Publications (14)
KVL-BERT: Knowledge Enhanced Visual-and-Linguistic BERT for Visual Commonsense Reasoning
Dandan Song, Siyi Ma, Zhanchen Sun +2
Reasoning is a critical ability towards complete visual understanding. To develop machine with cognition-level visual understanding and reasoning abilities, the visual commonsense…
Earlier Attention? Aspect-Aware LSTM for Aspect-Based Sentiment Analysis
Bowen Xing, Lejian Liao, Dandan Song +4
Aspect-based sentiment analysis (ABSA) aims to predict fine-grained sentiments of comments with respect to given aspect terms or categories. In previous ABSA methods, the importanc…
A Comprehensive Evaluation of Large Language Models on Aspect-Based Sentiment Analysis
Changzhi Zhou, Dandan Song, Yuhang Tian +6
Recently, Large Language Models (LLMs) have garnered increasing attention in the field of natural language processing, revolutionizing numerous downstream tasks with powerful reaso…
Small-footprint Keyword Spotting with Graph Convolutional Network
Xi Chen, Shouyi Yin, Dandan Song +3
Despite the recent successes of deep neural networks, it remains challenging to achieve high precision keyword spotting task (KWS) on resource-constrained devices. In this study, w…
Dynamic Multi-scale Convolution for Dialect Identification
Tianlong Kong, Shouyi Yin, Dawei Zhang +6
Time Delay Neural Networks (TDNN)-based methods are widely used in dialect identification. However, in previous work with TDNN application, subtle variant is being neglected in dif…
Laser: Parameter-Efficient LLM Bi-Tuning for Sequential Recommendation with Collaborative Information
Xinyu Zhang, Linmei Hu, Luhao Zhang +3
Sequential recommender systems are essential for discerning user preferences from historical interactions and facilitating targeted recommendations. Recent innovations employing La…
Dialogue State Distillation Network with Inter-slot Contrastive Learning for Dialogue State Tracking
Jing Xu, Dandan Song, Chong Liu +5
In task-oriented dialogue systems, Dialogue State Tracking (DST) aims to extract users' intentions from the dialogue history. Currently, most existing approaches suffer from error…
ActiShade: Activating Overshadowed Knowledge to Guide Multi-Hop Reasoning in Large Language Models
Huipeng Ma, Luan Zhang, Dandan Song +10
In multi-hop reasoning, multi-round retrieval-augmented generation (RAG) methods typically rely on LLM-generated content as the retrieval query. However, these approaches are inher…
HarnessCompass: Guiding Automatic Harness Evolution toward Generalizable and Effective Agent Harnesses
Luan Zhang, Ruochen Zhou, Dandan Song +9
Harness design plays a critical role in agent performance by shaping how large language models (LLMs) perceive, reason over, and act within executable environments. Recent work has…
Transformer with Bidirectional Decoder for Speech Recognition
Xi Chen, Songyang Zhang, Dandan Song +2
Attention-based models have made tremendous progress on end-to-end automatic speech recognition(ASR) recently. However, the conventional transformer-based approaches usually genera…
RefineCoder: Iterative Improving of Large Language Models via Adaptive Critique Refinement for Code Generation
Changzhi Zhou, Xinyu Zhang, Dandan Song +6
Code generation has attracted increasing attention with the rise of Large Language Models (LLMs). Many studies have developed powerful code LLMs by synthesizing code-related instru…
PruneTIR: Inference-Time Tool Call Pruning for Effective yet Efficient Tool-Integrated Reasoning
Luan Zhang, Dandan Song, Zhijing Wu +8
Tool-integrated reasoning (TIR) enables large language models (LLMs) to enhance their capabilities by interacting with external tools, such as code interpreters (CI). Most recent s…
A Multi-turn Machine Reading Comprehension Framework with Rethink Mechanism for Emotion-Cause Pair Extraction
Changzhi Zhou, Dandan Song, Jing Xu +1
Emotion-cause pair extraction (ECPE) is an emerging task in emotion cause analysis, which extracts potential emotion-cause pairs from an emotional document. Most recent studies use…
Hierarchical Image Classification with A Literally Toy Dataset
Long He, Dandan Song, Liang Zheng
Unsupervised domain adaptation (UDA) in image classification remains a big challenge. In existing UDA image dataset, classes are usually organized in a flattened way, where a plain…