Stars
Official implementation of "GPT or BERT: why not both?"
Training code for Baby-Llama, our submission to the strict-small track of the BabyLM challenge.
A Substring Extraction-Based RAG Method for Minimizing Hallucinations in Aircraft Maintenance Question Answering
Simple tool for generating tokens with open source transformers and/or calculate per-token surprisal.
An Open-source Neural Hierarchical Multi-label Text Classification Toolkit
[ACL 2023] Global and Local Hierarchy-aware Contrastive Framework for Hierarchical Implicit Discourse Relation Recognition
Repository of small data analysis and visualisation projects to try out libraries and create new types of visualisations. Mostly using Python.
Anatole is a minimalistic two-column theme for Hugo.
Kim, Yu, & Ettinger (2022). “No, they did not”: Dialogue response dynamics in pre-trained language models. COLING 2022.
The Universal Decompositional Semantics (UDS) dataset and the Decomp toolkit
A beautiful, simple, clean, and responsive Jekyll theme for academics
An annotated implementation of the Transformer paper.
Turn (almost) any Python command line program into a full GUI application with one line
Annotations related to the following paper: "Caption'' as a Coherence Relation: Evidence and Implications
A general text classifier based on BERT. Multi-process data processing, multi-gpu parallel training, rich monitoring indicators.
Transformers for Information Retrieval, Text Classification, NER, QA, Language Modelling, Language Generation, T5, Multi-Modal, and Conversational AI
Aspectuality across Genre: A Distributional Semantics Approach
Convert Wikipedia database dumps into plaintext files
Code for McCarthy et al. (2020): Measuring the Similarity of Grammatical Gender Systems by Comparing Partitions