Keyphrase Extraction

47 papers with code • 9 benchmarks • 6 datasets

A classic task to extract salient phrases that best summarize a document, which essentially has two stages: candidate generation and keyphrase ranking.

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.

Simple Unsupervised Keyphrase Extraction using Sentence Embeddings

swisscom/ai-research-keyphrase-extraction CONLL 2018

EmbedRank achieves higher F-scores than graph-based state of the art systems on standard datasets and is suitable for real-time processing of large amounts of Web data.

A Review of Keyphrase Extraction

talmago/spacy_yake 13 May 2019

Keyphrase extraction is a textual information processing task concerned with the automatic extraction of representative and characteristic phrases from a document that express all the key aspects of its content.

Open Domain Web Keyphrase Extraction Beyond Language Modeling

microsoft/OpenKP IJCNLP 2019

This paper studies keyphrase extraction in real-world scenarios where documents are from diverse domains and have variant content quality.

Finding Black Cat in a Coal Cellar -- Keyphrase Extraction & Keyphrase-Rubric Relationship Classification from Complex Assignments

manikandan-ravikiran/cs6460-proj 3 Apr 2020

Diversity in content and open-ended questions are inherent in complex assignments across online graduate programs.

Capturing Global Informativeness in Open Domain Keyphrase Extraction

thunlp/BERT-KPE 28 Apr 2020

Open-domain KeyPhrase Extraction (KPE) aims to extract keyphrases from documents without domain or quality restrictions, e. g., web pages with variant domains and qualities.

Constrained Abstractive Summarization: Preserving Factual Consistency with Constrained Generation

morningmoni/ede 24 Oct 2020

Despite significant progress, state-of-the-art abstractive summarization methods are still prone to hallucinate content inconsistent with the source document.

UCPhrase: Unsupervised Context-aware Quality Phrase Tagging

xgeric/UCPhrase-reproduce 28 May 2021

Training a conventional neural tagger based on silver labels usually faces the risk of overfitting phrase surface names.

Enhancing In-Context Learning with Answer Feedback for Multi-Span Question Answering

nju-websoft/FBPrompt 7 Jun 2023

Previous researches found that in-context learning is an effective approach to exploiting LLM, by using a few task-related labeled data as demonstration examples to construct a few-shot prompt for answering new questions.