-
# title
A Unified Model for Extractive and Abstractive Summarization using Inconsistency Loss
# notes
用抽取式摘要辅助生成式摘要，最终给出生成式摘要的结果，打过了sota。
主要贡献点在于提出了一个inconsistency loss，用来衡量句子维度注意力和词维度注意力的不一致性。然…
-
### Deep Learning Simplified Repository (Proposing new issue)
:red_circle: **Project Title** : Automated Legal Document Summarizer
:red_circle: **Aim** : Create a model that can read and summarize…
-
# SARI & D-SARI
# JADOS
-
Great work. I intend to utilize it for my abstractive text summarization paper. Would you be able to upload the related examples? I am interested in evaluating semantic coverage, factuality, informati…
-
# URL
- https://arxiv.org/abs/2203.16804
# Affiliations
- Yixin Liu, N/A
- Pengfei Liu, N/A
- Dragomir Radev, N/A
- Graham Neubig, N/A
# Abstract
- Abstractive summarization models are commo…
-
Hi, thx for your nice work accepted by acl2020. I check out the link attached on paper `leveraging graph to improve abstractive multi-document summarization`. But I did not find code and result in thi…
-
Compared with the headmap showing in "A Neural Attention Model for Abstractive Sentence Summarization"(A.M.Rush), there are some problems here.
A heatmap should map the attention relationship betwe…
-
# URL
- https://arxiv.org/abs/2009.13312
# Affiliations
- Zheng Zhao, N/A
- Shay B. Cohen, N/A
- Bonnie Webber, N/A
# Abstract
- It is well-known that abstractive summaries are subject tohallu…
-
Hello,
Thank you for this fantastic code release! I'm currently running the abstractive summarization on input longer than 512, and changed the max_pos arg in train.py accordingly.
But I notic…
-
## ざっくり言うと
- seq2seqモデルに，元の文章をコピーするpointer-generatorネットワークを追加
- 同じ文章を繰り返さないようにcoverage機構を追加
- 文書要約の精度向上(先行研究が少ないのでSOTAかどうかの比較がしづらい)
- abstractive summarization
#### キーワード
- NLP
- document summa…