• Publications
  • Influence
Neural CRF Model for Sentence Alignment in Text Simplification
TLDR
A novel neural CRF alignment model is proposed which not only leverages the sequential nature of sentences in parallel documents but also utilizes a neural sentence pair model to capture semantic similarity.
Discourse Level Factors for Sentence Deletion in Text Simplification
TLDR
It is found that discourse level factors contribute to the challenging task of predicting sentence deletion for simplification, and it is revealed that professional editors utilize different strategies to meet readability standards of elementary and middle schools.
Learning Word Embeddings for Low-Resource Languages by PU Learning
TLDR
A Positive-Unlabeled Learning (PU-Learning) approach is designed to factorize the co-occurrence matrix and validate the proposed approaches in four different languages.
Multi-task Learning for Universal Sentence Embeddings: A Thorough Evaluation using Transfer and Auxiliary Tasks
TLDR
This paper shows that joint learning of multiple tasks results in better generalizable sentence representations by conducting extensive experiments and analysis comparing the multi-task and single-task learned sentence encoders.
Neural CRF Sentence Alignment Model for Text Simplification
TLDR
A novel neural CRF alignment model is proposed which not only leverages the sequential nature of sentences in parallel documents but also utilizes a neural sentence pair model to capture semantic similarity.
Neural semi-Markov CRF for Monolingual Word Alignment
TLDR
A novel neural semi-Markov CRF alignment model, which unifies word and phrase alignments through variable-length spans and demonstrates good generalizability to three out-of-domain datasets and shows great utility in two downstream applications: automatic text simplification and sentence pair classification tasks.