Papers by Yichao Zhou
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. |