An Empirical Survey on Long Document Summarization: Datasets, Models, and Metrics

Koh, Huan Yee; Ju, Jiaxin; Liu, Ming; Pan, Shirui

doi:10.1145/3545176

Cited by 45 publications

(23 citation statements)

References 120 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We can cite the UDEG model (Jeong et al , 2021). This one uses an abstract automatic summarization system to summarize documents (Lu and Conrad, 2012; Koh et al , 2022). Its abstraction capacity allows it to introduce words into summaries that are not present in original documents.…”

Section: Related Workmentioning

confidence: 99%

LoGE: an unsupervised local-global document extension generation in information retrieval for long documents

Ayoub,

Rodrigues,

Travers

2023

IJWIS

View full text Add to dashboard Cite

Purpose This paper aims to manage the word gap in information retrieval (IR) especially for long documents belonging to specific domains. In fact, with the continuous growth of text data that modern IR systems have to manage, existing solutions are needed to efficiently find the best set of documents for a given request. The words used to describe a query can differ from those used in related documents. Despite meaning closeness, nonoverlapping words are challenging for IR systems. This word gap becomes significant for long documents from specific domains. Design/methodology/approach To generate new words for a document, a deep learning (DL) masked language model is used to infer related words. Used DL models are pretrained on massive text data and carry common or specific domain knowledge to propose a better document representation. Findings The authors evaluate the approach of this study on specific IR domains with long documents to show the genericity of the proposed model and achieve encouraging results. Originality/value In this paper, to the best of the authors’ knowledge, an original unsupervised and modular IR system based on recent DL methods is introduced.

show abstract

Section: Related Workmentioning

confidence: 99%

LoGE: an unsupervised local-global document extension generation in information retrieval for long documents

Ayoub,

Rodrigues,

Travers

2023

IJWIS

View full text Add to dashboard Cite

show abstract

“…While there do exist more powerful dialogue summarization models such as DialogLM [29] and Summ [28], we use the BART (Bidirectional and Auto-Regressive Transformers) model [12] due to its speed and high performance in long document summarization tasks [11]. In addition, there has been previous research in assessing different topic segmentation methods on the BART model, so this allows us to evaluate our techniques.…”

Section: Bart Model For Meeting Summarizationmentioning

confidence: 99%

“…Extractive summarization techniques locate the most important phrases and sentences from the input transcript and concatenate them to form a concise summary. However, the summaries generated by these techniques are usually awkward to read because of the forceful concatenation of unrelated sentences [11]. Abstractive summarization techniques focus more on understanding the overall meaning of a transcript and then generating a concise summary based on the entire text.…”

Section: Introductionmentioning

confidence: 99%

Action-Item-Driven Summarization of Long Meeting Transcripts

Golia,

Kalita

2023

Proceedings of the 2023 7th International Conference on Natural Language Processing and Information Retrieval

View full text Add to dashboard Cite

The increased prevalence of online meetings has significantly enhanced the practicality of a model that can automatically generate the summary of a given meeting. This paper introduces a novel and effective approach to automate the generation of meeting summaries. Current approaches to this problem generate general and basic summaries, considering the meeting simply as a long dialogue. However, our novel algorithms can generate abstractive meeting summaries that are driven by the action items contained in the meeting transcript. This is done by recursively generating summaries and employing our action-item extraction algorithm for each section of the meeting in parallel. All of these sectional summaries are then combined and summarized together to create a coherent and action-item-driven summary. In addition, this paper introduces three novel methods for dividing up long transcripts into topic-based sections to improve the time efficiency of our algorithm, as well as to resolve the issue of large language models (LLMs) forgetting long-term dependencies. Our pipeline achieved a BERTScore of 64.98 across the AMI corpus, which is an approximately 4.98% increase from the current state-of-the-art result produced by a fine-tuned BART (Bidirectional and Auto-Regressive Transformers) model. 1

show abstract

“…Performing salient content selection is a nature way to alleviate the problem and it has been widely used in other fields [15]. For example, Gehrmann et al [10] apply extract-abstract methods to improve summary performance.…”

Section: Query Reformulation and Content Selectionmentioning

confidence: 99%

Boosting legal case retrieval by query content selection with large language models

Zhou,

Huang,

2023

Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia P

View full text Add to dashboard Cite

Legal case retrieval, which aims to retrieve relevant cases to a given query case, benefits judgment justice and attracts increasing attention. Unlike generic retrieval queries, legal case queries are typically long and the definition of relevance is closely related to legal-specific elements. Therefore, legal case queries may suffer from noise and sparsity of salient content, which hinders retrieval models from perceiving correct information in a query. While previous studies have paid attention to improving retrieval models and understanding relevance judgments, we focus on enhancing legal case retrieval by utilizing the salient content in legal case queries. We first annotate the salient content in queries manually and investigate how sparse and dense retrieval models attend to those content. Then we experiment with various query content selection methods utilizing large language models (LLMs) to extract or summarize salient content and incorporate it into the retrieval models. Experimental results show that reformulating long queries using LLMs improves the performance of both sparse and dense models in legal case retrieval. CCS CONCEPTS• Information systems → Retrieval models and ranking.

show abstract

An Empirical Survey on Long Document Summarization: Datasets, Models, and Metrics

Cited by 45 publications

References 120 publications

LoGE: an unsupervised local-global document extension generation in information retrieval for long documents

LoGE: an unsupervised local-global document extension generation in information retrieval for long documents

Action-Item-Driven Summarization of Long Meeting Transcripts

Boosting legal case retrieval by query content selection with large language models

Contact Info

Product

Resources

About