SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1907.12484 · 2019

Joey NMT: A Minimalist NMT Toolkit for Novices

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 17 functions out of this paper's own repositories and ran 13 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
deep-spin/sigmorphon-seq2seq pwc_unofficial 6 of 7
jarl93/joeynmt-modified pwc_unofficial 2 of 5
benjaminbeilharz/hierarchical-reinforcement-learning pwc_unofficial 2 of 2
deep-spin/S7 extension 2 of 2
copy not recorded — 1 of 1
FunctionStatusWhere it lives
build_general_value_network Ran benjaminbeilharz/hierarchical-reinforcement-learning/joeynmt/value_network.py
code served (permissive licence) · get_code("fbfce742341c3312")
check_vocab_and_split Ran this paper's copy was not recorded; identical code first harvested from rsennrich/subword-nmt
pointer only · get_code("a0deb98db94ae939")
clones Ran jarl93/joeynmt-modified/joeynmt/helpers.py
code served (permissive licence) · get_code("86b7d1950504d5b1")
encode Ran deep-spin/S7/scripts/apply_bpe.py
code served (permissive licence) · get_code("52d69829a4cee830")
ends Ran deep-spin/sigmorphon-seq2seq/hallucination/augment.py
code served (permissive licence) · get_code("a8c303bcecfe0b48")
find_good_range Ran deep-spin/sigmorphon-seq2seq/hallucination/augment.py
code served (permissive licence) · get_code("294b5b42eb8b85cc")
get_pairs Ran deep-spin/S7/scripts/apply_bpe.py
code served (permissive licence) · get_code("290febe7a42e8479")
make_fake_user_answer_labels Ran benjaminbeilharz/hierarchical-reinforcement-learning/subtask_pretraining.py
code served (permissive licence) · get_code("5664f103cf301cd7")
make_logger Ran jarl93/joeynmt-modified/joeynmt/helpers.py
code served (permissive licence) · get_code("aad8945d314699ad")
pad_and_stack_hyps Ran deep-spin/sigmorphon-seq2seq/joeynmt/model.py
code served (permissive licence) · get_code("a19f205cc566f56c")
read_data Ran deep-spin/sigmorphon-seq2seq/hallucination/augment.py
code served (permissive licence) · get_code("ff0ec87d63da9b32")
read_task1_data Ran deep-spin/sigmorphon-seq2seq/hallucination/generate_task1_data.py
code served (permissive licence) · get_code("77a42ba2975545ab")
rules Ran deep-spin/sigmorphon-seq2seq/hallucination/generate_task1_data.py
code served (permissive licence) · get_code("9e0d921dd261c239")
build_scheduler Not yet run jarl93/joeynmt-modified/joeynmt/builders.py
code served (permissive licence) · get_code("e0cdbcc27a1c011a")
build_scheduler Not yet run deep-spin/sigmorphon-seq2seq/joeynmt/builders.py
code served (permissive licence) · get_code("c7677be26fa62d12")
make_model_dir Not yet run jarl93/joeynmt-modified/joeynmt/helpers.py
code served (permissive licence) · get_code("d2439dd3cffbf595")
token_batch_size_fn Not yet run jarl93/joeynmt-modified/joeynmt/data.py
code served (permissive licence) · get_code("cb329af957271d21")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We present Joey NMT, a minimalist neural machine translation toolkit based on PyTorch that is specifically designed for novices. Joey NMT provides many popular NMT features in a small and simple code base, so that novices can easily and quickly learn to use it and adapt it to their needs. Despite its focus on simplicity, Joey NMT supports classic architectures (RNNs, transformers), fast beam search, weight tying, and more, and achieves performance comparable to more complex toolkits on standard benchmarks. We evaluate the accessibility of our toolkit in a user study where novices with general knowledge about Pytorch and NMT and experts work through a self-contained Joey NMT tutorial, showing that novices perform almost as well as experts in a subsequent code quiz. Joey NMT is available at https://github.com/joeynmt/joeynmt .

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1907.12484")
get_code_for_paper("1907.12484")
have("1907.12484")

Connect an agent — have() is free.