Papers with metric based

3 papers
Judicious Selection of Training Data in Assisting Language for Multilingual Neural NER (P18-2)

Copied to clipboard

Challenge: Existing approaches to improve NER performance add training data from one or more assisting languages to the primary language.
Approach: They propose a metric based on symmetric KL divergence to filter out highly divergent training instances in the assisting language.
Outcome: The proposed method improves NER performance in many languages, including those with limited training data.
Not Every Metric is Equal: Cognitive Models for Predicting N400 and P600 Components During Reading Comprehension (2025.coling-main)

Copied to clipboard

Challenge: Several studies have focused on predicting the surprisal of a word and its reading time, but only recently, attention has been given to other components, such as P600.
Approach: They propose to model reading times and ERP amplitudes using surprisal and entropy . they also propose a metric based on semantic similarity for N400 and P600 .
Outcome: The proposed metric predicts reading times and ERP amplitudes in Mandarin Chinese.
Transformer Based Multi-Source Domain Adaptation (2020.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to improve machine learning performance are mixed experts and domain adversarial training.
Approach: They investigate the problem of unsupervised multi-source domain adaptation . they combine predictions of multiple domain experts and combine them to induce a domain agnostic representation space .
Outcome: The proposed methods improve models' performance while limiting learning time.

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