Lasuie: Unifying information extraction with latent adaptive structure-aware generative language model
Universally modeling all typical information extraction tasks (UIE) with one generative
language model (GLM) has revealed great potential by the latest study, where various IE …
language model (GLM) has revealed great potential by the latest study, where various IE …
Layoutllm-t2i: Eliciting layout guidance from llm for text-to-image generation
In the text-to-image generation field, recent remarkable progress in Stable Diffusion makes it
possible to generate rich kinds of novel photorealistic images. However, current models still …
possible to generate rich kinds of novel photorealistic images. However, current models still …
Entity-centered cross-document relation extraction
Relation Extraction (RE) is a fundamental task of information extraction, which has attracted
a large amount of research attention. Previous studies focus on extracting the relations …
a large amount of research attention. Previous studies focus on extracting the relations …
Revisiting disentanglement and fusion on modality and context in conversational multimodal emotion recognition
It has been a hot research topic to enable machines to understand human emotions in
multimodal contexts under dialogue scenarios, which is tasked with multimodal emotion …
multimodal contexts under dialogue scenarios, which is tasked with multimodal emotion …
Knowledge-enhanced event relation extraction via event ontology prompt
L Zhuang, H Fei, P Hu - Information Fusion, 2023 - Elsevier
Identifying temporal and subevent relationships between different events (ie, event relation
extraction) is an important step towards event-centric natural language processing, which …
extraction) is an important step towards event-centric natural language processing, which …
Syntax-based dynamic latent graph for event relation extraction
L Zhuang, H Fei, P Hu - Information Processing & Management, 2023 - Elsevier
This paper focuses on extracting temporal and parent–child relationships between news
events in social news. Previous methods have proved that syntactic features are valid …
events in social news. Previous methods have proved that syntactic features are valid …
Diaasq: A benchmark of conversational aspect-based sentiment quadruple analysis
The rapid development of aspect-based sentiment analysis (ABSA) within recent decades
shows great potential for real-world society. The current ABSA works, however, are mostly …
shows great potential for real-world society. The current ABSA works, however, are mostly …
Constructing holistic spatio-temporal scene graph for video semantic role labeling
As one of the core video semantic understanding tasks, Video Semantic Role Labeling
(VidSRL) aims to detect the salient events from given videos, by recognizing the predict …
(VidSRL) aims to detect the salient events from given videos, by recognizing the predict …
Joint alignment of multi-task feature and label spaces for emotion cause pair extraction
Emotion cause pair extraction (ECPE), as one of the derived subtasks of emotion cause
analysis (ECA), shares rich inter-related features with emotion extraction (EE) and cause …
analysis (ECA), shares rich inter-related features with emotion extraction (EE) and cause …
A tree-like structured perceptron for transition-based biomedical event extraction
Event extraction in the biomedical domain has many complex situations, such as nested
events, overlapping events, and multiple processing streams. For the problem of massive …
events, overlapping events, and multiple processing streams. For the problem of massive …