Benjamin Heinzerling

bpemb. Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)

pyrouge. A Python wrapper for the ROUGE summarization evaluation package

bunny. A progress bar like tqdm, but with more bunny.

ran. A PyTorch implementation of Recurrent Additive Networks by Lee et al. (2017)

dougu. Assorted tools and utility functions, mainly for doing NLP with Python

lm-as-kb. Code for the paper: Language Models as Knowledge Bases: On Entity Representations, Storage Capacity, and Paraphrased Queries (EACL 2021)

descriptors. A collection of descriptors for validating input data.

draw_entity.js. A package for visualizing entities in texts

subword-sequence-tagging. Code for the paper: Sequence Tagging with Contextual and Non-Contextual Subword Representations: A Multilingual Evaluation (ACL 2019)

numeric-property-repr. Code for the paper: Monotonic Representation of Numeric Properties in Language Models (ACL 2024)

rank-corr. An application designed to teach the ranked correlation measures Kendall's tau, Spearman's rho, and average precision.

selpref-emb. Selectional Preference Embeddings (EMNLP 2017)

anth. A simple command line interface to the ACL Anthology

semantic-search. Simple example showing "semantic" search with sentence-transformers and FAISS nearest neighbor search