Yibo Hu


2024

pdf bib
Leveraging Codebook Knowledge with NLI and ChatGPT for Zero-Shot Political Relation Classification
Yibo Hu | Erick Skorupa Parolin | Latifur Khan | Patrick Brandt | Javier Osorio | Vito D’Orazio
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Is it possible accurately classify political relations within evolving event ontologies without extensive annotations? This study investigates zero-shot learning methods that use expert knowledge from existing annotation codebook, and evaluates the performance of advanced ChatGPT (GPT-3.5/4) and a natural language inference (NLI)-based model called ZSP. ChatGPT uses codebook’s labeled summaries as prompts, whereas ZSP breaks down the classification task into context, event mode, and class disambiguation to refine task-specific hypotheses. This decomposition enhances interpretability, efficiency, and adaptability to schema changes. The experiments reveal ChatGPT’s strengths and limitations, and crucially show ZSP’s outperformance of dictionary-based methods and its competitive edge over some supervised models. These findings affirm the value of ZSP for validating event records and advancing ontology development. Our study underscores the efficacy of leveraging transfer learning and existing domain expertise to enhance research efficiency and scalability.

2023

pdf bib
ChatEdit: Towards Multi-turn Interactive Facial Image Editing via Dialogue
Xing Cui | Zekun Li | Pei Li | Yibo Hu | Hailin Shi | Chunshui Cao | Zhaofeng He
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

This paper explores interactive facial image editing through dialogue and presents the ChatEdit benchmark dataset for evaluating image editing and conversation abilities in this context. ChatEdit is constructed from the CelebA-HQ dataset, incorporating annotated multi-turn dialogues corresponding to user editing requests on the images. The dataset is challenging, as it requires the system to dynamically track and edit images based on user requests, while generating appropriate natural language responses. To address these challenges, we propose a framework comprising a dialogue module for tracking user requests as well as generating responses, and an image editing module for editing images accordingly. Unlike previous approaches, our framework directly tracks the user request of the current turn from the entire dialogue history and edits the initial image instead of manipulating the output from the previous turn, mitigating error accumulation and attribute forgetting issues. Extensive experiments on the ChatEdit dataset demonstrate the superiority of our framework over previous methods and also improvement rooms, encouraging future research. We will release the code and data publicly to facilitate advancements in complex interactive facial image editing.

2022

pdf bib
Controllable Fake Document Infilling for Cyber Deception
Yibo Hu | Yu Lin | Erick Skorupa Parolin | Latifur Khan | Kevin Hamlen
Findings of the Association for Computational Linguistics: EMNLP 2022

Recent works in cyber deception study how to deter malicious intrusion by generating multiple fake versions of a critical document to impose costs on adversaries who need to identify the correct information. However, existing approaches are context-agnostic, resulting in sub-optimal and unvaried outputs. We propose a novel context-aware model, Fake Document Infilling (FDI), by converting the problem to a controllable mask-then-infill procedure. FDI masks important concepts of varied lengths in the document, then infills a realistic but fake alternative considering both the previous and future contexts. We conduct comprehensive evaluations on technical documents and news stories. Results show that FDI outperforms the baselines in generating highly believable fakes with moderate modification to protect critical information and deceive adversaries.

pdf bib
ConfliBERT: A Pre-trained Language Model for Political Conflict and Violence
Yibo Hu | MohammadSaleh Hosseini | Erick Skorupa Parolin | Javier Osorio | Latifur Khan | Patrick Brandt | Vito D’Orazio
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Analyzing conflicts and political violence around the world is a persistent challenge in the political science and policy communities due in large part to the vast volumes of specialized text needed to monitor conflict and violence on a global scale. To help advance research in political science, we introduce ConfliBERT, a domain-specific pre-trained language model for conflict and political violence. We first gather a large domain-specific text corpus for language modeling from various sources. We then build ConfliBERT using two approaches: pre-training from scratch and continual pre-training. To evaluate ConfliBERT, we collect 12 datasets and implement 18 tasks to assess the models’ practical application in conflict research. Finally, we evaluate several versions of ConfliBERT in multiple experiments. Results consistently show that ConfliBERT outperforms BERT when analyzing political violence and conflict.