Cambridge Language Technology Lab

Cambridge Language Technology Lab's repositories

visual-med-alpaca

Visual Med-Alpaca is an open-source, multi-modal foundation model designed specifically for the biomedical domain, built on the LLaMa-7B.

Language:PythonApache-2.0336 14 7

sapbert

[NAACL'21 & ACL'21] SapBERT: Self-alignment pretraining for BERT & XL-BEL: Cross-Lingual Biomedical Entity Linking.

Language:PythonMIT155 11 10

visual-spatial-reasoning

[TACL'23] VSR: A probing benchmark for spatial undersranding of vision-language models.

Language:PythonApache-2.081 7 2

mirror-bert

[EMNLP'21] Mirror-BERT: Converting Pretrained Language Models to universal text encoders without labels.

Language:PythonMIT73 8 4

composable-sft

A library for parameter-efficient and composable transfer learning for NLP with sparse fine-tunings.

Language:PythonNOASSERTION62 8 5

cometa

Corpus of Online Medical EnTities: the cometA corpus

Language:Jupyter Notebook45 8 4

autopeft

AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-Tuning (Zhou et al.; TACL)

Language:PythonApache-2.035 80

ContrastiveBLI

Improving Word Translation via Two-Stage Contrastive Learning (ACL 2022). Keywords: Bilingual Lexicon Induction, Word Translation, Cross-Lingual Word Embeddings.

Language:PythonMIT32 90

mop

Codes for paper: Mixture-of-Partitions: Infusing Large Biomedical Knowledge Graphs into BERT

Language:Python25 7 4

eva

[AAAI'21] Code release for "Visual Pivoting for (Unsupervised) Entity Alignment".

Language:PythonMIT24 6 8

python4cl

Introductory Python course for computational lingustics

Language:Jupyter NotebookNOASSERTION22 9 3

ACL2022_tutorial_multilingual_dialogue

Materials for "Natural Language Processing for Multilingual Task-Oriented Dialogue" Tutorial at ACL 2022

14 110

multi3woz

The official repository for Multi3WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog Systems (TACL 2023)

Language:PythonMIT14 70

BLICEr

Improving Bilingual Lexicon Induction with Cross-Encoder Reranking (Findings of EMNLP 2022). Keywords: Bilingual Lexicon Induction, Word Translation, Cross-Lingual Word Embeddings.

Language:PythonMIT13 70

ClaPS

Survival of the Most Influential Prompts: Efficient Black-Box Prompt Search via Clustering and Pruning (Zhou et al.; EMNLP 2023 Findings)

Language:PythonMIT13 40

medlama

Language:Python13 60

MirrorWiC

[CoNLL'21] MirrorWiC: On Eliciting Word-in-Context Representationsfrom Pretrained Language Models

Language:PythonMIT11 10 1

e2e_tod_toolkit

A codebase for e2e ToD toolkit.

Language:PythonMIT9 50

prompt4bli

On Bilingual Lexicon Induction with Large Language Models (EMNLP 2023). Keywords: Bilingual Lexicon Induction, Word Translation, Large Language Models, LLMs.

Language:PythonMIT8 60

PairS

Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators (Liu et al.; arXiv preprint arXiv:2403.16950)

Language:PythonMIT700

COD

6 7 1

ensembled-sicl

Language:Python400

functional-genomics-ie

Language:PythonMIT3 60

POSQA

Offical Repo of EMNLP Findings 2023 Paper: POSQA: Probe the World Models of LLMs with Size Comparisons

Language:PythonApache-2.03 50

response_reranking

Code repository for Reranking Overgenerated Responses for End-to-End Task-Oriented Dialogue Systems (LREC-COLING 2024)

Language:PythonMIT3 60

AM2iCo

CC-BY-4.02 20

biocaster_2021

This is a public repo for codes and resources of BioCaster 2021: http://www.biocaster.org

Language:Java2 60

deductive_reasoning_probing

Language:Jupyter NotebookMIT1 60

sqatin

Code for Paper "SQATIN: Supervised Instruction Tuning Meets Question Answering for Improved Dialogue NLU". Published at NAACL-2024 (main conference)

Language:Python100

glances

Glances an Eye on your system. A top/htop alternative for GNU/Linux, BSD, Mac OS and Windows operating systems.

Language:PythonLGPL-3.0030