paper-with-me

Papers

A Decoding Algorithm for Length-Control Summarization Based on Directed Acyclic Transformers

2025-02-06 · Chenyang Huang, Hao Zhou, Cameron Jen, Kangjie Zheng, Osmar R. Zaïane, Lili Mou

Length-control summarization aims to condense long texts into a short one within a certain length limit. Previous approaches often use autoregressive (AR) models and treat the length requirement as a soft constraint, which may not always be satisfied. In this study, we propose a novel length-control decoding algorithm based on the Directed Acyclic Transformer (DAT). Our approach allows for multiple plausible sequence fragments and predicts a \emph{path} to connect them. In addition, we propose a Sequence Maximum a Posteriori (SeqMAP) decoding algorithm that marginalizes different possible paths and finds the most probable summary satisfying the length budget. Our algorithm is based on beam search, which further facilitates a reranker for performance improvement. Experimental results on the Gigaword and DUC2004 datasets demonstrate our state-of-the-art performance for length-control summarization.

📄 PDF Abstract BibTeX arXiv:2502.04535

Code (1)

MANGA-UOFA/DAT-LenC 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

Control-DAG: Constrained Decoding for Non-Autoregressive Directed Acyclic T5 using Weighted Finite State Automata

2024-04-10 · Jinghong Chen, Weizhe Lin, Jingbiao Mei, Bill Byrne

The Directed Acyclic Transformer is a fast non-autoregressive (NAR) model that performs well in Neural Machine Translation. Two issues prevent its application to general Natural Language Generation (NLG) tasks: frequent …

Machine TranslationText GenerationTranslation

Controlling Summarization Length Through EOS Token Weighting

2025-06-05 · Zeno Belligoli, Emmanouil Stergiadis, Eran Fainman, Ilya Gusev

Controlling the length of generated text can be crucial in various text-generation tasks, including summarization. Existing methods often require complex model alterations, limiting compatibility with pre-trained models.…

DecoderText Generation

LenAtten: An Effective Length Controlling Unit For Text Summarization

2021-06-01 · Findings (ACL) 2021 8 · Zhongyi Yu, Zhenghao Wu, Hao Zheng, Zhe XuanYuan 외

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,…

Text SummarizationWord Embeddings

Length-controllable Abstractive Summarization by Guiding with Summary Prototype

2020-01-21 · Itsumi Saito, Kyosuke Nishida, Kosuke Nishida, Atsushi Otsuka 외

We propose a new length-controllable abstractive summarization model. Recent state-of-the-art abstractive summarization models based on encoder-decoder models generate only one summary per source text. However, controlla…

Abstractive Text SummarizationDecoder

Controlling Output Length in Neural Encoder-Decoders

2016-09-30 · EMNLP 2016 11 · Yuta Kikuchi, Graham Neubig, Ryohei Sasano, Hiroya Takamura 외

Neural encoder-decoder models have shown great success in many sequence generation tasks. However, previous work has not investigated situations in which we would like to control the length of encoder-decoder outputs. Th…

DecoderText Summarization