Papers by Yuchen Zhai

5 papers
UnClE: Explicitly Leveraging Semantic Similarity to Reduce the Parameters of Word Embeddings (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to reduce word embedding parameters ignore semantic information . existing methods do not consider semantic information, allowing for performance degradation .
Approach: They propose a method that leverages semantic similarity with weight sharing to reduce dimensionality of word embeddings.
Outcome: The proposed method reduces word embedding parameters by more than 11x on a standard English-German dataset.
Counterfactual Generator: A Weakly-Supervised Method for Named Entity Recognition (2020.emnlp-main)

Copied to clipboard

Challenge: Using labeled data, named entity recognition is labor-intensive, time-consuming and expensive.
Approach: They propose a method which decomposes named entity into two parts: entity and context.
Outcome: The proposed method improves the generalization ability of models under limited observational examples.
Investigating Hallucinations in Simultaneous Machine Translation: Knowledge Distillation Solution and Components Analysis (2025.naacl-long)

Copied to clipboard

Challenge: Existing methods to mitigate hallucinations in siMT generate fluency but unfaithful translation.
Approach: They propose a method that utilizes the OMT model to mitigate hallucinations in SiMT.
Outcome: The proposed method reduces hallucinations and improves the SiMT performance.
Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets (2026.findings-acl)

Copied to clipboard

Challenge: Existing methods for dataset poisoning require full-dataset poison, which breaks code compilability.
Approach: They propose a functionality-preserving poisoning approach that injects short, compilable weak-use fragments into executed code paths.
Outcome: The proposed method contaminates 10% of the dataset while maintaining 100% compilability and functional correctness.
Continual Few-shot Intent Detection (2022.coling-1)

Copied to clipboard

Challenge: Existing intent detection systems are trained with lots of labeled data over a predefined set of intent classes.
Approach: They propose a prefix-guided lightweight encoder with three auxiliary strategies to prevent catastrophic forgetting and negative knowledge transfer across tasks.
Outcome: The proposed system prevents catastrophic forgetting and encourages positive knowledge transfer across tasks.

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