SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1808.09075 · 2018

Evaluating the Utility of Hand-crafted Features in Sequence Labelling

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 6 functions out of this paper's own repositories and ran 6 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
minghao-wu/CRF-AE canonical 6 of 6
FunctionStatusWhere it lives
argmax Ran minghao-wu/CRF-AE/model.py
code served (permissive licence) · get_code("d38f06bbd9f9c98c")
create_dico Ran minghao-wu/CRF-AE/utils.py
code served (permissive licence) · get_code("993c98ce2b8239c2")
create_mapping Ran minghao-wu/CRF-AE/utils.py
code served (permissive licence) · get_code("6a16376f2de1c75f")
get_name Ran minghao-wu/CRF-AE/utils.py
code served (permissive licence) · get_code("326dd961371b8acb")
prepare_sequence Ran minghao-wu/CRF-AE/model.py
code served (permissive licence) · get_code("66f180f39c43eeb5")
to_scalar Ran minghao-wu/CRF-AE/model.py
code served (permissive licence) · get_code("ac476e734740149f")

Repositories linked to this paper

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

Abstract

Conventional wisdom is that hand-crafted features are redundant for deep learning models, as they already learn adequate representations of text automatically from corpora. In this work, we test this claim by proposing a new method for exploiting handcrafted features as part of a novel hybrid learning approach, incorporating a feature auto-encoder loss component. We evaluate on the task of named entity recognition (NER), where we show that including manual features for part-of-speech, word shapes and gazetteers can improve the performance of a neural CRF model. We obtain a $F_1$ of 91.89 for the CoNLL-2003 English shared task, which significantly outperforms a collection of highly competitive baseline models. We also present an ablation study showing the importance of auto-encoding, over using features as either inputs or outputs alone, and moreover, show including the autoencoder components reduces training requirements to 60\%, while retaining the same predictive accuracy.

For agents

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

get_harvested_code_for_paper("1808.09075")
get_code_for_paper("1808.09075")
have("1808.09075")

Connect an agent — have() is free.