el planeta Tierra. Un primer paso en esta direccion es medir la contribuci ´ on actual de las universidades a los ´ Objetivos de Desarrollo Sostenible (ODS). As´i, en esta tesis se exploro el uso de mode- ´ los de lenguage basados en Transformers para desarrollar un clasificador de para art´iculos academicos. Este modelo podr ´ ´ia lograr que las instituciones academicas midan su con- ´ tribucion a la sustentabilidad y tambi ´ en promover la colaboraci ´ on entre investigadores de ´ diferentes areas para resolver desaf ´ ´ios del mundo actual. Se propone un modelo RoBERTa al que se aplico´ fine-tuning que alcanza un f1-score de 73%. Adicionalmente se estudio el ´ uso de dos tecnicas de Inteligencia Artificial Explicable (XAI): mecanismos de atenci ´ on´ y gradientes integrados, para entender las predicciones generadas por el modelo. Finalmente, se condujo un estudio de usuario para descubrir cual de los m ´ etodos de explicaci ´ on´ descritos es mejor, a traves del uso de t ´ ecnicas de visualizaci ´ on de texto. Se concluye ´ que los mecanismos de atencion ayudan m ´ as que los gradientes integrados a entender las ´ predicciones del modelo, incluso cuando dichas predicciones son erroneas.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Language. $3 643551
650 4 $a Text categorization. $3 3689475
650 4 $a Deep learning. $3 3554982
650 4 $a Clean technology. $3 3564885
650 4 $a Neural networks. $3 677449
650 4 $a Librarians. $3 3399392
650 4 $a Probability. $3 518898
650 4 $a Machine translation. $3 3687988
650 4 $a Visualization. $3 586179
650 4 $a Probability distribution. $3 3562293
650 4 $a Finance. $3 542899
650 4 $a Library science. $3 539284
650 4 $a Statistics. $3 517247
650 4 $a Sustainability. $3 1029978
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0679
690 $a 0800
690 $a 0508
690 $a 0399
690 $a 0338
690 $a 0463
690 $a 0640
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a Pontificia Universidad Catolica de Chile (Chile). $3 3550823
773 0 $t Masters Abstracts International $g 84-09.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30355358 $z click for full text (PQDT)