Browse State-of-the-Art › Keyphrase Extraction
Keyphrase Extraction
52 papers with code · 5 benchmarks · 8 datasets archive 2025-07-28
A classic task to extract salient phrases that best summarize a document, which essentially has two stages: candidate generation and keyphrase ranking.
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
5 leaderboard tables shown for this task, 5 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| KP20k (7 rows) | Wiki+RoBERTa | UCPhrase: Unsupervised Context-aware Quality Phrase Tagging | code | — | Compare |
| KPTimes (4 rows) | UCPhrase | UCPhrase: Unsupervised Context-aware Quality Phrase Tagging | code | — | Compare |
| Inspec (3 rows) | Attention-Seeker | Attention-Seeker: Dynamic Self-Attention Scoring for Unsupervised... | code | — | Compare |
| Krapivin (2 rows) | Attention-Seeker | Attention-Seeker: Dynamic Self-Attention Scoring for Unsupervised... | code | — | Compare |
| NUS (1 row) | PromptRank | PromptRank: Unsupervised Keyphrase Extraction Using Prompt | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
8 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Most implemented papers archive 2025-07-28
30 shown of 52 papers with code (153 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.
-
23 Apr 2017 4 repositories listedKeyphrase provides highly-condensed information that can be effectively used for understanding, organizing and retrieving text content.
-
7 Jun 2023 3 repositories listedPrevious 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…
-
13 Jan 2018 3 repositories listedEmbedRank 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.
-
8 May 2023 2 repositories listedThis demonstrates the great potential of using prompt for unsupervised keyphrase extraction.
-
28 May 2021 2 repositories listedTraining a conventional neural tagger based on silver labels usually faces the risk of overfitting phrase surface names.
-
24 Oct 2020 2 repositories listedDespite significant progress, state-of-the-art abstractive summarization methods are still prone to hallucinate content inconsistent with the source document.
-
28 Apr 2020 2 repositories listedOpen-domain KeyPhrase Extraction (KPE) aims to extract keyphrases from documents without domain or quality restrictions, e.
-
3 Apr 2020 2 repositories listedDiversity in content and open-ended questions are inherent in complex assignments across online graduate programs.
-
6 Nov 2019 2 repositories listedThis paper studies keyphrase extraction in real-world scenarios where documents are from diverse domains and have variant content quality.
-
26 Sep 2019 2 repositories listedThis shows that the proposed method is independent of the domain, collection, and language of the training corpora.
-
13 May 2019 2 repositories listedKeyphrase 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.
-
1 Jun 2013 2 repositories listed
-
20 May 2025 1 repository listedTo address this issue, this paper utilized the structural features and section texts obtained from the section structure information of academic articles to extract keyphrase from academic papers.
-
26 Nov 2024 1 repository listedIn an era of information overload, manually annotating the vast and growing corpus of documents and scholarly papers is increasingly impractical.
-
26 Oct 2024 1 repository listedKeyphrase ranking plays a crucial role in information retrieval and summarization by indexing and retrieving relevant information efficiently.
-
14 Oct 2024 1 repository listedWe evaluate our method on multiple long document classification tasks and long document token classification tasks, demonstrating its effectiveness through comprehensive qualitative and quantitative analyses.
-
17 Sep 2024 1 repository listedThis paper proposes Attention-Seeker, an unsupervised keyphrase extraction method that leverages self-attention maps from a Large Language Model to estimate the importance of candidate phrases.
-
7 Feb 2024 1 repository listedA typical OrConvQA pipeline consists of three modules: a Retriever to retrieve relevant documents from the collection, a Reranker to rerank them given the question and the context, and a Reader to extract an answer span.
-
23 Dec 2023 1 repository listedZero-shot keyphrase extraction aims to build a keyphrase extractor without training by human-annotated data, which is challenging due to the limited human intervention involved.
-
13 Oct 2023 1 repository listedAutomatic Keyphrase Extraction involves identifying essential phrases in a document.
-
12 Oct 2023 1 repository listedKeyphrase generation (KG) aims to generate a set of summarizing words or phrases given a source document, while keyphrase extraction (KE) aims to identify them from the text.
-
16 May 2023 1 repository listedIn this study, we investigate using graph neural network (GNN) representations to enhance contextualized representations of pre-trained language models (PLMs) for keyphrase extraction from lengthy documents.
-
27 Mar 2023 1 repository listedDespite the significant advancements in keyphrase extraction and keyphrase generation methods, the predominant approach for evaluation mainly relies on exact matching with human references.
-
24 Mar 2023 1 repository listedTo prompt SLP advancement, we establish a large-scale general Meeting Understanding and Generation Benchmark (MUG) to benchmark the performance of a wide range of SLP tasks, including topic segmentation, topic-level and…
-
20 Dec 2022 1 repository listedHowever, there lacks a systematic study of how the two types of approaches compare and how different design choices can affect the performance of PLM-based models.
-
11 Oct 2022 1 repository listedKeyphrase extraction is the process of automatically selecting a small set of most relevant phrases from a given text.
-
11 May 2022 1 repository listedTransformer-based architectures in natural language processing force input size limits that can be problematic when long documents need to be processed.
-
4 May 2022 1 repository listedMeanwhile, considering the hierarchical structure hidden in the document, HyperMatch embeds both phrases and documents in the same hyperbolic space via a hyperbolic phrase encoder and a hyperbolic document encoder.
-
15 Mar 2022 1 repository listedKeyphrase extraction aims at automatically extracting a list of "important" phrases representing the key concepts in a document.
-
17 Jan 2022 1 repository listedThe salient phrases are extracted using a ranking algorithm on an undirected graph constructed for the given document.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections