Related papers: EventWeave: A Dynamic Framework for Capturing Core…
Existing AI systems for modeling human behavior operate at the level of individuals or detect events after they occur. As a result, they systematically fail to capture the collective dynamics that determine whether a group remains stable or…
Event co-occurrences have been proved effective for event extraction (EE) in previous studies, but have not been considered for event argument extraction (EAE) recently. In this paper, we try to fill this gap between EE research and EAE…
While model-based reinforcement learning (MBRL) improves sample efficiency by learning world models from raw observations, existing methods struggle to generalize across structurally similar scenes and remain vulnerable to spurious…
Event extraction involves the detection and extraction of both the event triggers and corresponding event arguments. Existing systems often decompose event extraction into multiple subtasks, without considering their possible interactions.…
People frequently use speech-to-text systems to compose short texts with voice. However, current voice-based interfaces struggle to support composing more detailed, contextually complex texts, especially in scenarios where users are on the…
Social platforms have emerged as crucial platforms for distributing information and discussing social events, offering researchers an excellent opportunity to design and implement novel event detection frameworks. Identifying unspecified…
In recent years, large language models have demonstrated remarkable capabilities in natural language understanding and generation. However, these models often struggle with hallucinations and maintaining long term contextual relevance,…
Retrieval-based conversational systems learn to rank response candidates for a given dialogue context by computing the similarity between their vector representations. However, training on a single textual form of the multi-turn context…
Indoor scene synthesis has become increasingly important with the rise of Embodied AI, which requires 3D environments that are not only visually realistic but also physically plausible and functionally diverse. While recent approaches have…
Event Relation Extraction (ERE) aims to extract multiple kinds of relations among events in texts. However, existing methods singly categorize event relations as different classes, which are inadequately capturing the intrinsic semantics of…
Multi-turn dialogues are essential in many real-world applications of large language models, such as chatbots and virtual assistants. As conversation histories become longer, existing large language models face increasing computational and…
Fully understanding narratives often requires identifying events in the context of whole documents and modeling the event relations. However, document-level event extraction is a challenging task as it requires the extraction of event and…
Event cameras offer microsecond-level latency and robustness to motion blur, making them ideal for understanding dynamic environments. Yet, connecting these asynchronous streams to human language remains an open challenge. We introduce…
While recent advances in large language models (LLMs) have shown promise in automating test generation for regression testing, they often suffer from limited reasoning about program execution, resulting in stagnated coverage growth - a…
A good empathetic dialogue system should first track and understand a user's emotion and then reply with an appropriate emotion. However, current approaches to this task either focus on improving the understanding of users' emotion or on…
Recent work has utilised knowledge-aware approaches to natural language understanding, question answering, recommendation systems, and other tasks. These approaches rely on well-constructed and large-scale knowledge graphs that can be…
We present a new approach to dialogue management using conversational knowledge graphs as core representation of the dialogue state. To this end, we introduce a new dataset, GraphWOZ, which comprises Wizard-of-Oz dialogues in which human…
Adapting large language models to full document translation remains challenging due to the difficulty of capturing long-range dependencies and preserving discourse coherence throughout extended texts. While recent agentic machine…
We present a novel natural language generation system for spoken dialogue systems capable of entraining (adapting) to users' way of speaking, providing contextually appropriate responses. The generator is based on recurrent neural networks…
Generating realistic human motions that naturally respond to both spoken language and physical objects is crucial for interactive digital experiences. Current methods, however, address speech-driven gestures or object interactions…