1. CastorPyTorch deep learning models for text processing
2. PyseriniPython interface to the Anserini IR toolkit built on Lucene
3. CovidexA multi-stage neural search engine for the COVID-19 Open Research Dataset
4. Mp Cnn TorchMulti-Perspective Convolutional Neural Networks for modeling textual similarity (He et al., EMNLP 2015)
5. HowlWake word detection modeling toolkit for Firefox Voice, supporting open datasets like Speech Commands and Common Voice.
7. AnseriniA Lucene toolkit for replicable information retrieval research
8. HedwigPyTorch deep learning models for document classification
9. HonkPyTorch implementations of neural network models for keyword spotting
10. BuboqaSimple question answering over knowledge graphs (Mohammed et al., NAACL 2018)
11. DeeBERTDeeBERT: Dynamic Early Exiting for Accelerating BERT Inference
14. VDPWI-NN-TorchVery Deep Pairwise Word Interaction Neural Networks for modeling textual similarity (He and Lin, NAACL/HLT 2016)
16. TREC-COVIDTREC-COVID results - this is a mirror of data on the TREC website in a more convenient format.
17. NCE-CNN-TorchNoise-Contrastive Estimation for Question Answering with Convolutional Neural Networks (Rao et al. CIKM 2016)
18. pygagglea gaggle of deep neural architectures for text ranking and question answering, designed for Pyserini
19. d-bertDistilling BERT using natural language generation.
21. mr.tydiMr. TyDi is a multi-lingual benchmark dataset built on TyDi, covering eleven typologically diverse languages.