LenAtten: An Effective Length Controlling Unit For Text Summarization

• URL: http://arxiv.org/abs/2106.00316v1
• Date: Tue, 1 Jun 2021 08:45:41 GMT
• Title: LenAtten: An Effective Length Controlling Unit For Text Summarization
• Authors: Zhongyi Yu, Zhenghao Wu, Hao Zheng, Zhe XuanYuan, Jefferson Fong, Weifeng Su
• Abstract summary: Fixed length summarization aims at generating summaries with a preset number of words or characters. Most recent researches incorporate length information with word embeddings as the input to the recurrent decoding unit. We present an effective length controlling unit Length Attention (LenAtten) to break this trade-off.
• Score: 5.554982420311913
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fixed length summarization aims at generating summaries with a preset number of words or characters. Most recent researches incorporate length information with word embeddings as the input to the recurrent decoding unit, causing a compromise between length controllability and summary quality. In this work, we present an effective length controlling unit Length Attention (LenAtten) to break this trade-off. Experimental results show that LenAtten not only brings improvements in length controllability and ROGUE scores but also has great generalization ability. In the task of generating a summary with the target length, our model is 732 times better than the best-performing length controllable summarizer in length controllability on the CNN/Daily Mail dataset.

Related papers

• Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost [4.299153274884264]
  This paper analyzes the impact of output lengths on large language models (LLMs) inference pipelines. It proposes novel metrics to evaluate them in terms of textitcorrect conciseness. It also examines the impact of controlling output length through a refined prompt engineering strategy, Constrained-CoT.
  arXiv  Detail & Related papers  (2024-07-29T09:21:52Z)
• Improving Citation Text Generation: Overcoming Limitations in Length Control [10.555859097367286]
  Key challenge in citation text generation is that the length of generated text often differs from the length of the target, lowering the quality of the generation. In this work, we present an in-depth study of the limitations of predicting scientific citation text length and explore the use of estimates of desired length.
  arXiv  Detail & Related papers  (2024-07-20T22:10:37Z)
• SirLLM: Streaming Infinite Retentive LLM [74.40196814292426]
  Large Language Models (LLMs) process inputs of any length and maintain a degree of memory. Recent efforts have employed streaming inputs to alleviate the pressure of excessively long text inputs. We introduce Streaming Infinite Retentive LLM (SirLLM), which allows LLMs to maintain longer memory during infinite-length dialogues.
  arXiv  Detail & Related papers  (2024-05-21T06:37:03Z)
• LongAlign: A Recipe for Long Context Alignment of Large Language Models [61.85923382850057]
  LongAlign is a recipe of the instruction data, training, and evaluation for long context alignment. We construct a long instruction-following dataset using Self-Instruct. We adopt the packing and sorted strategies to speed up supervised fine-tuning on data with varied length distributions.
  arXiv  Detail & Related papers  (2024-01-31T18:29:39Z)
• Effective Long-Context Scaling of Foundation Models [90.57254298730923]
  We present a series of long-context LLMs that support effective context windows of up to 32,768 tokens. Our models achieve consistent improvements on most regular tasks and significant improvements on long-context tasks over Llama 2.
  arXiv  Detail & Related papers  (2023-09-27T21:41:49Z)
• Prompt-Based Length Controlled Generation with Reinforcement Learning [48.49553921757085]
  We propose a prompt-based length control method to achieve high-accuracy length controlled generation. We adopt reinforcement learning with the reward signal given by either trainable or rule-based reward models. Our method significantly improves the accuracy of prompt-based length control for summarization task on popular datasets like CNNDM and NYT.
  arXiv  Detail & Related papers  (2023-08-23T09:43:10Z)
• Summarization with Precise Length Control [23.688834410051]
  We present a framework to generate summaries with precisely the specified number of tokens or sentences. We jointly train the models to predict the lengths, so our model can generate summaries with optimal length.
  arXiv  Detail & Related papers  (2023-05-09T04:45:24Z)
• MACSum: Controllable Summarization with Mixed Attributes [56.685735509260276]
  MACSum is the first human-annotated summarization dataset for controlling mixed attributes. We propose two simple and effective parameter-efficient approaches for the new task of mixed controllable summarization.
  arXiv  Detail & Related papers  (2022-11-09T17:17:37Z)
• A Focused Study on Sequence Length for Dialogue Summarization [68.73335643440957]
  We analyze the length differences between existing models' outputs and the corresponding human references. We identify salient features for summary length prediction by comparing different model settings. Third, we experiment with a length-aware summarizer and show notable improvement on existing models if summary length can be well incorporated.
  arXiv  Detail & Related papers  (2022-09-24T02:49:48Z)
• Reinforced Abstractive Summarization with Adaptive Length Controlling [12.793451906532223]
  Controllable summarization, especially of the length, is an important issue for some practical applications. We propose an textbfAdaptive textbfLength textbfControlling textbfOptimization (textbfALCO) method to leverage two-stage abstractive summarization model.
  arXiv  Detail & Related papers  (2021-12-14T16:48:47Z)
• Length-controllable Abstractive Summarization by Guiding with Summary Prototype [27.094797760775297]
  We propose a new length-controllable abstractive summarization model. Our model generates a summary in two steps. Experiments with the CNN/Daily Mail dataset and the NEWSROOM dataset show that our model outperformed previous models in length-controlled settings.
  arXiv  Detail & Related papers  (2020-01-21T04:01:58Z)

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.