Jia Peng Lim
4 papers · 2022–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
Venues
Top co-authors
Research topics
Keywords
topic model
(2)
neural network interpretability
(1)
topic coherence
(1)
variational autoencoder
(1)
neural topic model
(1)
transformer language model
(1)
byte pair encoding
(1)
metric evaluation
(1)
human judgement
(1)
coherence evaluation
(1)
vocabulary space
(1)
decoder weight
(1)
statistical correlation
(1)
coherence metric
(1)
composite activation
(1)
zero-shot topic modeling
(1)
weight disentanglement
(1)
composite topic
(1)
topic modeling
(1)
decoder interpretation
(1)
Papers
Interpreting Topic Models in Byte-Pair Encoding Space
COLING 2025
Disentangling Transformer Language Models as Superposed Topic Models
EMNLP 2023
Large-Scale Correlation Analysis of Automated Metrics for Topic Models
ACL 2023
Towards Reinterpreting Neural Topic Models via Composite Activations
EMNLP 2022