Sentence Level or Token Level Features for Automatic Short Answer Grading?: Use Both

Saha, Swarnadeep; Dhamecha, Tejas I.; Marvaniya, Smit; Sindhgatta, Renuka; Sengupta, Bikram

doi:10.1007/978-3-319-93843-1_37

Cited by 49 publications

(33 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We find that the MDA-ASAS yields significantly better results than all compared systems except Saha et al (Saha et al 2018) in all the three tasks. We report 4 points and 3 points better macro-averaged-F1 than Saha et al (Saha et al 2018) in 2-way and 3-way respectively.…”

Section: Effect Of the Data Augmentation Strategiesmentioning

confidence: 56%

“…InferSent (Conneau et al 2017) used a max pooled bidirectional LSTM network to learn universal sentence embeddings from the MultiNLI corpus (Williams, Nangia, and Bowman 2017). These embeddings have been employed as features in conjunction with hand-crafted features by Saha et al (Saha et al 2018) for ASAS. Hassan et al (Hassan, Fahmy, and El-Ramly 2018) proposed a supervised learning approach for short answer automatic scoring based on paragraph embeddings, which included Word2Vec (Pennington, Socher, and Manning 2014), GloVe (Pennington, Socher, andManning 2014), Fasttext (Joulin et al 2016) and Elmo (Peters et al 2018).…”

Section: Transfer Learning In Asasmentioning

confidence: 99%

“…One of the two neural models is a state-of-the-art model by Marvaniya et al (Marvaniya et al 2018). Marvaniya et al (Marvaniya et al 2018) utilizes simple lexical baseline features and sophisticated sentence-embedding base features. The other neural model is Saha et al (Saha et al 2018).…”

Section: Effect Of the Data Augmentation Strategiesmentioning

confidence: 99%

“…Marvaniya et al (Marvaniya et al 2018) utilizes simple lexical baseline features and sophisticated sentence-embedding base features. The other neural model is Saha et al (Saha et al 2018). Saha et al utilize hand-crafted token features along with deep learning embeddings, suggesting that such fusion is helpful for ASAS.…”

Section: Effect Of the Data Augmentation Strategiesmentioning

confidence: 99%

See 3 more Smart Citations

Multiple Data Augmentation Strategies for Improving Performance on Automatic Short Answer Scoring

Lun

Zhu

Tang

et al. 2020

AAAI

View full text Add to dashboard Cite

Automatic short answer scoring (ASAS) is a research subject of intelligent education, which is a hot field of natural language understanding. Many experiments have confirmed that the ASAS system is not good enough, because its performance is limited by the training data. Focusing on the problem, we propose MDA-ASAS, multiple data augmentation strategies for improving performance on automatic short answer scoring. MDA-ASAS is designed to learn language representation enhanced by data augmentation strategies, which includes back-translation, correct answer as reference answer, and swap content. We argue that external knowledge has a profound impact on the ASAS process. Meanwhile, the Bidirectional Encoder Representations from Transformers (BERT) model has been shown to be effective for improving many natural language processing tasks, which acquires more semantic, grammatical and other features in large amounts of unsupervised data, and actually adds external knowledge. Combining with the latest BERT model, our experimental results on the ASAS dataset show that MDA-ASAS brings a significant gain over state-of-art. We also perform extensive ablation studies and suggest parameters for practical use.

show abstract

Section: Effect Of the Data Augmentation Strategiesmentioning

confidence: 56%

Section: Transfer Learning In Asasmentioning

confidence: 99%

Section: Effect Of the Data Augmentation Strategiesmentioning

confidence: 99%

Section: Effect Of the Data Augmentation Strategiesmentioning

confidence: 99%

See 2 more Smart Citations

Multiple Data Augmentation Strategies for Improving Performance on Automatic Short Answer Scoring

Lun

Zhu

Tang

et al. 2020

AAAI

View full text Add to dashboard Cite

show abstract

“…One specific task, automatic short answer grading (ASAG), whose objective is to automatically score the free-text answers from students according to the corresponding reference answer [9], has attracted great attentions from a variety of research communities and some promising results have been already obtained [7,8,5,9,10]. However, ASAG still remains challenging mainly for two reasons.…”

Section: Introductionmentioning

confidence: 99%

Automatic Short Answer Grading via Multiway Attention Networks

Liu¹,

Ding²,

Wang

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Automatic short answer grading (ASAG), which autonomously score student answers according to reference answers, provides a costeffective and consistent approach to teaching professionals and can reduce their monotonous and tedious grading workloads. However, ASAG is a very challenging task due to two reasons: (1) student answers are made up of free text which requires a deep semantic understanding; and (2) the questions are usually open-ended and across many domains in K-12 scenarios. In this paper, we propose a generalized end-to-end ASAG learning framework which aims to (1) autonomously extract linguistic information from both student and reference answers; and (2) accurately model the semantic relations between free-text student and reference answers in open-ended domain. The proposed ASAG model is evaluated on a large real-world K-12 dataset and can outperform the state-of-the-art baselines in terms of various evaluation metrics.

show abstract

Text mining in education

Mello

Andre

Pinheiro

et al. 2019

WIREs Data Min & Knowl

138

View full text Add to dashboard Cite

The explosive growth of online education environments is generating a massive volume of data, specially in text format from forums, chats, social networks, assessments, essays, among others. It produces exciting challenges on how to mine text data in order to find useful knowledge for educational stakeholders. Despite the increasing number of educational applications of text mining published recently, we have not found any paper surveying them. In this line, this work presents a systematic overview of the current status of the Educational Text Mining field. Our final goal is to answer three main research questions: Which are the text mining techniques most used in educational environments? Which are the most used educational resources? And which are the main applications or educational goals? Finally, we outline the conclusions and the more interesting future trends. This article is categorized under: Application Areas > Education and Learning Ensemble Methods > Text Mining

show abstract

Sentence Level or Token Level Features for Automatic Short Answer Grading?: Use Both

Cited by 49 publications

References 13 publications

Multiple Data Augmentation Strategies for Improving Performance on Automatic Short Answer Scoring

Multiple Data Augmentation Strategies for Improving Performance on Automatic Short Answer Scoring

Automatic Short Answer Grading via Multiway Attention Networks

Text mining in education

Contact Info

Product

Resources

About