Papers by Zhongqing Wang
Exploring Knowledge Filtering for Retrieval-Augmented Discriminative Tasks (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent studies have focused on generative tasks, while its potential in discriminative tasks remains largely unexplored. |
| Approach: | They propose a framework that incorporates knowledge filtering and prediction fusion mechanisms to improve model performance. |
| Outcome: | The proposed framework improves model performance on discriminative tasks by filtering out harmful knowledge and integrating it into the input context. |
A Unified Framework for Synaesthesia Analysis (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Synaesthesia is a cognitive phenomenon structuring human thought and action, which makes understanding it challenging. |
| Approach: | They propose a framework for annotating synaesthetic elements and exploring their relationship . they propose to include sensory modalities, cues and stimuli in the framework . |
| Outcome: | The proposed framework yields state-of-the-art results, demonstrating its effectiveness. |
Exploring Hybrid Sampling Inference for Aspect-based Sentiment Analysis (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for inference require multiple sampling with preset size . however, it is a high-cost method that requires multiple sampling . |
| Approach: | They propose a method that combines multiple and single sampling to greatly reduce the cost of multiple sampling without sacrificing performance. |
| Outcome: | The proposed method greatly reduces the cost of multiple sampling without sacrificing performance. |
Aspect-based Sentiment Analysis via Synthetic Image Generation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in Aspect-Based Sentiment Analysis (ABSA) have shown promising results, yet the semantics derived solely from textual data remain limited. |
| Approach: | They propose a supervised image generation framework to generate synthetic images with alignment to text and sentiment information. |
| Outcome: | The proposed approach significantly outperforms state-of-the-art methods on multiple benchmark datasets. |
Transition-based Opinion Generation for Aspect-based Sentiment Analysis (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to aspect-based sentiment analysis often overlook the importance of explicitly modeling structure among sentiment elements. |
| Approach: | They propose to integrate general pre-trained sequence-to-sequence language models with a structure-aware transition-based approach to model sentiment structure. |
| Outcome: | The proposed model improves the state-of-the-art performance on several benchmark datasets. |
Sentimental Image Generation for Aspect-based Sentiment Analysis (2025.findings-acl)
Copied to clipboard
| Challenge: | Recent work on textual Aspect-Based Sentiment Analysis (ABSA) has demonstrated promising performance, but limited semantics derived from raw data. |
| Approach: | They propose a method that provides visual semantics to reinforce textual ABSA by adding additional augmentations to the input data. |
| Outcome: | The proposed method can provide visual semantics to reinforce the textual extraction. |
Uncovering Sentiment Analysis Circuit in Large Language Model (2026.acl-long)
Copied to clipboard
| Challenge: | Prior work has shown that sentiment is encoded linearly in LLM representations, but their ability to utilize this information remains fragile to prompt variations. |
| Approach: | They propose a simple inference-time intervention method that amplifies circuit features to compensate for insufficient activation. |
| Outcome: | The proposed method improves on a sentiment analysis circuit with sparse autoencoders and circuit-level analysis. |
Exploring Graph Pre-training for Aspect-based Sentiment Analysis (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies tend to extract the sentiment elements in a generative manner to avoid complex modeling of sentiment elements. |
| Approach: | They propose a generative model with an Element-level Graph Pre-training paradigm and a Task Decomposition Pre- training paradigm to make it generalizable and robust against irregular sentiment quadruples. |
| Outcome: | The proposed model is generalizable and robust against irregular sentiment quadruples. |
Structure-aware Generation Model for Cross-Domain Aspect-based Sentiment Classification (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing generation models for cross-domain aspect-based sentiment classification ignore syntactic structures . syntaktic structures are pre-trained on natural language and can be catastrophic forgetting of distributional knowledge. |
| Approach: | They propose a structure-aware generation model that explicitly encodes syntactic structure into the model. |
| Outcome: | The proposed model can learn domain-irrelevant features based on syntactic pivot features. |
End-to-End Emotion Semantic Parsing (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing studies focus on detecting emotion from text, but recent studies have shown that emotions may be experienced and caused by semantic constituents. |
| Approach: | They propose a task called emotion semantic parsing which parses emotion and semantic constituents into an abstract semantic tree structure. |
| Outcome: | The proposed model performs better than existing models and is more cognitive and structurally robust. |
Revisiting Classical Chinese Event Extraction with Ancient Literature Information (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies on classical Chinese event extraction focus on grafting the complex modeling from English or modern Chinese works, neglecting the unique characteristic of this language. |
| Approach: | They propose a Literary Vision-Language Model (VLM) for classical Chinese event extraction . they integrate annotations, historical background and character glyphs to capture the inner- and outer-context information from the sequence. |
| Outcome: | The proposed model can capture the inner- and outer-context information at nearly zero cost. |
Semantic Simplification for Sentiment Classification (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent work on document-level sentiment classification has shown that the sentiment in the original text is often hard to capture . previous studies focus on predicting the overall sentiment from original text using statistical or neural models, but these methods either heavily rely on human knowledge or suffer from the complex structure of the text. |
| Approach: | They propose a document-level sentiment classification model that enhances the original text with a simplified clause to intensify its sentiment. |
| Outcome: | Empirical studies show that the proposed model over strong baselines is effective over several strong baseline models. |
Opinion Tree Parsing for Aspect-based Sentiment Analysis (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing generative models for aspect-based sentiment analysis lack structure well-formedness guarantees and built-in elements alignments. |
| Approach: | They propose an opinion tree parsing model which parses all sentiment elements from an opinion-tree. |
| Outcome: | The proposed model is much faster than previous models and can explore correlations among sentiment elements. |
Employing Glyphic Information for Chinese Event Extraction with Vision-Language Model (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies on event extraction have incorporated a variety of features, including textual elements and annotations. |
| Approach: | They propose a glyphic multi-modal Chinese event extraction model with hieroglyphic images to capture morphological structure from the sequence. |
| Outcome: | The proposed model can extract events from a Chinese and KBP Eval datasets at low cost. |
Chinese Synesthesia Detection: New Dataset and Models (2022.findings-acl)
Copied to clipboard
| Challenge: | Synesthesia refers to the description of perceptions in one sensory modality through concepts from other modalities. |
| Approach: | They propose a task called synesthesia detection to extract the sensory word of a sentence and predict the original and synesthetic sensory modalities of the corresponding sensory word. |
| Outcome: | The proposed model achieves state-of-the-art on the Chinese synesthesia dataset. |
Sentiment Forecasting in Dialog (2020.coling-main)
Copied to clipboard
| Challenge: | Existing studies on sentiment classification focus on determining polarity of existing utterances. |
| Approach: | They propose a Neural Sentiment Forecasting task which simulates the next utterance based on context and a sequence influence model to learn both pair-wise and seq-wise influence. |
| Outcome: | The proposed model outperforms existing models over several strong baselines. |
Exploring Multilingual Pre-trained Language Model for Aspect-based Sentiment Analysis (2026.findings-acl)
Copied to clipboard
| Challenge: | Aspect-based sentiment analysis studies have focused on English datasets, but labeled data is scarce. |
| Approach: | They propose a multilingual pre-trained language model that leverages bilingual pre-training to leverage aspects-based sentiment analysis. |
| Outcome: | The proposed model outperforms state-of-the-art models across multiple languages. |
Exploring Artificial Image Generation for Stance Detection (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to stance detection focus on textual content, which may not capture the implicit stance conveyed by the author. |
| Approach: | They propose a novel approach that transforms original texts into artificially generated images and uses the visual representation to enhance stance detection. |
| Outcome: | The proposed model is able to detect author's stance from a set of artificially generated images and then leverages both the original textual content and the generated image to identify the author' stance. |
Discrete Opinion Tree Induction for Aspect-based Sentiment Analysis (2022.acl-long)
Copied to clipboard
| Challenge: | Dependency trees are used for aspect-based sentiment classification but are not optimized for aspect classification. |
| Approach: | They propose an aspect-specific and language-agnostic discrete latent opinion tree model as an alternative structure to explicit dependency trees. |
| Outcome: | The proposed model can achieve competitive performance and interpretability on six English benchmarks and one Chinese dataset. |
Emotion Detection with Neural Personal Discrimination (D19-1)
Copied to clipboard
| Challenge: | Existing approaches to automatically predict the emotions of posts consider each post individually and predict their emotions independently. |
| Approach: | They propose a Neural Personal Discrimination approach to identify personal attributes from posts and connect relevant posts with similar attributes to jointly learn their emotions. |
| Outcome: | The proposed approach improves on existing models by capturing attributes-aware words and predicting emotions among relevant posts. |
Bridging Modality Gap for Effective Multimodal Sentiment Analysis in Fashion-related Social Media (2025.coling-main)
Copied to clipboard
| Challenge: | Existing sentiment analysis tasks focus on text comprehension, but visual content is important for emotional expression. |
| Approach: | They propose a multimodal framework that integrates information from various modalities for sentiment classification of fashion posts. |
| Outcome: | The proposed framework outperforms existing unimodal and multimodal baselines on a comprehensive dataset and significantly outperformed existing unilmodal and multiple modal frameworks. |
Aligning Black-Box LLMs for Aspect Sentiment Quad Prediction (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models lack task-specific alignment with ASQP . supervised small language models (SLMs) lack the extensive knowledge of LLMs. |
| Approach: | They propose a framework that combines large language models and small language models to align LLM outputs with human preferences. |
| Outcome: | The proposed framework improves Aspect Sentiment Quad Prediction performance by combining SLMs and LLMs. |
Multi-Turn Dialogue Generation in E-Commerce Platform with the Context of Historical Dialogue (2020.findings-emnlp)
Copied to clipboard
WeiSheng Zhang, Kaisong Song, Yangyang Kang, Zhongqing Wang, Changlong Sun, Xiaozhong Liu, Shoushan Li, Min Zhang, Luo Si
| Challenge: | Existing research on customer service dialogue generation generates generic responses from sellers . however, such cost prohibits small businesses, and multiturn dialogue generation is becoming more popular. |
| Approach: | They propose a novel and extensible dialogue generation method by leveraging sellers’ historical dialogue information to generate generic seller responses. |
| Outcome: | The proposed model can generate high-quality responses that cater to specific sellers’ characteristics and exhibit consistent superiority over baselines on a real-world multi-turn customer service dialogue dataset. |
Cross-Domain Sentiment Classification using Semantic Representation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies on cross-domain sentiment classification ignore the semantic relevance between domains. |
| Approach: | They propose to use Abstract Meaning Representation to help with cross-domain sentiment classification by combining sentence-level AMRs with text-graph interaction models. |
| Outcome: | The proposed model is effective over strong baselines and shows its importance over strong models. |
New Compendium of a Myriad of Plants: A New Dataset Describing Ancient Chinese Plants (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to digitize ancient Chinese texts and extract information from them are shallow and inconsistent with modern realities. |
| Approach: | They propose to expand ancient Chinese datasets using large language model . they focus on Great Compendium of Myriad Flowers, an ancient plants dataset . |
| Outcome: | The proposed model can extract plant-related information from classical Chinese poetry and prose. |
Exploring Unified Training Framework for Multimodal User Profiling (2025.coling-main)
Copied to clipboard
| Challenge: | Recent studies on user profiling focus on extracting multiple aspects of user attributes from textual reviews, but these studies do not fully exploit the potential of the rich multimodal data at hand. |
| Approach: | They propose a task that utilizes both review texts and their accompanying images to generate comprehensive user profiles. |
| Outcome: | The proposed training framework incorporates historical review texts and images for user profile generation. |
Exploring Logographic Image for Chinese Aspect-based Sentiment Classification (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for aspect-based sentiment classification have focused on English text, but Chinese is a language derived from pictographs and different from other phonetic languages. |
| Approach: | They propose to use a logographic image to capture internal morphological structure from character sequence . they propose to explicitly incorporate a symbolic image with review text for sentiment classification . |
| Outcome: | The proposed method improves over baselines and improves on existing methods. |
Exploring Chain-of-Thought for Multi-modal Metaphor Detection (2024.acl-long)
Copied to clipboard
| Challenge: | Metaphors are commonly found in advertising and internet memes, but lack of high-quality textual data is a challenge for language models . a new framework for multi-modal metaphor detection is being developed to address these challenges . |
| Approach: | They propose a framework that extracts and integrates knowledge from Large Language Models into smaller ones to improve model performance. |
| Outcome: | The proposed framework outperforms existing models on the MET-MEME dataset. |
CalligraphicOCR for Chinese Calligraphy Recognition (2025.emnlp-main)
Copied to clipboard
| Challenge: | Increasing efforts to digitize calligraphy have rely on isolated character recognition, requiring expensive manual splitting into single characters. |
| Approach: | They propose a calligraphicOCR model with calligraphy image augmentation and action-based corrector targeting the root of the problem. |
| Outcome: | The proposed model outperforms baseline models due to visual variations and domain shifts in semantics and is more accurate than previous models. |
Stance Detection with Hierarchical Attention Network (C18-1)
Copied to clipboard
| Challenge: | Recent studies have focused on document-level opinion mining, but linguistic information is correlated with the stance of the document. |
| Approach: | They propose a hierarchical attention neural model to employ various linguistic information to construct the document representation. |
| Outcome: | The proposed model can detect stance of documents on two datasets. |
One-Dimensional Object Detection for Streaming Text Segmentation of Meeting Dialogue (2025.findings-acl)
Copied to clipboard
Rui He, Zhongqing Wang, Minjie Qiang, Hongling Wang, Yifan.zhang Yifan.zhang, Hua Xu, Shuai Fan, Guodong Zhou
| Challenge: | Current text segmentation models exhibit numerous limitations, such as imbalances in labels that affect the stability of model training and discrepancies between the model’s training tasks (sentence classification) and the actual text segmenting. |
| Approach: | They implement a sliding window-based segmentation method and employ two different levels of sliding window based balanced label strategies to stabilize the training process of the streaming segmentation model. |
| Outcome: | The proposed method is robust, controllable, and achieves state-of-the-art performance. |