REVIEW 8 cited by
Bottom-Up Abstractive Summarization
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original 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.
Forward citations
Cited by 8 Pith papers
-
TalkLess: Blending Extractive and Abstractive Speech Summarization for Editing Speech to Preserve Content and Style
TalkLess blends extractive and abstractive speech summarization through LLM candidate generation and a weighted scoring function, then converts transcript edits to audio with VoiceCraft, evaluating favorably against a...
-
Mixture Content Selection for Diverse Sequence Generation
A mixture-of-experts content selector that masks different input tokens for each generated sequence improves diversity and accuracy in question generation and summarization.
-
Earlier Isn't Always Better: Sub-aspect Analysis on Corpus and System Biases in Summarization
Across nine corpora, summarization bias toward position, importance, and diversity differs by domain and by system type, with news showing strong position bias and academic papers showing balance.
-
Exploring Domain Shift in Extractive Text Summarization
Publication source acts as a domain in extractive summarization, and domain tags plus meta-learning reduce, but do not eliminate, the performance drop on unseen news outlets.
-
Enriching and Controlling Global Semantics for Text Summarization
A normalizing-flow neural topic model plus control mechanism are added to Transformer summarizers to supply and regulate global semantics, with reported gains over prior models on five benchmarks.
-
Encoder-Agnostic Adaptation for Conditional Language Generation
Pseudo self attention, which injects learned encoder outputs into the self-attention of a pretrained language model, consistently outperforms prior encoder-agnostic adaptation methods on four conditional generation tasks.
-
Do Transformer Attention Heads Provide Transparency in Abstractive Summarization?
Analysis of transformer attention heads in abstractive summarization shows specialization in some heads and proposes a method to measure model reliance on learned attention distributions.
-
GeneSUM: Large Language Model-based Gene Summary Extraction
A two-stage LLM pipeline that selects key sentences from gene literature via GO annotations and fine-tunes Gemma-7B to generate gene summaries, reporting large ROUGE gains that may be inflated by training/evaluation overlap.
Discussion (0). Continue with ORCID to comment.