Automatic Document Summarization is the task of rewriting a document into its shorter form while still retaining its important content. The most popular two paradigms are extractive approaches and abstractive approaches. Extractive approaches generate summaries by extracting parts of the original document (usually sentences), while abstractive methods may generate new words or phrases which are not in the original document.
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP).
Ranked #1 on Natural Language Inference on MultiNLI
ABSTRACTIVE TEXT SUMMARIZATION COMMON SENSE REASONING COREFERENCE RESOLUTION DOCUMENT SUMMARIZATION LINGUISTIC ACCEPTABILITY MACHINE TRANSLATION NATURAL LANGUAGE INFERENCE QUESTION ANSWERING SEMANTIC TEXTUAL SIMILARITY SENTIMENT ANALYSIS TEXT CLASSIFICATION TRANSFER LEARNING WORD SENSE DISAMBIGUATION
Natural language processing tasks, such as question answering, machine translation, reading comprehension, and summarization, are typically approached with supervised learning on taskspecific datasets.
Ranked #1 on Language Modelling on enwik8 (using extra training data)
We show that generating English Wikipedia articles can be approached as a multi- document summarization of source documents.
This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks.
Ranked #2 on Generative Question Answering on CoQA (using extra training data)
For abstractive summarization, we propose a new fine-tuning schedule which adopts different optimizers for the encoder and the decoder as a means of alleviating the mismatch between the two (the former is pretrained while the latter is not).
Ranked #2 on Extractive Text Summarization on CNN / Daily Mail (using extra training data)
Graphs that capture relations between textual units have great benefits for detecting salient information from multiple documents and generating overall coherent summaries.
To this end, we propose incorporating latent and explicit dependencies across sentences in the source document into end-to-end single-document summarization models.
Neural extractive summarization models usually employ a hierarchical encoder for document encoding and they are trained using sentence-level labels, which are created heuristically using rule-based methods.
Ranked #6 on Extractive Text Summarization on CNN / Daily Mail
In this paper we conceptualize extractive summarization as a sentence ranking task and propose a novel training algorithm which globally optimizes the ROUGE evaluation metric through a reinforcement learning objective.
Ranked #11 on Extractive Text Summarization on CNN / Daily Mail