A Neural Attention Model for Abstractive Sentence Summarization
read the original abstract
Summarization based on text extraction is inherently limited, but generation-style abstractive methods have proven challenging to build. In this work, we propose a fully data-driven approach to abstractive sentence summarization. Our method utilizes a local attention-based model that generates each word of the summary conditioned on the input sentence. While the model is structurally simple, it can easily be trained end-to-end and scales to a large amount of training data. The model shows significant performance gains on the DUC-2004 shared task compared with several strong baselines.
This paper has not been read by Pith yet.
Forward citations
Cited by 5 Pith papers
-
Learning to summarize from human feedback
Reinforcement learning on a reward model trained from human summary comparisons produces summaries humans prefer over supervised fine-tuning or human references on TL;DR and transfers to CNN/DM.
-
CodeBERT: A Pre-Trained Model for Programming and Natural Languages
CodeBERT pre-trains a bimodal model on code and text pairs plus unimodal data to achieve state-of-the-art results on natural language code search and code documentation generation.
-
CTRL: A Conditional Transformer Language Model for Controllable Generation
CTRL is a large conditional transformer language model that uses naturally occurring control codes to steer text generation style and content.
-
Ranking sentences from product description & bullets for better search
Two RL-based extractive summarization models rank sentences from product fields by leveraging titles and click-through logs to improve search relevance.
-
Saliency Maps Generation for Automatic Text Summarization
LRP saliency maps on a seq2seq summarization model sometimes reflect actual input feature usage and sometimes do not, requiring quantitative counterfactual validation.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.