Papers by Matthias Hertel

3 papers
Fast Whitespace Correction with Encoder-Only Transformers (2023.acl-demo)

Copied to clipboard

Challenge: a new tool for whitespace correction is available for text with spurious spaces . the tool is 900 times faster than the previous best tool for text correction .
Approach: They propose to combine whitespace correction with a character-level encoder-decoder model and a byte-level byte encoder only model to improve quality.
Outcome: The proposed tool is over 900 times faster than the previous best tool, with the same high quality.
A Fair and In-Depth Evaluation of Existing End-to-End Entity Linking Systems (2023.emnlp-main)

Copied to clipboard

Challenge: Existing evaluations of entity linking systems often lack detailed error analysis or a closer look at the results.
Approach: They evaluate existing entity linking systems and propose two new benchmarks . they characterize their strengths and weaknesses and report on reproducibility aspects .
Outcome: The evaluations of existing system have strong biases and artifacts . they characterize their strengths and weaknesses and report on reproducibility aspects .
ELEVANT: A Fully Automatic Fine-Grained Entity Linking Evaluation and Analysis Tool (2022.emnlp-demos)

Copied to clipboard

Challenge: a tool for fine-grained evaluation of entity linkers on benchmarks is presented . a typical evaluation shows that overall precision and recall are poor . particular benchmarks often require very particular skills from an entity linker .
Approach: They propose a tool for fine-grained evaluation of entity linkers on benchmarks . they use a graph-based tool to analyze performance of a set of entity links .
Outcome: The proposed tool provides an automatic breakdown of the performance by error categories and by entity type.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations