Papers by Yichao Zhou

8 papers
Learning to Discriminate Perturbations for Blocking Adversarial Attacks in Text Classification (D19-1)

Copied to clipboard

Challenge: Existing studies on adversarial attacks on deep learning models focus on generation of adversarials and defense against adversarial attacks.
Approach: They propose a framework to identify and adjust malicious perturbations and block adversarial attacks for machine learning models.
Outcome: The proposed framework outperforms baseline methods in blocking adversarial attacks for text classification models.
Learning Gender-Neutral Word Embeddings (D18-1)

Copied to clipboard

Challenge: Word embeddings trained on human-generated corpora inherit strong gender stereotypes . prior studies show such embeddables exhibit social biases, such as gender stereotype .
Approach: They propose a method to preserve gender information in certain dimensions of word vectors . they propose GN-GloVe, which is a gender-neutral variant of the word embedding model .
Outcome: The proposed method preserves gender information in certain dimensions of word vectors while compelling other dimensions to be free of gender influence.
ProToM: Promoting Prosocial Behaviour via Theory of Mind-Informed Feedback (2026.findings-acl)

Copied to clipboard

Challenge: ProToM provides targeted, context-sensitive feedback to individual agents, achieving a higher success rate, shorter task completion times, and is consistently preferred by human users.
Approach: They propose a Theory of Mind-informed facilitator that provides targeted, context-sensitive feedback to individual agents.
Outcome: The proposed system provides targeted, context-sensitive feedback to promote prosocial behaviour, even when not directly aligned with one’s own goals.
SUMIE: A Synthetic Benchmark for Incremental Entity Summarization (2025.coling-main)

Copied to clipboard

Challenge: Existing datasets that test incrementally update entity summaries are lacking.
Approach: They propose a fully synthetic dataset that exposes real-world IES challenges by generating diverse attributes, summaries, and unstructured paragraphs with 99% alignment accuracy.
Outcome: The proposed dataset shows that state-of-the-art LLMs struggle to update summaries with an F1 higher than 80.4%.
Selective Labeling: How to Radically Lower Data-Labeling Costs for Document Extraction Models (2023.emnlp-main)

Copied to clipboard

Challenge: a key bottleneck in developing automatic extraction models for visually rich documents is the cost of acquiring labeled documents.
Approach: They propose selective labeling to provide "yes/no" labels for candidate extractions predicted by a model trained on partially labeled documents.
Outcome: The proposed method reduces the cost of acquiring labeled data by 10 with a negligible loss in accuracy.
Domain Knowledge Empowered Structured Neural Net for End-to-End Event Temporal Relation Extraction (2020.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to extract event temporal relations from text data are limited by hard constraints and large datasets.
Approach: They propose a framework that enhances deep neural network with distributional constraints constructed by probabilistic domain knowledge to improve the baseline neural network models.
Outcome: The proposed framework improves baseline models with strong statistical significance on two widely used datasets in news and clinical domains.
“The Boating Store Had Its Best Sail Ever”: Pronunciation-attentive Contextualized Pun Recognition (2020.acl-main)

Copied to clipboard

Challenge: Identifying and modeling puns is challenging as they involve implicit semantic or phonological tricks.
Approach: They propose a method to detect puns in a sentence and then locate them in it . they propose to capture phonetic associations between the context and phonetic symbols .
Outcome: The proposed method outperforms state-of-the-art methods in pun detection and location tasks.
Enhancing Incremental Summarization with Structured Representations (2024.findings-emnlp)

Copied to clipboard

Challenge: Large language models struggle with processing extensive input contexts, leading to redundancy or incoherency.
Approach: They propose a chain-of-key update based on JSON structured memory representations to improve summarization performance by 40% and 14% on two public datasets.
Outcome: The proposed method improves summarization performance by 40% and 14% on two datasets.

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