--- title: "Frame Semantic-Enhanced Sentence Modeling for — Guan 2021" description: "The paper addresses sentence-level extractive summarization, where a system picks the document sentences that best convey its main content." authors: ["Yong Guan", "Shaoru Guo", "Ru Li", "Xiaoli Li", "Hongye Tan"] year: 2021 venue: "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing" source: "https://aclanthology.org/2021.emnlp-main.331/" doi: "10.18653/v1/2021.emnlp-main.331" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/papers/guan-2021-frame-semantic-enhanced-sentence-modeling/" --- [Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/guan-2021-frame-semantic-enhanced-sentence-modeling/) [home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2021](https://md.research.elamur.ai/free/papers/2021/page/2/) / Frame Semantic-Enhanced Sentence Modeling for Sentence-level Extractive Text Summarization # Frame Semantic-Enhanced Sentence Modeling for Sentence-level Extractive Text Summarization **Authors:** [Yong Guan](https://md.research.elamur.ai/free/authors/yong-guan/), [Shaoru Guo](https://md.research.elamur.ai/free/authors/shaoru-guo/), [Ru Li](https://md.research.elamur.ai/free/authors/ru-li/), [Xiaoli Li](https://md.research.elamur.ai/free/authors/xiaoli-li/), [Hongye Tan](https://md.research.elamur.ai/free/authors/hongye-tan/) · **Year:** 2021 · **Venue:** Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2021.emnlp-main.331/) · [PDF](https://aclanthology.org/2021.emnlp-main.331.pdf) · [DOI 10.18653/v1/2021.emnlp-main.331](https://doi.org/10.18653/v1/2021.emnlp-main.331) · [OpenAlex](https://openalex.org/W3211389291) **Citations:** 8 citations (openalex-snapshot · 2026-10-14) · [15](#cited-by) in our library, of the 140673 papers whose bibliographies we read ## Summary The paper addresses sentence-level extractive summarization, where a system picks the document sentences that best convey its main content. The authors argue that sentences are usually modeled without explicit semantic structure, so the model can miss links between sentences that describe the same situation in different words. Their solution draws on frame semantics, the FrameNet-style idea that words evoke frames (e.g., Causation, Kinship, Taking_time) whose frame elements (such as Actor, Effect, Time) describe the participants. Sentences are first encoded with BERT, using a CLS token per sentence. The model also encodes frames using their textual definitions. All of this is placed in a graph module with three node types: sentences, frames and frame elements. Attention within a sentence (intra) and across sentences (inter) spreads frame information between related sentences before each sentence is scored for selection. Experiments use news data, including CNN/Daily Mail. The work matters because it shows that structured lexical-semantic resources can strengthen pretrained encoders for summarization. ## Key points - Venue: EMNLP 2021 Proceedings, pages 4045–4052; first author Yong Guan. - Graph nodes are sentence nodes (V_sen), frame nodes (V_f) and frame element nodes (V_fe). Sentence representations come from a BERT document encoder. - Frame representations are built from their FrameNet definitions. For example, Causation is defined roughly as "a cause causes an effect." - Intra-sentence and inter-sentence attention model frame-to-frame relations. These relations connect, for instance, an article's lead sentences with a later sentence that restates the same event. - The motivating example comes from CNN/Daily Mail. The extracted text available here did not include exact ROUGE scores or the full dataset list, so specific numbers are omitted. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* Fields: [Linguistics & languages](https://md.research.elamur.ai/free/shelves/linguistics/) ## Cited by Cited by 15 papers of our library cite it (of the 140673 whose bibliographies we read); 1 of them have a page here, 14 not yet. - [System Report for CCL25-Eval Task 4: Prompting, Scheduling, and Arbitration Strategies for Chinese Factivity Inference](https://md.research.elamur.ai/free/papers/liu-2025-system-report-ccl25-eval-task/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{guan2021frame, title = {{Frame Semantic-Enhanced Sentence Modeling for Sentence-level Extractive Text Summarization}}, author = {Guan, Yong and Guo, Shaoru and Li, Ru and Li, Xiaoli and Tan, Hongye}, booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing}, year = {2021}, doi = {10.18653/v1/2021.emnlp-main.331}, url = {https://doi.org/10.18653/v1/2021.emnlp-main.331} } ``` - [← previous Focus on what matters: Applying Discourse Coherence Theory to Cross Document Coreference](https://md.research.elamur.ai/free/papers/held-2021-focus-what-matters-applying-discourse/) - [next → From polysemy to semantic change: remarks on the lexeme miṣwà in Biblical and Mishnaic Hebrew](https://md.research.elamur.ai/free/papers/hbo-2021-vergari-polysemy-semantic-change-remarks-lexeme/) - [↑ back to papers of 2021](https://md.research.elamur.ai/free/papers/2021/page/2/)