{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/concatenated-power-mean-word-embeddings-as","title":"Concatenated Power Mean Word Embeddings as Universal Cross-Lingual Sentence Representations","arxiv_id":"1803.01400","date":"2018-03-04","proceeding":null,"authors":["Andreas Rücklé","Steffen Eger","Maxime Peyrard","Iryna Gurevych"],"abstract":"Average word embeddings are a common baseline for more sophisticated sentence\nembedding techniques. However, they typically fall short of the performances of\nmore complex models such as InferSent. Here, we generalize the concept of\naverage word embeddings to power mean word embeddings. We show that the\nconcatenation of different types of power mean word embeddings considerably\ncloses the gap to state-of-the-art methods monolingually and substantially\noutperforms these more complex techniques cross-lingually. In addition, our\nproposed method outperforms different recently proposed baselines such as SIF\nand Sent2Vec by a solid margin, thus constituting a much harder-to-beat\nmonolingual baseline. Our data and code are publicly available.","url_abs":"http://arxiv.org/abs/1803.01400v2","url_pdf":"http://arxiv.org/pdf/1803.01400v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"concatenated-power-mean-word-embeddings-as","repo_url":"https://github.com/UKPLab/arxiv2018-xling-sentence-embeddings","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"sentence-embedding","task_name":"Sentence Embedding"},{"task_slug":"sentence-embedding-1","task_name":"Sentence-Embedding"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1803.01400","atlas_url":"https://app.syntology.ai/?focus=1803.01400","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1803.01400"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/UKPLab/arxiv2018-xling-sentence-embeddings","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"481f4d2e70eea78e","entry":"gen_mean","repo":"UKPLab/arxiv2018-xling-sentence-embeddings","repo_kind":"official","path":"model/sentence_embeddings.py","file_url":"https://github.com/UKPLab/arxiv2018-xling-sentence-embeddings/blob/HEAD/model/sentence_embeddings.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"481f4d2e70eea78e"}},{"code_sha256_prefix":"bd508766f845b238","entry":"get_sentence_embedding","repo":"UKPLab/arxiv2018-xling-sentence-embeddings","repo_kind":"official","path":"model/sentence_embeddings.py","file_url":"https://github.com/UKPLab/arxiv2018-xling-sentence-embeddings/blob/HEAD/model/sentence_embeddings.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bd508766f845b238"}},{"code_sha256_prefix":"ed96e1b52abe539a","entry":"map_embeddings","repo":"UKPLab/arxiv2018-xling-sentence-embeddings","repo_kind":"official","path":"map-word-embeddings/map.py","file_url":"https://github.com/UKPLab/arxiv2018-xling-sentence-embeddings/blob/HEAD/map-word-embeddings/map.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ed96e1b52abe539a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}