erip Goto Github PK

audio

Data manipulation and transformation for audio signal processing, powered by PyTorch

benchmark

TorchBench is a collection of open source benchmarks used to evaluate PyTorch performance.

bin

bin files

cld3-cli

A command-line interface for Google's CLD3 language identification model.

comet

A Neural Framework for MT Evaluation

contextualized-topic-models

A python package to run contextualized topic modeling. CTMs combine contextualized embeddings (e.g., BERT) with topic models to get coherent topics. Published at EACL and ACL 2021.

contrastive-controlled-mt

Code and data for the IWSLT 2022 shared task on Formality Control for SLT

crfs-rs

Pure Rust port of CRFsuite: a fast implementation of Conditional Random Fields (CRFs)

ctranslate2

Fast inference engine for Transformer models

data

A PyTorch repo for data loading and utilities to be shared by the PyTorch domain libraries.

deep-learning

Repo for the Deep Learning Nanodegree Foundations program.

defer-to-classifiers-hacker

Accompanying code for hacker role for the paper "Teaching Humans When to Defer to a Classifier via Exemplars"

dialect_mt

erip

My silly little page

experiments

fairseq-1

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

fairseq-hello-world

A simple fairseq repro to capitalize a string

fasttext-feedstock

A conda-smithy repository for fasttext.

feiertag

An open-source neural sequence tagging toolkit.

human-or-neural-translation-demo

A small repro of the "Human or Neural Translation?" paper by Bhardwaj et al.

kenlm

KenLM: Faster and Smaller Language Model Queries

ling473-proj1

Project One -- counting Penn Treebank constituents

ling473-proj2

Project Two -- Creating a unigram model

ling473-proj3

Project Three -- Thai Syllabic Segmentation

ling473-proj4

Project Four -- DNA Sequence Searching

ling473-proj5

Project Five -- Bayesian Language Identification

ling570-proj1

English Tokenization

ling573-text-summarization

Text summarization for LING 573

lingvo

Lingvo is a JVM-compatible package containing enumerations of various ISO codes related to language including ISO 639-3 and ISO 15924.

lost-in-translation

What’s Lost in Translation? Characterizing the Impact of Machine Translation as Cross-lingual Normalization on Text Classification