SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1604.05529 · 2016

Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 4 functions out of this paper's own repositories and ran 1 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
bplank/bilstm-aux canonical 1 of 1
ilyagusev/rnnmorph pwc_unofficial 0 of 3
FunctionStatusWhere it lives
drop Ran bplank/bilstm-aux/src/structbilty.py
pointer only (licence: NOASSERTION) · get_code("7cd9c10b78a3b0e1")
build_dense_chars_layer Not yet run ilyagusev/rnnmorph/rnnmorph/char_embeddings_model.py
code served (permissive licence) · get_code("38d94fe63b23b68c")
convert_from_opencorpora_tag Not yet run ilyagusev/rnnmorph/rnnmorph/data_preparation/process_tag.py
code served (permissive licence) · get_code("6e1bbd301beb5989")
process_gram_tag Not yet run ilyagusev/rnnmorph/rnnmorph/data_preparation/process_tag.py
code served (permissive licence) · get_code("90ae33fed83d4f02")

Repositories linked to this paper

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

Abstract

Bidirectional long short-term memory (bi-LSTM) networks have recently proven successful for various NLP sequence modeling tasks, but little is known about their reliance to input representations, target languages, data set size, and label noise. We address these issues and evaluate bi-LSTMs with word, character, and unicode byte embeddings for POS tagging. We compare bi-LSTMs to traditional POS taggers across languages and data sizes. We also present a novel bi-LSTM model, which combines the POS tagging loss function with an auxiliary loss function that accounts for rare words. The model obtains state-of-the-art performance across 22 languages, and works especially well for morphologically complex languages. Our analysis suggests that bi-LSTMs are less sensitive to training data size and label corruptions (at small noise levels) than previously assumed.

For agents

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

get_harvested_code_for_paper("1604.05529")
get_code_for_paper("1604.05529")
have("1604.05529")

Connect an agent — have() is free.