Zihan Wang

Attention-based Bidirectional Long Short-Term Memory Networks for Relation Classification Using Knowledge Distillation from BERT

2020

Relation classification is an important task in the field of natural language processing. Today the best-performing models often use huge, transformer-based neural architectures like BERT and XLNet and have hundreds of millions of network parameters. …

Disaster Detector on Twitter Using Bidirectional Encoder Representation from Transformers with Keyword Position Information

2020 · 2020 IEEE 2nd International Conference on Civil Aviation Safety and Information Technology (ICCASIT

Deep learning, as one of the most currently remarkable machine learning techniques, has achieved great success in many applications such as image analysis, speech recognition, and text understanding. This work aims to make use of …

Dual Slot Selector via Local Reliability Verification for Dialogue State Tracking

2021 · arXiv (Cornell University)

The goal of dialogue state tracking (DST) is to predict the current dialogue state given all previous dialogue contexts. Existing approaches generally predict the dialogue state at every turn from scratch. However, the overwhelming majority …

Incorporating Hierarchy into Text Encoder: a Contrastive Learning Approach for Hierarchical Text Classification

2022 · arXiv (Cornell University)

Hierarchical text classification is a challenging subtask of multi-label classification due to its complex label hierarchy. Existing methods encode text and label hierarchy separately and mix their representations for classification, where the hierarchy remains unchanged …

Rethinking the Setting of Semi-supervised Learning on Graphs

2022 · arXiv (Cornell University)

We argue that the present setting of semisupervised learning on graphs may result in unfair comparisons, due to its potential risk of over-tuning hyper-parameters for models. In this paper, we highlight the significant influence of …

Evaluating the Smooth Control of Attribute Intensity in Text Generation with LLMs

2024 · arXiv (Cornell University)

Controlling the attribute intensity of text generation is crucial across scenarios (e.g., writing conciseness, chatting emotion, and explanation clarity). The remarkable capabilities of large language models (LLMs) have revolutionized text generation, prompting us to explore …

TDOA based Tightly Coupled Sensor Fusion for UAV Positioning in GPS-denied Environment

2024

Currently, the integration of the Global Navigation Satellite System (GNSS) and Inertial Navigation System (INS) meets the positioning requirements of unmanned aerial vehicles (UAVs) across a wide range of scenarios. However, these systems are not …

Open Ad-hoc Categorization with Contextualized Feature Learning

2025

Adaptive categorization of visual scenes is essential for AI agents to handle changing tasks. Unlike fixed common categories for plants or animals, ad-hoc categories, such as things to sell at a garage sale, are created …

Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis

2025

In the quest for artificial general intelligence, Multi-modal Large Language Models (MLLMs) have emerged as a focal point in recent advancements. However, the predominant focus remains on developing their capabilities in static image understanding. The …

A Simple "Try Again" Can Elicit Multi-Turn LLM Reasoning

2025 · arXiv (Cornell University)

Multi-turn problem solving is critical yet challenging for Large Reasoning Models (LRMs) to reflect on their reasoning and revise from feedback. Existing Reinforcement Learning (RL) methods train large reasoning models on a single-turn paradigm with …

Cross-Lingual Ability of Multilingual BERT: An Empirical Study

2019 · arXiv (Cornell University)

Recent work has exhibited the surprising cross-lingual abilities of multilingual BERT (M-BERT) -- surprising since it is trained without any cross-lingual objective and with no aligned data. In this work, we provide a comprehensive study …