SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1805.01052 · 2018

Constituency Parsing with a Self-Attentive Encoder

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 14 functions out of this paper's own repositories and ran 3 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
ringos/nfc-parser pwc_unofficial 3 of 14
FunctionStatusWhere it lives
collapse_unary_strip_pos Ran ringos/nfc-parser/src/analysis/get_sibling.py
code served (permissive licence) · get_code("bd029ebdc4c2a411")
format_elapsed Ran ringos/nfc-parser/src/export.py
code served (permissive licence) · get_code("d568621c7cfd96cc")
pad_charts Ran ringos/nfc-parser/src/benepar/decode_chart.py
code served (permissive licence) · get_code("5fa1c233f4e619bb")
arabic Not yet run ringos/nfc-parser/src/transliterate.py
code served (permissive licence) · get_code("c6fbc9f36f128a4d")
evalb Not yet run ringos/nfc-parser/src/evaluate.py
code served (permissive licence) · get_code("7186374092dc5b49")
get_labeled_spans Not yet run ringos/nfc-parser/src/analysis/get_sibling.py
code served (permissive licence) · get_code("847edf90713bade6")
get_labeled_spans Not yet run ringos/nfc-parser/src/benepar/decode_chart.py
code served (permissive licence) · get_code("7f1d42a1ee822236")
get_multi_ngram_pattern_children Not yet run ringos/nfc-parser/src/analysis/get_pattern_constituent_pair.py
code served (permissive licence) · get_code("31b6275073ba81d5")
get_pattern_children Not yet run ringos/nfc-parser/src/analysis/get_pattern_constituent_pair.py
code served (permissive licence) · get_code("59e93379f77df089")
hebrew Not yet run ringos/nfc-parser/src/transliterate.py
code served (permissive licence) · get_code("98db1b220dd2ecb7")
load_compatitble_data Not yet run ringos/nfc-parser/src/analysis/get_pattern_constituent_pair.py
code served (permissive licence) · get_code("2ed97e38f7090303")
load_trees Not yet run ringos/nfc-parser/src/analysis/trees.py
code served (permissive licence) · get_code("79f8c62f9471a066")
load_trees_from_text Not yet run ringos/nfc-parser/src/analysis/trees.py
code served (permissive licence) · get_code("7392b7fad2fd08a6")
tree_from_str Not yet run ringos/nfc-parser/src/analysis/trees.py
code served (permissive licence) · get_code("1be51ebb6a7c65f5")

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 demonstrate that replacing an LSTM encoder with a self-attentive architecture can lead to improvements to a state-of-the-art discriminative constituency parser. The use of attention makes explicit the manner in which information is propagated between different locations in the sentence, which we use to both analyze our model and propose potential improvements. For example, we find that separating positional and content information in the encoder can lead to improved parsing accuracy. Additionally, we evaluate different approaches for lexical representation. Our parser achieves new state-of-the-art results for single models trained on the Penn Treebank: 93.55 F1 without the use of any external data, and 95.13 F1 when using pre-trained word representations. Our parser also outperforms the previous best-published accuracy figures on 8 of the 9 languages in the SPMRL dataset.

For agents

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

get_harvested_code_for_paper("1805.01052")
get_code_for_paper("1805.01052")
have("1805.01052")

Connect an agent — have() is free.