Sequence Level Contrastive Learning for Text Summarization

نویسندگان

چکیده

Contrastive learning models have achieved great success in unsupervised visual representation learning, which maximize the similarities between feature representations of different views same image, while minimize images. In text summarization, output summary is a shorter form input document and they similar meanings. this paper, we propose contrastive model for supervised abstractive where view document, its gold generated summaries as mean them during training. We improve over strong sequence-to-sequence generation (i.e., BART) on three summarization datasets. Human evaluation also shows that our achieves better faithfulness ratings compared to counterpart without objectives. release code at https://github.com/xssstory/SeqCo.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Sequence-to-Sequence RNNs for Text Summarization

In this work, we cast text summarization as a sequence-to-sequence problem and apply the attentional encoder-decoder RNN that has been shown to be successful for Machine Translation (Bahdanau et al. (2014)). Our experiments show that the proposed architecture significantly outperforms the state-of-the art model of Rush et al. (2015) on the Gigaword dataset without any additional tuning. We also...

متن کامل

Contrastive Summarization

With the continual growth of the internet as a source of information, where a great amount of data is being uploaded every minute, the need for data compression is getting more important. This applies also to textual documents. As the amount of data grows, the probability of multiple similar documents is increasing. One way how to deal with this is to reduce the text, i.e. to use document summa...

متن کامل

Interactive Learning for Text Summarization

This paper describes a query-relevant text summary system based on interactive learning. The system proceeds in two steps, it first extracts the most relevant sentences of a document with regard to a user query using a classical tf-idf term weighting scheme, it then learns the user feedback in order to improve its performances. Learning operates at two levels: query expansion and sentence scoring.

متن کامل

Biogeography-Based Optimization Algorithm for Automatic Extractive Text Summarization

    Given the increasing number of documents, sites, online sources, and the users’ desire to quickly access information, automatic textual summarization has caught the attention of many researchers in this field. Researchers have presented different methods for text summarization as well as a useful summary of those texts including relevant document sentences. This study select...

متن کامل

Improving Semantic Relevance for Sequence-to-Sequence Learning of Chinese Social Media Text Summarization

Current Chinese social media text summarization models are based on an encoderdecoder framework. Although its generated summaries are similar to source texts literally, they have low semantic relevance. In this work, our goal is to improve semantic relevance between source texts and summaries for Chinese social media summarization. We introduce a Semantic Relevance Based neural model to encoura...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: Proceedings of the ... AAAI Conference on Artificial Intelligence

سال: 2022

ISSN: ['2159-5399', '2374-3468']

DOI: https://doi.org/10.1609/aaai.v36i10.21409