Skip to content
conftrace_
2017 IJCNLP IJCNLP 2017

Lexical Simplification with the Deep Structured Similarity Model

Abstract

AbstractWe explore the application of a Deep Structured Similarity Model (DSSM) to ranking in lexical simplification. Our results show that the DSSM can effectively capture fine-grained features to perform semantic matching when ranking substitution candidates, outperforming the state-of-the-art on two standard datasets used for the task.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing
🐣 Hot Topic Early Bird - semantic matching

Authors

Lis Pereira, Xiaodong Liu, John Lee

Topics

Machine Learning > Core Methods > Metric Learning Deep Learning > Architectures > Neural Networks Natural Language Processing > Applications > Text Classification Machine Learning > Core Methods > Ranking

Keywords

semantic matching text simplification lexical simplification deep structured similarity model neural network
Download PDF

More from IJCNLP 2017

All IJCNLP 2017 papers →
Learning to Explain Non-Standard English Words and Phrases
Towards Abstractive Multi-Document Summarization Using Submodular Function-Based Framework, Sentence Compression and Merging
Domain Adaptation for Relation Extraction with Domain Adversarial Neural Network
Proofread Sentence Generation as Multi-Task Learning with Editing Operation Prediction
An Exploration of Data Augmentation and RNN Architectures for Question Ranking in Community Question Answering
Deriving Consensus for Multi-Parallel Corpora: an English Bible Study