Papers by Juncheng Wan

4 papers
PAEG: Phrase-level Adversarial Example Generation for Neural Machine Translation (2022.coling-1)

Copied to clipboard

Challenge: Existing methods for adversarial example generation are word-level or character-level, which ignore the ubiquitous phrase structure.
Approach: They propose a phrase-level adversarial example generation framework to enhance the robustness of the translation model by adopting a sentence-level substitution strategy.
Outcome: The proposed method improves translation performance and robustness to noise on three benchmarks.
Smart-Start Decoding for Neural Machine Translation (2021.naacl-main)

Copied to clipboard

Challenge: Existing neural machine translation models adopt a monotonic decoding order of either left-to-right or right-to left.
Approach: They propose a method that starts decoding target words from the right side of a median word and generates words on the left.
Outcome: The proposed method outperforms baseline models on three datasets.
Nested Named Entity Recognition with Span-level Graphs (2022.acl-long)

Copied to clipboard

Challenge: Named entity recognition is one of the major subtasks of information extraction for extracting categorized named entities from unstructured text.
Approach: They propose to use retrieval-based span-level graphs to connect spans and entities in the training data based on n-gram features to integrate information of similar neighbor entities into the span representation.
Outcome: The proposed method achieves general improvements on all three benchmarks and special superiority on low frequency entities.
A Novel Negative Sample Generation Method for Contrastive Learning in Hierarchical Text Classification (2025.coling-main)

Copied to clipboard

Challenge: Existing methods for hierarchical text classification struggle with fine-grained labels, leading to difficulties in accurate classification.
Approach: They propose a hierarchical sequence ranking method for generating diverse negative samples using hierarchically structured hierarchic labels.
Outcome: The proposed method achieves state-of-art (SOTA) on two datasets showing that it can distinguish between fine-grained labels and discriminate.

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