MétaCan
Menu
Back to cohort
Record W2097120204

Towards Robust Abstractive Multi-Document Summarization: A Caseframe Analysis of Centrality and Domain

2013· article· en· W2097120204 on OpenAlexaff
Jackie Chi Kit Cheung, Gerald Penn

Bibliographic record

VenueMeeting of the Association for Computational Linguistics · 2013
Typearticle
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsAutomatic summarizationCentralityComputer scienceRedundancy (engineering)SentenceNatural language processingInformation retrievalDomain (mathematical analysis)Artificial intelligenceAbstractionMulti-document summarization
DOInot available

Abstract

fetched live from OpenAlex

In automatic summarization, centrality is the notion that a summary should contain the core parts of the source text. Current systems use centrality, along with redundancy avoidance and some sentence compression, to produce mostly extractive summaries. In this paper, we investigate how summarization can advance past this paradigm towards robust abstraction by making greater use of the domain of the source text. We conduct a series of studies comparing human-written model summaries to system summaries at the semantic level of caseframes. We show that model summaries (1) are more abstractive and make use of more sentence aggregation, (2) do not contain as many topical caseframes as system summaries, and (3) cannot be reconstructed solely from the source text, but can be if texts from in-domain documents are added. These results suggest that substantial improvements are unlikely to result from better optimizing centrality-based criteria, but rather more domain knowledge is needed.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.004
metaresearch head score (Gemma)0.022
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.005
Threshold uncertainty score0.019

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0040.022
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0050.003
Science and technology studies0.0010.001
Scholarly communication0.0030.005
Open science0.0010.002
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.021
GPT teacher head0.268
Teacher spread0.247 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations29
Published2013
Admission routes1
Has abstractyes

Explore more

Same venueMeeting of the Association for Computational LinguisticsSame topicTopic ModelingFrench-language works237,207