Papers by Dejing Dou
Parameter-Efficient Domain Knowledge Integration from Multiple Sources for Biomedical Pre-trained Language Models (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing domain-specific pre-trained language models (PLMs) rely on self-supervised learning over large amounts of domain text, without explicitly integrating domain- specific knowledge. |
| Approach: | They propose to integrate domain knowledge from diverse sources into PLMs by using adapters that are pre-trained for individual domain knowledge sources and integrated via an attention-based knowledge controller. |
| Outcome: | The proposed architecture integrates domain knowledge from diverse sources into PLMs in a parameter-efficient way. |
Simplified Graph Learning for Inductive Short Text Classification (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for short text classification are limited and lack of labeled data is not enough. |
| Approach: | They propose a novel short text classification algorithm which leverages words to handle the lack of labeled data. |
| Outcome: | The proposed model performs better with lower memory consumption and faster inference speed than previous models. |
Exploiting Node Content for Multiview Graph Convolutional Network and Adversarial Regularization (2020.coling-main)
Copied to clipboard
Qiuhao Lu, Nisansa de Silva, Dejing Dou, Thien Huu Nguyen, Prithviraj Sen, Berthold Reinwald, Yunyao Li
| Challenge: | Existing graph autoencoders and its variants have been used for node embedding . a new method is proposed to model consistency across different views of networks . |
| Approach: | They propose a network embedding method which enforces latent representations to be consistent across different views of networks by incorporating a multiview adversarial regularization module. |
| Outcome: | The proposed method compares favorably with the state-of-the-art methods on benchmark datasets and on a real-world application. |
Semantic Oppositeness Assisted Deep Contextual Modeling for Automatic Rumor Detection in Social Networks (2021.eacl-main)
Copied to clipboard
| Challenge: | Social networks face a major challenge in the form of rumors and fake news . rumor detection is suboptimal due to its rapidity and spread of information . |
| Approach: | They propose a semantic oppositeness model that captures elements of discord . they show that it is more resistant to variances introduced by randomness . |
| Outcome: | The proposed model achieves state-of-the-art on rumor detection task with extensive experiments on recent data sets. |
Fisher Information-based Efficient Curriculum Federated Learning with Large Language Models (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing frameworks for learning Large Language Models (LLMs) require adaptive data processing and low-rank adjustment to improve accuracy and fine-tuning speed. |
| Approach: | They propose a fisher information-based adaptive federated curriculum learning framework with two novel methods to improve FL fine-tuning process. |
| Outcome: | The proposed framework improves performance and fine-tuning speed compared with baseline approaches. |
Noise Stability Regularization for Improving BERT Fine-tuning (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent studies show that fine-tuning pre-trained language models is unstable when there are only a small number of training samples available. |
| Approach: | They propose to use a method to regularize noise in deep nets to improve fine-tuning on NLP tasks. |
| Outcome: | The proposed method improves fine-tuning on natural language processing tasks by incorporating noise to the input and demonstrating generalizability and stability. |
Delta Embedding Learning (P19-1)
Copied to clipboard
| Challenge: | Unsupervised word embeddings have limitations to the semantics of words and inadequate fine-tuning of embedded word can lead to suboptimal performance. |
| Approach: | They propose a method that optimizes word embeddings by regularizing them incrementally to ensure they are tuned in an incremental way. |
| Outcome: | The proposed method improves performance on various NLP tasks and shows that it absorbs semantic information without "forging" |
Towards Table-to-Text Generation with Pretrained Language Model: A Table Structure Understanding and Text Deliberating Approach (2022.emnlp-main)
Copied to clipboard
| Challenge: | Currently, the generalization issues hinder the applicability of neural table-to-text models due to the limited source tables. |
| Approach: | They propose a table-structureaware text generation model with pretrained language model and propose TASD to bridge the gap between the structured table and text input. |
| Outcome: | The proposed model bridges the gap between the structured table and text input and generates accurate and fluent descriptive texts on two public datasets. |
AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation (2026.acl-long)
Copied to clipboard
Rui Qian, Chuanhang Deng, Qiang Huang, Jian Xiong, Mingxuan Li, Yingbo Zhou, Wei Zhai, Jintao Chen, Dejing Dou
| Challenge: | Existing models rely on a single segmentation token whose hidden state implicitly encodes both semantic reasoning and spatial localization . Existing methods rely only on SEG>, which encodes semantic reasoning, limiting the model's ability to explicitly disentangle what to segment from where to segment. |
| Approach: | They propose a method which reformulates reasoning segmentation as a structured conditional generation process over image tokens conditioned on language grounded query banks. |
| Outcome: | The proposed model bridges token-level predictions and pixel-level supervision by decoupling spatial grounding from semantic reasoning through structured language grounded query banks. |
AAPO: Enhancing the Reasoning Capabilities of LLMs with Advantage Margin (2026.acl-long)
Copied to clipboard
| Challenge: | Reinforcement learning (RL) has emerged as an effective approach for enhancing the reasoning capabilities of large language models. |
| Approach: | They propose an algorithm that optimizes cross-entropy loss using advantages enhanced through a margin-based estimation scheme. |
| Outcome: | Experimental results show that AAPO improves group relative advantage estimation compared to other methods. |
Graph based Neural Networks for Event Factuality Prediction using Syntactic and Semantic Structures (P19-1)
Copied to clipboard
| Challenge: | Existing work on event factuality prediction (EFP) relies on syntactic and semantic information to identify important context words. |
| Approach: | They propose a graph-based neural network that integrates syntactic and semantic information more effectively. |
| Outcome: | The proposed model integrates syntactic and semantic information more effectively . it provides more meaningful information for downstream tasks than classification formulations . |
RGL: A Simple yet Effective Relation Graph Augmented Prompt-based Tuning Approach for Few-Shot Learning (2022.findings-naacl)
Copied to clipboard
| Challenge: | Pre-trained language models (PLMs) are a good starting point for downstream applications, but it is difficult to generalize them to new tasks given a few labeled samples. |
| Approach: | They propose to use Relation Graph augmented learning to improve the performance of few-shot natural language understanding tasks by rewriting the input sequence into a cloze question with masks. |
| Outcome: | Extensive experiments show that Relation Graph augmented learning (RGL) improves performance of prompt-based tuning strategies. |
Adversarial Attack against Cross-lingual Knowledge Graph Alignment (2021.emnlp-main)
Copied to clipboard
Zeru Zhang, Zijie Zhang, Yang Zhou, Lingfei Wu, Sixing Wu, Xiaoying Han, Dejing Dou, Tianshi Che, Da Yan
| Challenge: | Existing studies on cross-lingual entity alignment under adversarial attacks have not been conducted. |
| Approach: | They propose to use adversarial attack techniques to perturb cross-lingual entity alignment under adversarials. |
| Outcome: | The proposed model hides the attacked entities in dense regions in two KGs, and reduces the gradient vanishing issues in the process of adversarial attacks for further improving the attack effectiveness. |
HotFlip: White-Box Adversarial Examples for Text Classification (P18-2)
Copied to clipboard
| Challenge: | Existing methods to create adversarial examples without explicit knowledge of model parameters are not effective. |
| Approach: | They propose an efficient method to generate white-box adversarial examples to trick a character-level neural classifier by an atomic flip operation. |
| Outcome: | The proposed method can be adapted to attack a word-level classifier with a few constraints. |
Self-Reflection Improves Safety of Large Reasoning Models (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing safety alignment methods are shallow and do not address deeper risks and attacks in reasoning processes. |
| Approach: | They propose a technique that introduces a special Self-Reflection token to enable LRMs to perform self-reflection during generation and recover from harmful outputs. |
| Outcome: | The proposed approach outperforms the baseline model in terms of safety and helpfulness, and significantly improves model safety without adversarial training. |
ClinicalT5: A Generative Language Model for Clinical Text (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Recent generative language models like BART and T5 are gaining popularity with their competitive performance on text generation and tasks cast as generative problems. |
| Approach: | They propose to build domain-specific PLMs through fine-tuning or pre-training from scratch over domain corpora. |
| Outcome: | The proposed model outperforms existing models on domain-specific tasks and compares favorably with its close baselines. |
Introducing Syntactic Structures into Target Opinion Word Extraction with Deep Learning (2020.emnlp-main)
Copied to clipboard
| Challenge: | Current deep learning models fail to exploit syntactic information of sentences . proposed model incorporates syntax-based opinion possibility scores and syntaktic connections between the words . |
| Approach: | They propose to incorporate syntactic information of sentences into deep learning models for TOWE . they propose a novel regularization technique to improve the performance of the models . |
| Outcome: | The proposed model achieves state-of-the-art on four benchmark datasets. |
Federated Learning of Large Language Models with Parameter-Efficient Prompt Tuning and Adaptive Optimization (2023.emnlp-main)
Copied to clipboard
| Challenge: | Prompt tuning of Large Language Models (LLMs) can incur performance degradation or low training efficiency. |
| Approach: | They propose a prompt tuning approach with Adaptive Optimization to enable efficient FL of LLMs. |
| Outcome: | The proposed approach improves performance and efficiency simultaneously and addresses client drift problems on both the device and server sides. |
Improving Aspect-based Sentiment Analysis with Gated Graph Convolutional Networks and Syntax-based Regulation (2020.findings-emnlp)
Copied to clipboard
Amir Pouran Ben Veyseh, Nasim Nouri, Franck Dernoncourt, Quan Hung Tran, Dejing Dou, Thien Huu Nguyen
| Challenge: | Aspect-based Sentiment Analysis (ABSA) seeks to predict sentiment polarity of input sentences toward a specific aspect. |
| Approach: | They propose a graph-based deep learning model that integrates dependency trees into deep learning models to improve ABSA performance. |
| Outcome: | The proposed model achieves state-of-the-art on three benchmark datasets. |
Hierarchical Heterogeneous Graph Representation Learning for Short Text Classification (2021.emnlp-main)
Copied to clipboard
| Challenge: | Short text classification is a fundamental task in natural language processing. |
| Approach: | They propose a new method called SHINE which is based on graph neural network for short text classification. |
| Outcome: | The proposed method outperforms state-of-the-art methods on benchmark short text datasets. |
Exploiting the Syntax-Model Consistency for Neural Relation Extraction (2020.acl-main)
Copied to clipboard
| Challenge: | Existing deep learning models for Relation Extraction (RE) have limited generalization beyond the syntactic structures of the input sentences. |
| Approach: | They propose a deep learning model that uses dependency trees to extract syntactic importance of words for Relation Extraction. |
| Outcome: | The proposed model outperforms existing models on three RE benchmark datasets. |
On Adversarial Examples for Character-Level Neural Machine Translation (C18-1)
Copied to clipboard
| Challenge: | Using adversarial examples to measure robustness of deep learning models has become a standard procedure due to the difficulty of creating white-box adversarials for discrete text input. |
| Approach: | They propose two novel attacks which aim to remove or change a word in a translation, rather than simply break the NMT. |
| Outcome: | The proposed attacks are significantly stronger than their black-box counterparts in different attack scenarios, showing more serious vulnerabilities than previously known. |