Tapping the Potential of Coherence and Syntactic Features in Neural Models for Automatic Essay Scoring

11/24/2022
by   Xinying Qiu, et al.
0

In the prompt-specific holistic score prediction task for Automatic Essay Scoring, the general approaches include pre-trained neural model, coherence model, and hybrid model that incorporate syntactic features with neural model. In this paper, we propose a novel approach to extract and represent essay coherence features with prompt-learning NSP that shows to match the state-of-the-art AES coherence model, and achieves the best performance for long essays. We apply syntactic feature dense embedding to augment BERT-based model and achieve the best performance for hybrid methodology for AES. In addition, we explore various ideas to combine coherence, syntactic information and semantic embeddings, which no previous study has done before. Our combined model also performs better than the SOTA available for combined model, even though it does not outperform our syntactic enhanced neural model. We further offer analyses that can be useful for future study.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/08/2020

Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence

Topic models extract meaningful groups of words from documents, allowing...
research
07/09/2021

Learning Syntactic Dense Embedding with Correlation Graph for Automatic Readability Assessment

Deep learning models for automatic readability assessment generally disc...
research
11/14/2017

SkipFlow: Incorporating Neural Coherence Features for End-to-End Automatic Text Scoring

Deep learning has demonstrated tremendous potential for Automatic Text S...
research
07/24/2017

Thread Reconstruction in Conversational Data using Neural Coherence Models

Discussion forums are an important source of information. They are often...
research
04/18/2018

Neural Automated Essay Scoring and Coherence Modeling for Adversarially Crafted Input

We demonstrate that current state-of-the-art approaches to Automated Ess...
research
08/19/2018

Lexicosyntactic Inference in Neural Models

We investigate neural models' ability to capture lexicosyntactic inferen...
research
12/06/2018

Context is Key: New Approaches to Neural Coherence Modeling

We formulate coherence modeling as a regression task and propose two nov...

Please sign up or login with your details

Forgot password? Click here to reset