Dora Demszky

dspy. DSPy: The framework for programming—not prompting—language models

TalkMoves. The TalkMoves Dataset: K-12 mathematics lesson transcripts annotated for teacher and student discursive moves

little-mallet-wrapper. A Python wrapper around the topic modeling functions of MALLET.

ecco. Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, BERT, RoBERTA, T5, and T0).

lit. The Learning Interpretability Tool: Interactively analyze ML models to understand their behavior in an extensible and framework agnostic interface.

causal-text-papers. Curated research at the intersection of causal inference and natural language processing.

litbank. Annotated dataset of 100 works of fiction to support tasks in natural language processing and the computational humanities.

Top2Vec. Top2Vec learns jointly embedded topic, document and word vectors.

naacl2021-longdoc-tutorial. Python

NUS-MOOC-Transacts-Corpus. An annotated corpus of discussion forum threads from Massive Open Online Courses.

python-string-similarity. A library implementing different string similarity and distance measures using Python.

NUS-MOOC-Transacts-Corpus. An annotated corpus of discussion forum threads from Massive Open Online Courses.

LOTClass. [EMNLP 2020] Text Classification Using Label Names Only: A Language Model Self-Training Approach

snorkel. A system for quickly generating training data with weak supervision

SentiWordNet. The SentiWordNet sentiment lexicon

acl2020-confidence-regularization. Python

debias. Methods of training NLP models to ignored biased strategies

DiscoEval. EMNLP DiscoEval paper

cross_domain_coherence. A Cross-Domain Transferable Neural Coherence Model https://arxiv.org/abs/1905.11912

transfer-learning-conv-ai. 🦄 State-of-the-Art Conversational AI with Transfer Learning

ConvoKit. ConvoKit is a toolkit for extracting conversational features and analyzing social phenomena in conversations. It includes several large conversational datasets along with scripts exemplifying the use of the toolkit on these datasets.

unify-emotion-datasets. A Survey and Experiments on Annotated Corpora for Emotion Classification in Text

emmorphpy. A wrapper, a lemmatizer and REST API implemented in Python for emMorph (Humor) Hungarian morphological analyzer

huspacy. HuSpaCy: industrial-strength Hungarian natural language processing

pywnxml. Python3 API for WordNet XML (Hungarian WordNet / BalkaNet / VisDic format)

rnaseqtopicmodeling. A repository for research work involving topic modeling RNA-seq data.

hierarchical-attention-networks. Document classification with Hierarchical Attention Networks in TensorFlow. WARNING: project is currently unmaintained, issues will probably not be addressed.

deconfounded_lexicon_induction. Python

awesome-hungarian-nlp. A curated list of NLP resources for Hungarian

GuidedLDA. semi supervised guided topic model with custom guidedLDA

emLam. Preprocessing scripts for Hungarian Language Modeling

qanli. Source code for "Transforming Question Answering Datasets Into Natural Language Inference Datasets"