Papers by Xiaomeng Ma

3 papers
Evaluating Transformer Models and Human Behaviors on Chinese Character Naming (2023.tacl-1)

Copied to clipboard

Challenge: Neural network models have been proposed to explain the grapheme-phoneme mapping process in humans for many alphabet languages.
Approach: They propose to use a dictionary-like lookup procedure to map the letter strings to their pronunciations and then use 'transformers' to capture human behavior.
Outcome: The proposed models learned the correspondence of the letter strings and their pronunciation, and captured human behavior in nonce word naming tasks.
How do we get there? Evaluating transformer neural networks as cognitive models for English past tense inflection (2022.aacl-main)

Copied to clipboard

Challenge: English past tense inflections is a typical quasi-regularity task, but it is criticized that it learns only to generalize the most frequent pattern, but not the regular pattern.
Approach: They train a set of transformer models with different settings to examine their behavior on a typical English quasi-regularity task.
Outcome: The models achieved high accuracy on unseen regular verbs and some accuracy on unseen irregular verbs.

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