Keyphrase Generation

30 papers with code • 2 benchmarks • 1 datasets

Keyphrase Generation aims at generating keyphrases (or phrases) that best summarize a given text article or document.


Most implemented papers

Deep Keyphrase Generation

memray/OpenNMT-kpg-release ACL 2017

Keyphrase provides highly-condensed information that can be effectively used for understanding, organizing and retrieving text content.

Topic-Aware Neural Keyphrase Generation for Social Media Language

yuewang-cuhk/TAKG ACL 2019

Further discussions show that our model learns meaningful topics, which interprets its superiority in social media keyphrase generation.

One Size Does Not Fit All: Generating and Evaluating Variable Number of Keyphrases

memray/OpenNMT-kpg-release ACL 2020

With both previous and new evaluation metrics, our model outperforms strong baselines on all datasets.

An Integrated Approach for Keyphrase Generation via Exploring the Power of Retrieval and Extraction

Chen-Wang-CUHK/KG-KE-KR-M NAACL 2019

For further exploiting the power of extraction and retrieval, we propose a neural-based merging module to combine and re-rank the predicted keyphrases from the enhanced generative model, the extractive model, and the retrieved keyphrases.

Neural Keyphrase Generation via Reinforcement Learning with Adaptive Rewards

kenchan0226/keyphrase-generation-rl ACL 2019

To address this problem, we propose a reinforcement learning (RL) approach for keyphrase generation, with an adaptive reward function that encourages a model to generate both sufficient and accurate keyphrases.

Does Order Matter? An Empirical Study on Generating Multiple Keyphrases as a Sequence

memray/OpenNMT-kpg-release 9 Sep 2019

Recently, concatenating multiple keyphrases as a target sequence has been proposed as a new learning paradigm for keyphrase generation.

Keyphrase Generation for Scientific Articles using GANs

avinsit123/keyphrase-gan 24 Sep 2019

In this paper, we present a keyphrase generation approach using conditional Generative Adversarial Networks (GAN).

KPTimes: A Large-Scale Dataset for Keyphrase Generation on News Documents

ygorg/KPTimes WS 2019

Keyphrase generation is the task of predicting a set of lexical units that conveys the main content of a source text.

Exclusive Hierarchical Decoding for Deep Keyphrase Generation

Chen-Wang-CUHK/ExHiRD-DKG ACL 2020

A new setting is recently introduced into this problem, in which, given a document, the model needs to predict a set of keyphrases and simultaneously determine the appropriate number of keyphrases to produce.

Keyphrase Generation with Cross-Document Attention

svaigba/cdkgen 21 Apr 2020

Keyphrase generation aims to produce a set of phrases summarizing the essentials of a given document.