Papers by Urchade Zaratiana
GLiNER: Generalist Model for Named Entity Recognition using Bidirectional Transformer (2024.naacl-long)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) models are limited to a set of predefined entity types. Large language models (LLMs) can extract arbitrary entities through natural language instructions. |
| Approach: | They propose a model that can identify any type of entity using a transformer encoder. |
| Outcome: | The proposed model outperforms existing models on NER benchmarks on a set of predefined entities. |
GNNer: Reducing Overlapping in Span-based NER Using Graph Neural Networks (2022.acl-srw)
Copied to clipboard
| Challenge: | Named Entity Recognition (NER) uses sequence labelling and span classification to identify entities. |
| Approach: | They propose a framework that uses Graph Neural Networks to enrich the span representation to reduce the number of overlapping spans during prediction. |
| Outcome: | The proposed framework reduces the number of overlapping spans while maintaining competitive metric performance. |
Filtered Semi-Markov CRF (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for sequence labeling tasks such as Named Entity Recognition (NER) suffer from quadratic complexity over sequence length and poor performance compared to CRF. |
| Approach: | They propose a variant of Semi-Markov CRF that incorporates a filtering step to eliminate irrelevant segments, reducing complexity and search space. |
| Outcome: | The proposed method outperforms both CRF and Semi-CRF on several NER benchmarks while being significantly faster. |
GLiNER2: Schema-Driven Multi-Task Learning for Structured Information Extraction (2025.emnlp-demos)
Copied to clipboard
| Challenge: | Existing solutions for information extraction (IE) require specialized models for different tasks or require expensive large language models. |
| Approach: | They propose a framework that enhances the original GLiNER architecture to support named entity recognition, text classification, and hierarchical structured data extraction within a single efficient model. |
| Outcome: | The proposed framework improves performance across diverse IE tasks and accessibility compared to LLM-based alternatives. |