Papers by De Wen Soh

4 papers
Re3Syn: A Dependency-Based Data Synthesis Framework for Long-Context Post-training (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for constructing long-context data by concatenating short documents have overlooked a crucial characteristic of long-constituency data quality, semantic dependency.
Approach: They propose a framework called Retrieval, Dependency Recognition, and Reorder for data synthesis which leverages semantic similarity to retrieve relevant documents and form several batches.
Outcome: The proposed framework leverages semantic similarity to retrieve relevant documents and form several batches.
Towards Better Characterization of Paraphrases (2022.acl-long)

Copied to clipboard

Challenge: Existing models of natural language processing lack generalization and performance . existing models are often overreliant on learned spurious correlations resulting in poor generalization.
Approach: They propose to use word position deviation and lexical deviation to characterize paraphrase pairs without expert human annotation.
Outcome: The proposed metrics improve generalizability of models trained on the dataset and can be used to generate specific forms of paraphrases for data augmentation or robustness testing of NLP models.
Order-Agnostic Data Augmentation for Few-Shot Named Entity Recognition (2024.acl-long)

Copied to clipboard

Challenge: Existing DA methods for named entity recognition (NER) are costly and labor-intensive to acquire, necessitating innovative approaches to data scarcity.
Approach: They propose an order-agnostic data augmentation solution that exploits the order-based property in the training phase of sequence-to-sequence NER methods for data augmented.
Outcome: The proposed method significantly enhances the few-shot capabilities of pre-trained language models in low-resource settings.
Large Language Models can Contrastively Refine their Generation for Better Sentence Representation Learning (2024.naacl-long)

Copied to clipboard

Challenge: Existing methods for training contrastive learning based sentence embedding models are largely influenced by the quality of sentence pairs.
Approach: They propose a framework that decomposes LLMs into three stages for training . they propose to refine the generated content at these stages to ensure only high-quality sentence pairs are utilized to train a base contrastive learning model.
Outcome: The proposed framework surpasses ChatGPT and ChatGPP in terms of performance.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations