RECORD
Summarizing Text on Any Aspects: A Knowledge-Informed Weakly-Supervised Approach
Computation and Language · Submitted 14 Oct 2020
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Experiments show our approach achieves performance boosts on summarizing both real and synthetic documents given pre-defined or arbitrary aspects.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Given a document and a target aspect (e.g., a topic of interest), aspect-based abstractive summarization attempts to generate a summary with respect to the aspect. Previous studies usually assume a small pre-defined set of aspects and fall short of summarizing on other diverse topics. In this work, we study summarizing on arbitrary aspects relevant to the document, which significantly expands the application of the task in practice. Due to the lack of supervision data, we develop a new weak supervision construction method and an aspect modeling scheme, both of which integrate rich external knowledge sources such as ConceptNet and Wikipedia. Experiments show our approach achieves performance boosts on summarizing both real and synthetic documents given pre-defined or arbitrary aspects.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Given a document and a target aspect (e.g., a topic of interest), aspect-based abstractive summarization attempts to generate a summary with respect to the aspect. | background 1.00 | 0.05 | 0.03 | asserted 0.98 |
| s1 | Previous studies usually assume a small pre-defined set of aspects and fall short of summarizing on other diverse topics. | gap 0.88 | 0.03 | 0.03 | asserted 1.00 |
| s2 | In this work, we study summarizing on arbitrary aspects relevant to the document, which significantly expands the application of the task in practice. | contribution 0.99 | 0.55 | 0.13 | asserted 0.99 |
| s3 | Due to the lack of supervision data, we develop a new weak supervision construction method and an aspect modeling scheme, both of which integrate rich external knowledge sources such as ConceptNet and Wikipedia. | method 0.86 | 0.94 | 0.06 | asserted 1.00 |
| s4 | Experiments show our approach achieves performance boosts on summarizing both real and synthetic documents given pre-defined or arbitrary aspects. | result 1.00 | 0.96 | 0.83 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v2
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Given a document and a target aspect (e.g., a topic of interest), aspect-based abstractive summarization attempts to generate a summary with respect to the aspect. Previous studies usually assume a small pre-defined set of aspects and fall short of summarizing on other diverse topics. In this work, we study summarizing on arbitrary aspects relevant to the document, which significantly expands the application of the task in practice. Due to the lack of supervision data, we develop a new weak supervision construction method and an aspect modeling scheme, both of which integrate rich external knowledge sources such as ConceptNet and Wikipedia. Experiments show our approach achieves performance boosts on summarizing both real and synthetic documents given pre-defined or arbitrary aspects.
Human review
How the literature uses it
1 arXiv paper cite this in 1 sentence
Papers citing it
Cites it as background 1 paper
-
[ref] and [ref] address QFS by prepending the query or aspect to the input document and fine-tuning pre-trained models in an end-to-end manner.
IDEAL: Leveraging Infinite and Dynamic Characterizations of Large Language Models for Query-focused Summarization · Query-focused Summarization · 0.95
What it cites · 3 sentences without a confident label
Uses the method or tool of 1 paper
-
We use the CNN/DailyMail-pretrained BART [ref] provided by Fairseq [ref] as our base summarization model, and fine-tune with our approach implemented using Texar [ref] .
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension · Experiments · 1.00
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.