deep-spin/sparse-marginalization-lvm

Stars
28
Rank 882,216 (Top 18 %)
Language
Python
License
MIT License
Created about 4 years ago
Updated over 3 years ago

deep-spin/sparse-marginalization-lvm

deep-spin

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Official PyTorch (Lightning) implementation of the NeurIPS 2020 paper "Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity".

entmax

The entmax mapping and its loss, a family of sparse softmax alternatives.

infinite-former

tutorial

Web page for our tutorial on latent structure for NLP

lp-sparsemap

LP-SparseMAP: Differentiable sparse structured prediction in coarse factor graphs

UA_COMET

Repository for "Uncertainty-Aware Machine Translation Evaluation", accepted to Findings of EMNLP 2021.

OpenNMT-APE

scheduled-sampling-transformers

Code for the paper "Scheduled Sampling for Transformers"

tower-eval

mcan-vqa-continuous-attention

uncertainties_MT_eval

Code and data for the paper "Disentangling Uncertainty in Machine Translation Evaluation", accepted at EMNLP 2022.

sparse_text_generation

hallucinations-in-nmt

sparse_continuous_distributions

This repository provides open-source code for sparse continuous distributions and corresponding Fenchel-Young losses.

robust_MT_evaluation

Repository for "BLEU Meets COMET: Combining Lexical and Neural Metrics Towards Robust Machine Translation Evaluation", accepted at EAMT 2023.

Jupyter Notebook

lmt_hallucinations

qaware-decode

A repository for experiments in quality-aware decoding

OpenNMT-entmax

qe-evaluation

Evaluation scripts for the 2019 machine translation quality estimation shared task

sparse-communication

Jupyter Notebook

understanding-spigot

Code for the paper "Understanding the Mechanics of SPIGOT: Surrogate Gradients for Latent Structure Learning"

entmax-jax

The entmax mapping in JAX

spectra-rationalization

Repository for SPECTRA: Sparse Structured Text Rationalization, accepted at EMNLP 2021 main conference.

explainable-qe-shared-task

IST-Unbabel 2021 Submission for the Quality Estimation Shared Task

Jupyter Notebook

translation_llm

Jupyter Notebook

non-exchangeable-crc

Jupyter Notebook

crest

Code for CREST: A Joint Framework for Rationalization and Counterfactual Text Generation, accepted at ACL 2023.

pyturbo

Neural dependency parser with higher-order features

S7

Smoothing and Shrinking the Sparse Seq2Seq Search Space

ot-hallucination-detection

efficient_kNN_MT

unn

Code for the paper "Modeling Structure with Undirected Neural Networks"

chunk-based_knn-mt

sigmorphon-seq2seq

DeepSPIN's submission to SIGMORPHON 2020

spec

The Explanation Game: Towards Prediction Explainability through Sparse Communication

SIGMORPHON2019

IT-IST's submission to SIGMORPHON 2019 Task 1

speech-continuous-attention

Speech Classification using Continuous Attention Mechanisms

tutorial-latent-struct-src

Sources for our slides for the latent structure in NLP tutorial

quest-decoding

A package for sampling from Gibbs distributions during inference with LLMs.

translation-hypothesis-ensembling

vqa-multimodal-continuous-attention

quati

Simple and modular library for document classification and sequence tagging.

TVmax

SSHN

Sparse and Structured Hopfield Networks

doce

This is the a repo of DOCE

Jupyter Notebook

deep-spin.github.io

Website of the DeepSPIN ERC project.