L'utilisation de schémas de discours pour améliorer la pertinence et la cohérence discursive dans le cadre du résumé automatique de blogs
Bibliographic record
Abstract
Question irrelevance and discourse incoherence are important and typical problems in multi-document summarization especially when dealing with informal and opinionated texts. To address these two issues, we propose a domain-independent query-based summarization approach for opinionated documents that uses intra-sentential discourse structures in the framework of schemata. We have developed a generic domain-independent schema-based approach that selects the most appropriate text schema to answer specific types of questions. The schemata define the content and the organization of summaries based on the discourse relations present in candidate sentences. To decide which candidate sentences should be included in the final summary and where, each sentence is automatically tagged with the rhetorical predicates it conveys and allowed to fill a slot of the schema. Finally post-schema heuristics that work at the inter-sentence level are used to improve coherence further. To validate our approach, we have built a system named BlogSum and have evaluated its performance for question relevance and coherence using two datasets: blogs and reviews. ROUGE scores show that our approach is effective at reducing question irrelevant sentences and a manual evaluation shows a significant improvement in question relevance and coherence compared to the original candidate list. These results indicate that the use of discourse relations combined with text schemas can effectively reduce question irrelevance and discourse incoherence even with informal and opinionated documents.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
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".