Challenge: Determinantal point processes (DPP) is one of the best performing techniques for extractive summarization.
Approach: They propose to combine determinantal point processes with surface indicators for effective identification of summary-worthy sentences.
Outcome: The determinantal point processes (DPP) framework is one of the best performing in summarization competitions.

Similar Papers

Improving the Similarity Measure of Determinantal Point Processes for Extractive Multi-Document Summarization (P19-1)

Copied to clipboard

Challenge: Despite the empirical success of multi-document summarization, most datasets remain small and the cost of hiring hu-1 is prohibitive.
Approach: They propose a novel method for extractive multi-document summarization that measures redundancy between a pair of sentences based on surface form and semantic information.
Outcome: The proposed method outperforms baseline methods on benchmark datasets and is particularly useful for documents created by multiple authors containing redundant yet lexically diverse expressions.
Principled Content Selection to Generate Diverse and Personalized Multi-Document Summaries (2025.acl-long)

Copied to clipboard

Challenge: Large language models exhibit the _”lost in the middle” phenomenon when they are unevenly attending to different parts of the provided context.
Approach: They propose principled content selection as a way to increase source coverage . they use determinantal point processes to prioritize diverse content .
Outcome: The proposed method improves source coverage on the DiverseSumm benchmark.
Contextualized Word Representations for Reading Comprehension (N18-2)

Copied to clipboard

Challenge: Reading comprehension (RC) is a high-level task in natural language understanding that requires reading a document and answering questions about its content.
Approach: They propose to provide a standard neural network for reading a document and answering a question about its content.
Outcome: The proposed model improves on the competitive SQuAD dataset by providing rich contextualized word representations and allowing it to choose between context-dependent and context-independent representations.
Frame Semantic-Enhanced Sentence Modeling for Sentence-level Extractive Text Summarization (2021.emnlp-main)

Copied to clipboard

Challenge: Sentence-level extractive text summarization is difficult to model the importance of sentences.
Approach: They propose a Frame Semantic-Enhanced Sentence Modeling for Extractive Summarization that leverages Frame semantics to model sentences from both intra-sentence level and inter-sentent level.
Outcome: The proposed model outperforms six state-of-the-art methods on two benchmark corpus datasets.
Better Highlighting: Creating Sub-Sentence Summary Highlights (2020.emnlp-main)

Copied to clipboard

Challenge: Abstractive summarizations are considered to be less reliable because they distort the original meaning and can be confusing for readers.
Approach: They propose a method to generate summary highlights that are understandable on their own to avoid confusion.
Outcome: The proposed method allows summaries to be understood in context and avoids misdirecting readers to false conclusions.
On Context Utilization in Summarization with Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Large language models excel in abstractive summarization tasks, delivering fluent and pertinent summaries.
Approach: They conduct the first comprehensive study on context utilization and position bias in summarization.
Outcome: The proposed benchmark compares two methods to alleviate position bias in summarization tasks.
Proceedings of the 2nd Workshop on New Frontiers in Summarization (D19-54)

Copied to clipboard

Challenge: EMNLP 2017 is a workshop on enhancing natural language processing's ability to produce concise, fluent summaries.
Approach: the workshop provides a forum for cross-fertilization of ideas towards automatic summarization . four invited speakers will be present at the workshop .
Outcome: the workshop aims to provide a forum for cross-fertilization of ideas towards automatic summarization.
At Which Level Should We Extract? An Empirical Analysis on Extractive Document Summarization (2020.coling-main)

Copied to clipboard

Challenge: Existing studies have shown that extracting sentences at sentence level is not the best solution for document summarization.
Approach: They propose to extract sub-sentential units based on the constituency parsing tree and a neural extractive model which leverages the sub-sensential information and extracts them.
Outcome: The proposed model performs competitively compared to full sentence extraction under automatic and human evaluations.
Multi-doc Hybrid Summarization via Salient Representation Learning (2023.acl-industry)

Copied to clipboard

Challenge: Multi-document summarization is gaining more and more attention . extractive multi-doc approaches intend to directly extract key facts from multiple sources .
Approach: They propose a multi-document hybrid summarization approach that generates a human-readable summary and extracts corresponding key evidences based on multi-doc inputs.
Outcome: The proposed method generates a human-readable summary and extracts key evidences based on multi-doc inputs.
Summary Level Training of Sentence Rewriting for Abstractive Summarization (D19-54)

Copied to clipboard

Challenge: Existing models rely on sentence-level rewards or suboptimal labels to achieve summary-level ROUGE scores.
Approach: They propose a model that extracts salient sentences from a document and paraphrases them to generate a summary.
Outcome: The proposed model improves on CNN/Daily Mail and New York Times datasets.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations