Publications

We propose PLAYER*, a novel framework for Murder Mystery Games (剧本杀) using an anytime sampling-based planner and a questioning-driven search framework. 

Existing datasets for narrative understanding often fail to represent the complexity and uncertainty of relationships in real-life social scenarios. To address this gap, we introduce a new benchmark, Conan, designed for extracting and analysing intricate character relation graphs from detective narratives. 

we construct OpenToM, a new benchmark for assessing N-ToM with (1) longer and clearer narrative stories, (2) characters with explicit personality traits, (3) actions that are triggered by character intentions, and (4) questions designed to challenge LLMs' capabilities of modeling characters' mental states of both the physical and psychological world. 

NarrativePlay has been evaluated on two types of narratives, detective and adventure stories, where users can either explore the world or increase affinity with other characters through conversations.

We introduce NarrativePlay, a novel system that allows users to role-play a fictional character and interact with other characters in narratives such as novels in an immersive environment. 

We propose to leverage the in-context learning capability of LLMs to handle multiple task inputs, thereby reducing token and time costs. This could potentially improve task performance during API queries due to better conditional distribution mapping. 

We conduct a comprehensive survey of narrative understanding tasks and the potential of modularized LLMs to address novel narrative understanding tasks. 

Contrastive opinion extraction aims to extract a structured summary or key points organised as positive and negative viewpoints towards a common aspect or topic.

We propose a novel semi-supervised approach for vaccine attitude detection, called VADET. A variational autoencoding architecture based on language models is employed to learn from unlabelled data the topical information of the domain. 

In this work, we present the results of interviews with eight members of fact-checking teams from two organisations. Team members described their fact-checking processes and the challenges they currently face in completing a fact-check in a robust and timely way. 

In this demo, we introduce a web-based misinformation detection system PANACEA on COVID-19 related claims, which has two modules, fact-checking and rumour detection.

In this paper, we propose a novel dynamic Brand-Topic Model (dBTM) which is able to automatically detect and track brand-associated sentiment scores and polarity-bearing topics from product reviews organised in temporally-ordered time intervals.

In this paper, we propose the Brand-Topic Model (BTM) which aims to detect brand-associated polarity-bearing topics from product reviews.