Related papers: EventWeave: A Dynamic Framework for Capturing Core…
While existing video benchmarks largely consider specialized downstream tasks like retrieval or question-answering (QA), contemporary multimodal AI systems must be capable of well-rounded common-sense reasoning akin to human visual…
Capturing interactions among event arguments is an essential step towards robust event argument extraction (EAE). However, existing efforts in this direction suffer from two limitations: 1) The argument role type information of contextual…
Given a set of graphs from some unknown family, we want to generate new graphs from that family. Recent methods use diffusion on either graph embeddings or the discrete space of nodes and edges. However, simple changes to embeddings (say,…
Script event prediction aims to predict the subsequent event given the context. This requires the capability to infer the correlations between events. Recent works have attempted to improve event correlation reasoning by using pretrained…
Empathy, which is widely used in psychological counselling, is a key trait of everyday human conversations. Equipped with commonsense knowledge, current approaches to empathetic response generation focus on capturing implicit emotion within…
Empathy is a critical factor in fostering positive user experiences in conversational AI. While models can display empathy, it is often generic rather than tailored to specific tasks and contexts. In this work, we introduce a novel…
Event extraction (EE) is one of the core information extraction tasks, whose purpose is to automatically identify and extract information about incidents and their actors from texts. This may be beneficial to several domains such as…
We present FlipDial, a generative model for visual dialogue that simultaneously plays the role of both participants in a visually-grounded dialogue. Given context in the form of an image and an associated caption summarising the contents of…
We examine the capabilities of a unified, multi-task framework for three information extraction tasks: named entity recognition, relation extraction, and event extraction. Our framework (called DyGIE++) accomplishes all tasks by…
Generative document retrieval, an emerging paradigm in information retrieval, learns to build connections between documents and identifiers within a single model, garnering significant attention. However, there are still two challenges: (1)…
Large Language Models face significant challenges in maintaining coherent interactions over extended dialogues due to their limited contextual memory. This limitation often leads to fragmented exchanges and reduced relevance in responses,…
Event detection is a critical task for timely decision-making in graph analytics applications. Despite the recent progress towards deep learning on graphs, event detection on dynamic graphs presents particular challenges to existing…
Commonsense knowledge is crucial to many natural language processing tasks. Existing works usually incorporate graph knowledge with conventional graph neural networks (GNNs), resulting in a sequential pipeline that compartmentalizes the…
Dialogue disentanglement aims to detach the chronologically ordered utterances into several independent sessions. Conversation utterances are essentially organized and described by the underlying discourse, and thus dialogue disentanglement…
Dense video captioning aims to generate corresponding text descriptions for a series of events in the untrimmed video, which can be divided into two sub-tasks, event detection and event captioning. Unlike previous works that tackle the two…
There is a growing interest in improving the conversational ability of models by filtering the raw dialogue corpora. Previous filtering strategies usually rely on a scoring method to assess and discard samples from one perspective, enabling…
LLM-based social network simulation introduces a new computational approach for modeling event evolution in complex online environments. However, existing methods typically simulate social processes under a fixed event trajectory, treating…
Event detection has been one of the most important research topics in social media analysis. Most of the traditional approaches detect events based on fixed temporal and spatial resolutions, while in reality events of different scales…
State-of-the-art conversational agents have advanced significantly in conjunction with the use of large transformer-based language models. However, even with these advancements, conversational agents still lack the ability to produce…
The diverse relationships among real-world events, including coreference, temporal, causal, and subevent relations, are fundamental to understanding natural languages. However, two drawbacks of existing datasets limit event relation…