Progress in summarizing long texts is inhibited by the lack of appropriate evaluation frameworks. A long summary that appropriately covers the facets of that text must also present a coherent narrative, but current automatic and human evaluation methods fail to identify gaps in coherence. In this work, we introduce SNaC, a narrative coherence evaluation framework for fine-grained annotations of long summaries. We develop a taxonomy of coherence errors in generated narrative summaries and collect span-level annotations for 6.6k sentences across 150 book and movie summaries. Our work provides the first characterization of coherence errors generated by state-of-the-art summarization models and a protocol for eliciting coherence judgments from crowdworkers. Furthermore, we show that the collected annotations allow us to benchmark past work in coherence modeling and train a strong classifier for automatically localizing coherence errors in generated summaries. Finally, our SNaC framework can support future work in long document summarization and coherence evaluation, including improved summarization modeling and post-hoc summary correction.
more »
« less
This content will become publicly available on June 17, 2025
AWESOME: GPU Memory-constrained Long Document Summarization using Memory Mechanism and Global Salient Content
Long document summarization systems are critical for domains with lengthy and jargonladen text, yet they present significant challenges to researchers and developers with limited computing resources. Existing solutions mainly focus on efficient attentions or divideand- conquer strategies. The former reduces theoretical time complexity, but is still memoryheavy. The latter methods sacrifice global context, leading to uninformative and incoherent summaries. This work aims to leverage the memory-efficient nature of divide-and-conquer methods while preserving global context. Concretely, our framework AWESOME uses two novel mechanisms: (1) External memory mechanisms track previously encoded document segments and their corresponding summaries, to enhance global document understanding and summary coherence. (2) Global salient content is further identified beforehand to augment each document segment to support its summarization. Extensive experiments on diverse genres of text, including government reports, meeting transcripts, screenplays, scientific papers, and novels, show that AWESOME produces summaries with improved informativeness, faithfulness, and coherence than competitive baselines on longer documents, while having a smaller GPU memory footprint.
more »
« less
- Award ID(s):
- 2046016
- NSF-PAR ID:
- 10518737
- Publisher / Repository:
- Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)
- Date Published:
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Proc. 2023 The Web Conf. (Ed.)Summarizing text-rich documents has been long studied in the literature, but most of the existing efforts have been made to summarize a static and predefined multi-document set. With the rapid development of online platforms for generating and distributing text-rich documents, there arises an urgent need for continuously summarizing dynamically evolving multi-document sets where the composition of documents and sets is changing over time. This is especially challenging as the summarization should be not only effective in incorporating relevant, novel, and distinctive information from each concurrent multi-document set, but also efficient in serving online applications. In this work, we propose a new summarization problem, Evolving Multi-Document sets stream Summarization (EMDS), and introduce a novel unsupervised algorithm PDSum with the idea of prototype-driven continuous summarization. PDSum builds a lightweight prototype of each multi-document set and exploits it to adapt to new documents while preserving accumulated knowledge from previous documents. To update new summaries, the most representative sentences for each multi-document set are extracted by measuring their similarities to the prototypes. A thorough evaluation with real multi-document sets streams demonstrates that PDSum outperforms state-of-the-art unsupervised multi-document summarization algorithms in EMDS in terms of relevance, novelty, and distinctiveness and is also robust to various evaluation settings.more » « less
-
Summarization datasets are often assembled either by scraping naturally occurring public-domain summaries -- which are nearly always in difficult-to-work-with technical domains -- or by using approximate heuristics to extract them from everyday text -- which frequently yields unfaithful summaries. In this work, we turn to a slower but more straightforward approach to developing summarization benchmark data: We hire highly-qualified contractors to read stories and write original summaries from scratch. To amortize reading time, we collect five summaries per document, with the first giving an overview and the subsequent four addressing specific questions. We use this protocol to collect SQuALITY, a dataset of question-focused summaries built on the same public-domain short stories as the multiple-choice dataset QuALITY (Pang et al., 2021). Experiments with state-of-the-art summarization systems show that our dataset is challenging and that existing automatic evaluation metrics are weak indicators of quality.more » « less
-
Extractive summarization is an important natural language processing approach used for document compression, improved reading comprehension, key phrase extraction, indexing, query set generation, and other analytics approaches. Extractive summarization has specific advantages over abstractive summarization in that it preserves style, specific text elements, and compound phrases that might be more directly associated with the text. In this article, the relative effectiveness of extractive summarization is considered on two widely different corpora: (1) a set of works of fiction (100 total, mainly novels) available from Project Gutenberg, and (2) a large set of news articles (3000) for which a ground truthed summarization (gold standard) is provided by the authors of the news articles. Both sets were evaluated using 5 different Python Sumy algorithms and compared to randomly-generated summarizations quantitatively. Two functional approaches to assessing the efficacy of summarization using a query set on both the original documents and their summaries, and using document classification on a 12-class set to compare among different summarization approaches, are introduced. The results, unsurprisingly, show considerable differences consistent with the different nature of these two data sets. The LSA and Luhn summarization approaches were most effective on the database of fiction, while all five summarization approaches were similarly effective on the database of articles. Overall, the Luhn approach was deemed the most generally relevant among those tested.more » « less
-
The quadratic computational and memory complexities of large Transformers have limited their scalability for long document summarization. In this paper, we propose HEPOS, a novel efficient encoder-decoder attention with head-wise positional strides to effectively pinpoint salient information from the source. We further conduct a systematic study of existing efficient self-attentions. Combined with HEPOS, we are able to process ten times more tokens than existing models that use full attentions. For evaluation, we present a new dataset, GOVREPORT, with significantly longer documents and summaries. Results show that our models produce significantly higher ROUGE scores than competitive comparisons, including new state-of-the-art results on PubMed. Human evaluation also shows that our models generate more informative summaries with fewer unfaithful errors.more » « less
