RefSum: Refactoring Neural Summarization

• URL: http://arxiv.org/abs/2104.07210v1
• Date: Thu, 15 Apr 2021 02:58:41 GMT
• Title: RefSum: Refactoring Neural Summarization
• Authors: Yixin Liu, Zi-Yi Dou, Pengfei Liu
• Abstract summary: We present a new framework Refactor that provides a unified view of text summarization and summaries combination. Our system can be directly used by other researchers as an off-the-shelf tool to achieve further performance improvements.
• Score: 16.148781118509255
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Although some recent works show potential complementarity among different state-of-the-art systems, few works try to investigate this problem in text summarization. Researchers in other areas commonly refer to the techniques of reranking or stacking to approach this problem. In this work, we highlight several limitations of previous methods, which motivates us to present a new framework Refactor that provides a unified view of text summarization and summaries combination. Experimentally, we perform a comprehensive evaluation that involves twenty-two base systems, four datasets, and three different application scenarios. Besides new state-of-the-art results on CNN/DailyMail dataset (46.18 ROUGE-1), we also elaborate on how our proposed method addresses the limitations of the traditional methods and the effectiveness of the Refactor model sheds light on insight for performance improvement. Our system can be directly used by other researchers as an off-the-shelf tool to achieve further performance improvements. We open-source all the code and provide a convenient interface to use it: https://github.com/yixinL7/Refactoring-Summarization. We have also made the demo of this work available at: http://explainaboard.nlpedia.ai/leaderboard/task-summ/index.php.

Related papers

• ReFeR: Improving Evaluation and Reasoning through Hierarchy of Models [12.035509884945789]
  We introduce a tuning-free framework called ReFeR, designed to evaluate generative outputs, including both text and images. We rigorously evaluate our framework, ReFeR, across four diverse evaluation tasks. Experiments on four reasoning tasks demonstrate superior collective reasoning abilities of the framework.
  arXiv  Detail & Related papers  (2024-07-16T08:25:26Z)
• Re-Reading Improves Reasoning in Large Language Models [87.46256176508376]
  We introduce a simple, yet general and effective prompting method, Re2, to enhance the reasoning capabilities of off-the-shelf Large Language Models (LLMs) Unlike most thought-eliciting prompting methods, such as Chain-of-Thought (CoT), Re2 shifts the focus to the input by processing questions twice, thereby enhancing the understanding process. We evaluate Re2 on extensive reasoning benchmarks across 14 datasets, spanning 112 experiments, to validate its effectiveness and generality.
  arXiv  Detail & Related papers  (2023-09-12T14:36:23Z)
• Balancing Lexical and Semantic Quality in Abstractive Summarization [0.38073142980733]
  We propose a novel training method in which a re-ranker balances the lexical and semantic quality. Experiments on the CNN/DailyMail and XSum datasets show that our method can estimate the meaning of summaries without seriously degrading the lexical aspect.
  arXiv  Detail & Related papers  (2023-05-17T02:18:31Z)
• Incorporating Relevance Feedback for Information-Seeking Retrieval using Few-Shot Document Re-Ranking [56.80065604034095]
  We introduce a kNN approach that re-ranks documents based on their similarity with the query and the documents the user considers relevant. To evaluate our different integration strategies, we transform four existing information retrieval datasets into the relevance feedback scenario.
  arXiv  Detail & Related papers  (2022-10-19T16:19:37Z)
• Neural Code Summarization: How Far Are We? [30.324396716447602]
  Deep learning techniques have been exploited to automatically generate summaries for given code snippets. In this paper, we conduct a systematic and in-depth analysis of five state-of-the-art neural source code summarization models.
  arXiv  Detail & Related papers  (2021-07-15T04:33:59Z)
• Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations [78.12377360145078]
  Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. In this paper, we first study how biases in the dataset affect existing methods. We show that current contrastive approaches work surprisingly well across: (i) object- versus scene-centric, (ii) uniform versus long-tailed and (iii) general versus domain-specific datasets.
  arXiv  Detail & Related papers  (2021-06-10T17:59:13Z)
• Omniscient Video Super-Resolution [84.46939510200461]
  In this paper, we propose an omniscient framework to not only utilize the preceding SR output, but also leverage the SR outputs from the present and future. Our method is superior to the state-of-the-art methods in objective metrics, subjective visual effects and complexity.
  arXiv  Detail & Related papers  (2021-03-29T15:09:53Z)
• Knowledge Graph Embedding with Atrous Convolution and Residual Learning [4.582412257655891]
  We propose a simple but effective atrous convolution based knowledge graph embedding method. It effectively increases feature interactions by using atrous convolutions. It addresses the original information forgotten issue and vanishing/exploding gradient issue.
  arXiv  Detail & Related papers  (2020-10-23T00:57:23Z)
• Learning from Context or Names? An Empirical Study on Neural Relation Extraction [112.06614505580501]
  We study the effect of two main information sources in text: textual context and entity mentions (names) We propose an entity-masked contrastive pre-training framework for relation extraction (RE) Our framework can improve the effectiveness and robustness of neural models in different RE scenarios.
  arXiv  Detail & Related papers  (2020-10-05T11:21:59Z)
• Scale-Localized Abstract Reasoning [79.00011351374869]
  We consider the abstract relational reasoning task, which is commonly used as an intelligence test. Since some patterns have spatial rationales, while others are only semantic, we propose a multi-scale architecture that processes each query in multiple resolutions. We show that indeed different rules are solved by different resolutions and a combined multi-scale approach outperforms the existing state of the art in this task on all benchmarks by 5-54%.
  arXiv  Detail & Related papers  (2020-09-20T10:37:29Z)

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.