# Word Sense Disambiguation on Concatenation of Datasets SE2 SE3 SE13 SE15 (test) Source: [Word Sense Disambiguation on Concatenation of Datasets SE2 SE3 SE13 SE15 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:53:57.407Z Evaluation of Word Sense Disambiguation performance across a combined test set derived from SemEval tasks SE2, SE3, SE13, and SE15, with results broken down by part-of-speech categories. 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 | Word Sense Disambiguation | | Dataset (including any stated split) | Concatenation of Datasets SE2 SE3 SE13 SE15 (test) | | Metric | Noun Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 12 of 12 | | 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 - [Noun Accuracy](): Higher is better; unit: PERCENT. - [Verb Accuracy](): Higher is better; unit: PERCENT. - [Adj Accuracy](): Higher is better; unit: PERCENT. - [Adv Accuracy](): Higher is better; unit: PERCENT. - [Overall Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Noun Accuracy | Result date | Report paper | | --- | --- | --- | --- | | GASext | 0.722 | Not recorded | 68fa649e1e209131cea05a04 | | GAS | 0.721 | Not recorded | 68fa649e1e209131cea05a04 | | IMS+emb | 0.719 | Not recorded | 68fa649e1e209131cea05a04 | | GASext | 0.719 | Not recorded | 68fa649e1e209131cea05a04 | | GAS | 0.717 | Not recorded | 68fa649e1e209131cea05a04 | | Bi-LSTM+att.+LEX | 0.716 | Not recorded | 68fa649e1e209131cea05a04 | | Bi-LSTM+att.+LEX+POS | 0.715 | Not recorded | 68fa649e1e209131cea05a04 | | IMS | 0.705 | Not recorded | 68fa649e1e209131cea05a04 | | Leskext+emb | 0.7 | Not recorded | 68fa649e1e209131cea05a04 | | Bi-LSTM | 0.695 | Not recorded | 68fa649e1e209131cea05a04 | | Babelfy | 0.689 | Not recorded | 68fa649e1e209131cea05a04 | | MFS baseline | 0.677 | Not recorded | 68fa649e1e209131cea05a04 | ### GASext Noun Accuracy: 0.722. Result ID: 698c4f1b37894ef7d9cd6941. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Composition method":"Concatenation","External Knowledge":true}. This record does not assert independent reproduction. ### GAS Noun Accuracy: 0.721. Result ID: 698c4f1b37894ef7d9cd693f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Composition method":"Concatenation","External Knowledge":true}. This record does not assert independent reproduction. ### IMS+emb Noun Accuracy: 0.719. Result ID: 698c4f1b37894ef7d9cd693a. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GASext Noun Accuracy: 0.719. Result ID: 698c4f1b37894ef7d9cd6940. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Composition method":"Linear","External Knowledge":true}. This record does not assert independent reproduction. ### GAS Noun Accuracy: 0.717. Result ID: 698c4f1b37894ef7d9cd693e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Composition method":"Linear","External Knowledge":true}. This record does not assert independent reproduction. ### Bi-LSTM+att.+LEX Noun Accuracy: 0.716. Result ID: 698c4f1b37894ef7d9cd693c. [Reporting paper]() Recorded evaluation configuration: {"External Knowledge":true}. This record does not assert independent reproduction. ### Bi-LSTM+att.+LEX+POS Noun Accuracy: 0.715. Result ID: 698c4f1b37894ef7d9cd693d. [Reporting paper]() Recorded evaluation configuration: {"External Knowledge":true}. This record does not assert independent reproduction. ### IMS Noun Accuracy: 0.705. Result ID: 698c4f1b37894ef7d9cd6939. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Leskext+emb Noun Accuracy: 0.7. Result ID: 698c4f1b37894ef7d9cd6937. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Bi-LSTM Noun Accuracy: 0.695. Result ID: 698c4f1b37894ef7d9cd693b. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Babelfy Noun Accuracy: 0.689. Result ID: 698c4f1b37894ef7d9cd6938. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### MFS baseline Noun Accuracy: 0.677. Result ID: 698c4f1b37894ef7d9cd6936. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.