A Prism Module for Semantic Disentanglement in Name Entity Recognition
Natural Language Processing has been perplexed for many years by the problem that multiple semantics are mixed inside a word, even with the help of context. To solve this problem, we propose a prism module to disentangle the semantic aspects of words and reduce noise at the input layer of a model. In the prism module, some words are selectively replaced with task-related semantic aspects, then these denoised word representations can be fed into downstream tasks to make them easier. Besides, we also introduce a structure to train this module jointly with the downstream model without additional data. This module can be easily integrated into the downstream model and significantly improve the performance of baselines on named entity recognition (NER) task. The ablation analysis demonstrates the rationality of the method. As a side effect, the proposed method also provides a way to visualize the contribution of each word.
Code (1)
Tasks
Disentanglementnamed-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NERSimilar Papers 제목 키워드 기반
Learning Disentangled Representation for One-shot Progressive Face Swapping
Although face swapping has attracted much attention in recent years, it remains a challenging problem. Existing methods leverage a large number of data samples to explore the intrinsic properties of face swapping without…
AttributeDisentanglementFace SwappingMeasuring the Unspoken: A Disentanglement Model and Benchmark for Psychological Analysis in the Wild
Generative psychological analysis of in-the-wild conversations faces two fundamental challenges: (1) existing Vision-Language Models (VLMs) fail to resolve Articulatory-Affective Ambiguity, where visual patterns of speec…
Visual GroundingConceptPrism: Concept Disentanglement in Personalized Diffusion Models via Residual Token Optimization
Personalized text-to-image (T2I) generation has emerged as a key application for creating user-specific concepts from a few reference images. The core challenge is concept disentanglement: separating the target concept f…
PRISM: Privacy-Aware Routing for Adaptive Cloud-Edge LLM Inference via Semantic Sketch Collaboration
Large Language Models (LLMs) demonstrate impressive capabilities in natural language understanding and generation, but incur high communication overhead and privacy risks in cloud deployments, while facing compute and me…
Natural Language UnderstandingHeterogeneous Face Recognition via Face Synthesis with Identity-Attribute Disentanglement
Heterogeneous Face Recognition (HFR) aims to match faces across different domains (e.g., visible to near-infrared images), which has been widely applied in authentication and forensics scenarios. However, HFR is a challe…
AttributeData AugmentationDisentanglementFace Generation+2