xyz's starred repositories
counterfactually-augmented-data
Learning the Difference that Makes a Difference with Counterfactually-Augmented Data
siamese-triplet
Siamese and triplet networks with online pair/triplet mining in PyTorch
perspectiveapi
Perspective is an API that uses machine learning models to score the perceived impact a comment might have on a conversation. See https://developers.perspectiveapi.com for more information.
disentangling-influence
Code to audit indirect influence in black box models.
Structured-Self-Attention
A Structured Self-attentive Sentence Embedding
adaptive-span
Transformer training code for sequential tasks
neural-editor
Repository for "Generating Sentences by Editing Prototypes"
python-ftfy
Fixes mojibake and other glitches in Unicode text, after the fact.
lm-context-analysis
Code for the ACL 2018 paper "Sharp Nearby, Fuzzy Far Away: How Neural Language Models Use Context"
vmf_vae_nlp
Code for EMNLP18 paper "Spherical Latent Spaces for Stable Variational Autoencoders"
topically-driven-language-model
Tensorflow code to train TDLM
multimodal-vae-public
A PyTorch implementation of "Multimodal Generative Models for Scalable Weakly-Supervised Learning" (https://arxiv.org/abs/1802.05335)
SDLM-pytorch
Code accompanying EMNLP 2018 paper Language Modeling with Sparse Product of Sememe Experts
aspect_adversarial
Aspect-augmented Adversarial Networks for Domain Adaptation
awd-lstm-lm
LSTM and QRNN Language Model Toolkit for PyTorch
para-nmt-50m
Pre-trained models and code and data to train and use models from "Pushing the Limits of Paraphrastic Sentence Embeddings with Millions of Machine Translations"
iclr2016
Python code for training all models in the ICLR paper, "Towards Universal Paraphrastic Sentence Embeddings". These models achieve strong performance on semantic similarity tasks without any training or tuning on the training data for those tasks. They also can produce features that are at least as discriminative as skip-thought vectors for semantic similarity tasks at a minimum. Moreover, this code can achieve state-of-the-art results on entailment and sentiment tasks.
MSVED-morph-reinflection
An implementation of semi-supervised VAE for morphology reinflection.
disentangle-semantics-syntax
Code for "A Multi-Task Approach for Disentangling Syntax and Semantics in Sentence Representations" (NAACL 2019)
structural-probes
Codebase for testing whether hidden states of neural networks encode discrete structures.