Papers by Luciano Del Corro
A Study of the Importance of External Knowledge in the Named Entity Recognition Task (P18-2)
Copied to clipboard
| Challenge: | Existing studies have shown that external knowledge is important for Named Entity Recognition . |
| Approach: | They propose a modular framework that divides knowledge into four categories according to depth . they show the effects when incrementally adding deeper knowledge . |
| Outcome: | The proposed framework outperforms agnostic frameworks with more external knowledge . the proposed frameworks outperformed agrarian frameworks on two standard datasets . |
A BERTology View of LLM Orchestrations: Token- and Layer-Selective Probes for Efficient Single-Pass Classification (2026.acl-long)
Copied to clipboard
| Challenge: | Modern LLM deployments are rarely a single model in isolation. |
| Approach: | They propose a model that reuses computation already paid for by the serving LLM . they instantiate a template with pooling, a scoring-attention gate, and a downcast multi-head self-attention probe . |
| Outcome: | The proposed model improves safety and sentiment benchmarks on dense and mixture-of-experts architectures while preserving near-serving latency. |
Facts That Matter (D18-1)
Copied to clipboard
| Challenge: | Existing methods to discover facts from natural language text are based on relation extraction and open information extraction. |
| Approach: | They propose a task of generating a machine-readable representation of the most prominent information in a text document as a set of facts. |
| Outcome: | The proposed system outperforms baselines and text summarizers in a supervised evaluation of salience tasks. |
Autonomous Knowledge Graph Exploration with Adaptive Breadth-Depth Retrieval (2026.acl-long)
Copied to clipboard
Joaquin Polonuer, Lucas Vittor, Iñaki Arango, Ayush Noori, David A. Clifton, Luciano Del Corro, Marinka Zitnik
| Challenge: | ARK: Adaptive Retriever of Knowledge is a tool-using KG retriever that allows a language model to control breadth-depth tradeoffs without requiring a fragile seed selection or pre-set hop depth. |
| Approach: | They propose a tool-using KG retriever that gives a language model control over breadth-depth tradeoff using global lexical search over node descriptors and one-hop neighborhood exploration that composes into multi-hop traversal. |
| Outcome: | The proposed model improves on a teacher's dataset by +7.0, +26.6, and +13.5% while retaining 98.5% of the teacher' s Hit@1 rate. |
Unsupervised Multi-View Post-OCR Error Correction With Language Models (2021.emnlp-main)
Copied to clipboard
| Challenge: | Prior work used text generation techniques or redundancy in similar passages for OCR error correction, which is not appropriate in cases of low corpus redundancies or weak document contextual information. |
| Approach: | They propose to use a pretrained language model to reconcile different OCR views in unsupervised way so that their combination contains fewer errors than each individual view. |
| Outcome: | The proposed model can reconcile multiple OCR views so that their combined version contains fewer errors than the best OCR view. |