SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.15838 · ACL Findings · 2021

HySPA: Hybrid Span Generation for Scalable Text-to-Graph Extraction

Heng Ji, Liliang Ren, Chenkai Sun, Julia Hockenmaier

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 5 functions out of this paper's own repositories and ran 0 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
dwadden/dygiepp canonical 0 of 5
FunctionStatusWhere it lives
batch_identity Not yet run dwadden/dygiepp/dygie/models/shared.py
code served (permissive licence) · get_code("bbc5dc5142133340")
compute_f1 Not yet run dwadden/dygiepp/dygie/training/f1.py
code served (permissive licence) · get_code("fada67a6d1459131")
cumsum_shifted Not yet run dwadden/dygiepp/dygie/models/shared.py
code served (permissive licence) · get_code("7e0b52001d4f5323")
fields_to_batches Not yet run dwadden/dygiepp/dygie/models/shared.py
code served (permissive licence) · get_code("1b01fb249fb7cd71")
safe_div Not yet run dwadden/dygiepp/dygie/training/f1.py
code served (permissive licence) · get_code("ac4edaf53cf349f7")

Repositories linked to this paper

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

Abstract

Text-to-Graph extraction aims to automatically extract information graphs consisting of mentions and types from natural language texts. Existing approaches, such as table filling and pairwise scoring, have shown impressive performance on various information extraction tasks, but they are difficult to scale to datasets with longer input texts because of their secondorder space/time complexities with respect to the input length. In this work, we propose a Hybrid SPan GenerAtor (HySPA) that invertibly maps the information graph to an alternating sequence of nodes and edge types, and directly generates such sequences via a hybrid span decoder which can decode both the spans and the types recurrently in linear time and space complexities. Extensive experiments on the ACE05 dataset show that our approach also significantly outperforms state-ofthe-art on the joint entity and relation extraction task. 1

For agents

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

get_harvested_code_for_paper("2106.15838")
get_code_for_paper("2106.15838")
have("2106.15838")

Connect an agent — have() is free.