# Unsupervised Deep Keyphrase Generation

arXiv: https://arxiv.org/abs/2104.08729 · HTML: https://mlsanity.com/paper/2104.08729/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 50 references that are in the map.
- First posted on arXiv 18 Apr 2021.

## Builds on (most cited first, 20 of 20)

- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models](https://mlsanity.com/paper/1507.04808/) (2015)
- [Deep Keyphrase Generation](https://mlsanity.com/paper/1704.06879/) (2017)
- [A Convolutional Attention Network for Extreme Summarization of Source Code](https://mlsanity.com/paper/1602.03001/) (2016)
- [Automated Phrase Mining from Massive Text Corpora](https://mlsanity.com/paper/1702.04457/) (2017)
- [Simple Unsupervised Keyphrase Extraction using Sentence Embeddings](https://mlsanity.com/paper/1801.04470/) (2018)
- [One Size Does Not Fit All: Generating and Evaluating Variable Number of Keyphrases](https://mlsanity.com/paper/1810.05241/) (2018)
- [Deep Communicating Agents for Abstractive Summarization](https://mlsanity.com/paper/1803.10357/) (2018)
- [An Empirical Evaluation of doc2vec with Practical Insights into Document Embedding Generation](https://mlsanity.com/paper/1607.05368/) (2016)
- [Exclusive Hierarchical Decoding for Deep Keyphrase Generation](https://mlsanity.com/paper/2004.08511/) (2020)
- [Semi-Supervised Learning for Neural Keyphrase Generation](https://mlsanity.com/paper/1808.06773/) (2018)
- [Title-Guided Encoding for Keyphrase Generation](https://mlsanity.com/paper/1808.08575/) (2018)
- [Open Domain Web Keyphrase Extraction Beyond Language Modeling](https://mlsanity.com/paper/1911.02671/) (2019)
- [An Empirical Study on Neural Keyphrase Generation](https://mlsanity.com/paper/2009.10229/) (2020)
- [DivGraphPointer: A Graph Pointer Network for Extracting Diverse Keyphrases](https://mlsanity.com/paper/1905.07689/) (2019)
- [Redefining Absent Keyphrases and their Effect on Retrieval Effectiveness](https://mlsanity.com/paper/2103.12440/) (2021)
- [Does Order Matter? An Empirical Study on Generating Multiple Keyphrases as a Sequence](https://mlsanity.com/paper/1909.03590/) (2019)

## Built on by (most cited first, 7 of 7)

- [Representation Learning for Resource-Constrained Keyphrase Generation](https://mlsanity.com/paper/2203.08118/) (2022)
- [From Statistical Methods to Deep Learning, Automatic Keyphrase Prediction: A Survey](https://mlsanity.com/paper/2305.02579/) (2023)
- [Keyphrase Generation Beyond the Boundaries of Title and Abstract](https://mlsanity.com/paper/2112.06776/) (2021)
- [Data Augmentation for Low-Resource Keyphrase Generation](https://mlsanity.com/paper/2305.17968/) (2023)
- [Self-Compositional Data Augmentation for Scientific Keyphrase Generation](https://mlsanity.com/paper/2411.03039/) (2024)
- [ConExion: Concept Extraction with Large Language Models](https://mlsanity.com/paper/2504.12915/) (2025)
- [Unsupervised Open-domain Keyphrase Generation](https://mlsanity.com/paper/2306.10755/) (2023)

## Abstract (arXiv)

Keyphrase generation aims to summarize long documents with a collection of salient phrases. Deep neural models have demonstrated a remarkable success in this task, capable of predicting keyphrases that are even absent from a document. However, such abstractiveness is acquired at the expense of a substantial amount of annotated data. In this paper, we present a novel method for keyphrase generation, AutoKeyGen, without the supervision of any human annotation. Motivated by the observation that an absent keyphrase in one document can appear in other places, in whole or in part, we first construct a phrase bank by pooling all phrases in a corpus. With this phrase bank, we then draw candidate absent keyphrases for each document through a partial matching process. To rank both types of candidates, we combine their lexical- and semantic-level similarities to the input document. Moreover, we utilize these top-ranked candidates as to train a deep generative model for more absent keyphrases. Extensive experiments demonstrate that AutoKeyGen outperforms all unsupervised baselines and can even beat strong supervised methods in certain cases.