# Keyphrase Extraction on SemEval Task 10 ScienceIE 2017 (test) Source: [Keyphrase Extraction on SemEval Task 10 ScienceIE 2017 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:43:06.569Z Evaluation of Keyphrase Extraction performance on the test split of the SemEval Task 10 ScienceIE 2017 dataset, typically measured using Precision (P), Recall (R), and F1 score. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Keyphrase Extraction | | Dataset (including any stated split) | SemEval Task 10 ScienceIE 2017 (test) | | Metric | F1 Score | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 15 of 15 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [F1 Score](): Higher is better; unit: PERCENT. - [Precision](): Higher is better; unit: PERCENT. - [Recall](): Higher is better; unit: PERCENT. ## Recorded results | Method | F1 Score | Result date | Report paper | | --- | --- | --- | --- | | Phraseformer(BERT, ExEm\_ft) | 67.13 | Not recorded | 68fa6a1d1e209131cea26047 | | Phraseformer(BERT, ExEm\_w2v) | 66.96 | Not recorded | 68fa6a1d1e209131cea26047 | | Phraseformer(BERT, Node2vec) | 65.94 | Not recorded | 68fa6a1d1e209131cea26047 | | Phraseformer(BERT, DeepWalk) | 65.7 | Not recorded | 68fa6a1d1e209131cea26047 | | BERT | 59.04 | Not recorded | 68fa6a1d1e209131cea26047 | | BiLSTM-CRF | 52.1 | Not recorded | 68fa6a1d1e209131cea26047 | | SCIIE | 46 | Not recorded | 68fa64c61e209131cea067ec | | (Luan 2017) | 45.3 | Not recorded | 68fa64c61e209131cea067ec | | Best SemEval | 44 | Not recorded | 68fa64c61e209131cea067ec | | Word2Vec | 29.2 | Not recorded | 68fa6a1d1e209131cea26047 | | ExEm\_ft | 29.13 | Not recorded | 68fa6a1d1e209131cea26047 | | ExEm\_w2v | 29.11 | Not recorded | 68fa6a1d1e209131cea26047 | | DeepWalk | 28.87 | Not recorded | 68fa6a1d1e209131cea26047 | | Node2vec | 28.63 | Not recorded | 68fa6a1d1e209131cea26047 | | TextRank | 20.9 | Not recorded | 68fa6a1d1e209131cea26047 | ### Phraseformer(BERT, ExEm\_ft) F1 Score: 67.13. Result ID: 698e0f01ffc3901de09a7930. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Hybrid method","Base Text Model":"BERT","Base Graph Model":"ExEm\_ft"}. This record does not assert independent reproduction. ### Phraseformer(BERT, ExEm\_w2v) F1 Score: 66.96. Result ID: 698e0f01ffc3901de09a792f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Hybrid method","Base Text Model":"BERT","Base Graph Model":"ExEm\_w2v"}. This record does not assert independent reproduction. ### Phraseformer(BERT, Node2vec) F1 Score: 65.94. Result ID: 698e0f01ffc3901de09a792e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Hybrid method","Base Text Model":"BERT","Base Graph Model":"Node2vec"}. This record does not assert independent reproduction. ### Phraseformer(BERT, DeepWalk) F1 Score: 65.7. Result ID: 698e0f01ffc3901de09a792d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Hybrid method","Base Text Model":"BERT","Base Graph Model":"DeepWalk"}. This record does not assert independent reproduction. ### BERT F1 Score: 59.04. Result ID: 698e0f01ffc3901de09a792c. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Text-based method"}. This record does not assert independent reproduction. ### BiLSTM-CRF F1 Score: 52.1. Result ID: 698e0f01ffc3901de09a792b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Text-based method"}. This record does not assert independent reproduction. ### SCIIE F1 Score: 46. Result ID: 698c8d970b614d12cff18db3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### (Luan 2017) F1 Score: 45.3. Result ID: 698c8d970b614d12cff18db1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Best SemEval F1 Score: 44. Result ID: 698c8d970b614d12cff18db2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Word2Vec F1 Score: 29.2. Result ID: 698e0f01ffc3901de09a792a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Text-based method"}. This record does not assert independent reproduction. ### ExEm\_ft F1 Score: 29.13. Result ID: 698e0f01ffc3901de09a7929. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Graph-based method"}. This record does not assert independent reproduction. ### ExEm\_w2v F1 Score: 29.11. Result ID: 698e0f01ffc3901de09a7928. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Graph-based method"}. This record does not assert independent reproduction. ### DeepWalk F1 Score: 28.87. Result ID: 698e0f01ffc3901de09a7926. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Category":"Graph-based method"}. This record does not assert independent reproduction. ### Node2vec F1 Score: 28.63. Result ID: 698e0f01ffc3901de09a7927. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Category":"Graph-based method"}. This record does not assert independent reproduction. ### TextRank F1 Score: 20.9. Result ID: 698e0f01ffc3901de09a7925. [Reporting paper]() Recorded evaluation configuration: {"Category":"Graph-based method"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.