SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1808.10792 · 2018

Bottom-Up Abstractive Summarization

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 6 functions out of this paper's own repositories and ran 5 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
sebastianGehrmann/bottom-up-summary canonical 5 of 6
FunctionStatusWhere it lives
compile_substring Ran sebastianGehrmann/bottom-up-summary/preprocess_copy.py
code served (permissive licence) · get_code("17692adbeaedd54d")
format_json Ran sebastianGehrmann/bottom-up-summary/preprocess_copy.py
code served (permissive licence) · get_code("1489df8b19518049")
get_sents Ran sebastianGehrmann/bottom-up-summary/prediction_to_text.py
code served (permissive licence) · get_code("6b890c90cd5ecfa6")
get_three Ran sebastianGehrmann/bottom-up-summary/prediction_to_text.py
code served (permissive licence) · get_code("20cb63f02f26da92")
splits Ran sebastianGehrmann/bottom-up-summary/preprocess_copy.py
code served (permissive licence) · get_code("12d9e8622f8706e2")
get_phrases Not yet run sebastianGehrmann/bottom-up-summary/prediction_to_text.py
code served (permissive licence) · get_code("e378ee2b26dd8ebc")

Repositories linked to this paper

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

Abstract

Neural network-based methods for abstractive summarization produce outputs that are more fluent than other techniques, but which can be poor at content selection. This work proposes a simple technique for addressing this issue: use a data-efficient content selector to over-determine phrases in a source document that should be part of the summary. We use this selector as a bottom-up attention step to constrain the model to likely phrases. We show that this approach improves the ability to compress text, while still generating fluent summaries. This two-step process is both simpler and higher performing than other end-to-end content selection models, leading to significant improvements on ROUGE for both the CNN-DM and NYT corpus. Furthermore, the content selector can be trained with as little as 1,000 sentences, making it easy to transfer a trained summarizer to a new domain.

For agents

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

get_harvested_code_for_paper("1808.10792")
get_code_for_paper("1808.10792")
have("1808.10792")

Connect an agent — have() is free.