A Second Look on BASS -- Boosting Abstractive Summarization with Unified Semantic Graphs -- A Replication Study

• URL: http://arxiv.org/abs/2403.02930v2
• Date: Mon, 25 Mar 2024 12:07:13 GMT
• Title: A Second Look on BASS -- Boosting Abstractive Summarization with Unified Semantic Graphs -- A Replication Study
• Authors: Osman Alperen Koraş, Jörg Schlötterer, Christin Seifert,
• Abstract summary: We present a detailed replication study of the BASS framework, an abstractive summarization system based on the notion of Unified Semantic Graphs. Our investigation includes challenges in replicating key components and an ablation study to systematically isolate error sources rooted in replicating novel components.
• Score: 2.592470112714595
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present a detailed replication study of the BASS framework, an abstractive summarization system based on the notion of Unified Semantic Graphs. Our investigation includes challenges in replicating key components and an ablation study to systematically isolate error sources rooted in replicating novel components. Our findings reveal discrepancies in performance compared to the original work. We highlight the significance of paying careful attention even to reasonably omitted details for replicating advanced frameworks like BASS, and emphasize key practices for writing replicable papers.

Related papers

• Inducing Causal Structure for Abstractive Text Summarization [76.1000380429553]
  We introduce a Structural Causal Model (SCM) to induce the underlying causal structure of the summarization data. We propose a Causality Inspired Sequence-to-Sequence model (CI-Seq2Seq) to learn the causal representations that can mimic the causal factors. Experimental results on two widely used text summarization datasets demonstrate the advantages of our approach.
  arXiv  Detail & Related papers  (2023-08-24T16:06:36Z)
• PROM: A Phrase-level Copying Mechanism with Pre-training for Abstractive Summarization [139.242907155883]
  This work proposes PROM, a new PhRase-level cOpying Mechanism that enhances attention on n-grams. PROM adds an indicator layer to explicitly pick up tokens in n-gram that can be copied from the source, and calculates an auxiliary loss for the copying prediction. In zero-shot setting, PROM is utilized in the self-supervised pre-training on raw corpora and provides new general baselines on a wide range of summarization datasets.
  arXiv  Detail & Related papers  (2023-05-11T08:29:05Z)
• Replication in Requirements Engineering: the NLP for RE Case [9.251594928574892]
  Natural language processing (NLP) techniques have been widely applied in the requirements engineering (RE) field. Re replication is hampered by several factors, including the context specificity of the studies. We propose a new artifact, referred to as ID-Card, whose goal is to provide a structured summary of research papers emphasizing replication-relevant information.
  arXiv  Detail & Related papers  (2023-04-20T12:45:21Z)
• An Empirical Investigation of Representation Learning for Imitation [76.48784376425911]
  Recent work in vision, reinforcement learning, and NLP has shown that auxiliary representation learning objectives can reduce the need for large amounts of expensive, task-specific data. We propose a modular framework for constructing representation learning algorithms, then use our framework to evaluate the utility of representation learning for imitation.
  arXiv  Detail & Related papers  (2022-05-16T11:23:42Z)
• RetrievalSum: A Retrieval Enhanced Framework for Abstractive Summarization [25.434558112121778]
  We propose a novel retrieval enhanced abstractive summarization framework consisting of a dense Retriever and a Summarizer. We validate our method on a wide range of summarization datasets across multiple domains and two backbone models: BERT and BART. Results show that our framework obtains significant improvement by 1.384.66 in ROUGE-1 score when compared with the powerful pre-trained models.
  arXiv  Detail & Related papers  (2021-09-16T12:52:48Z)
• BASS: Boosting Abstractive Summarization with Unified Semantic Graph [49.48925904426591]
  BASS is a framework for Boosting Abstractive Summarization based on a unified Semantic graph. A graph-based encoder-decoder model is proposed to improve both the document representation and summary generation process. Empirical results show that the proposed architecture brings substantial improvements for both long-document and multi-document summarization tasks.
  arXiv  Detail & Related papers  (2021-05-25T16:20:48Z)
• EASE: Extractive-Abstractive Summarization with Explanations [18.046254486733186]
  We present an explainable summarization system based on the Information Bottleneck principle. Inspired by previous research that humans use a two-stage framework to summarize long documents, our framework first extracts a pre-defined amount of evidence spans as explanations. We show that explanations from our framework are more relevant than simple baselines, without substantially sacrificing the quality of the generated summary.
  arXiv  Detail & Related papers  (2021-05-14T17:45:06Z)
• Semantic Extractor-Paraphraser based Abstractive Summarization [40.05739160204135]
  We propose an extractor-paraphraser based abstractive summarization system that exploits semantic overlap. Our model outperforms the state-of-the-art baselines in terms of ROUGE, METEOR and word similarity (WMS)
  arXiv  Detail & Related papers  (2021-05-04T05:24:28Z)
• Contextualized Rewriting for Text Summarization [10.666547385992935]
  We formalized rewriting as a seq2seq problem with group alignments. Results show that our approach significantly outperforms non-contextualized rewriting systems.
  arXiv  Detail & Related papers  (2021-01-31T05:35:57Z)
• Multi-Fact Correction in Abstractive Text Summarization [98.27031108197944]
  Span-Fact is a suite of two factual correction models that leverages knowledge learned from question answering models to make corrections in system-generated summaries via span selection. Our models employ single or multi-masking strategies to either iteratively or auto-regressively replace entities in order to ensure semantic consistency w.r.t. the source text. Experiments show that our models significantly boost the factual consistency of system-generated summaries without sacrificing summary quality in terms of both automatic metrics and human evaluation.
  arXiv  Detail & Related papers  (2020-10-06T02:51:02Z)
• Salience Estimation with Multi-Attention Learning for Abstractive Text Summarization [86.45110800123216]
  In the task of text summarization, salience estimation for words, phrases or sentences is a critical component. We propose a Multi-Attention Learning framework which contains two new attention learning components for salience estimation.
  arXiv  Detail & Related papers  (2020-04-07T02:38:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.