{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/optimal-hyperparameters-for-deep-lstm","title":"Optimal Hyperparameters for Deep LSTM-Networks for Sequence Labeling Tasks","arxiv_id":"1707.06799","date":"2017-07-21","proceeding":null,"authors":["Nils Reimers","Iryna Gurevych"],"abstract":"Selecting optimal parameters for a neural network architecture can often make\nthe difference between mediocre and state-of-the-art performance. However,\nlittle is published which parameters and design choices should be evaluated or\nselected making the correct hyperparameter optimization often a \"black art that\nrequires expert experiences\" (Snoek et al., 2012). In this paper, we evaluate\nthe importance of different network design choices and hyperparameters for five\ncommon linguistic sequence tagging tasks (POS, Chunking, NER, Entity\nRecognition, and Event Detection). We evaluated over 50.000 different setups\nand found, that some parameters, like the pre-trained word embeddings or the\nlast layer of the network, have a large impact on the performance, while other\nparameters, for example the number of LSTM layers or the number of recurrent\nunits, are of minor importance. We give a recommendation on a configuration\nthat performs well among different tasks.","url_abs":"http://arxiv.org/abs/1707.06799v2","url_pdf":"http://arxiv.org/pdf/1707.06799v2.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":"optimal-hyperparameters-for-deep-lstm","repo_url":"https://github.com/UKPLab/emnlp2017-bilstm-cnn-crf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"optimal-hyperparameters-for-deep-lstm","repo_url":"https://github.com/SuphanutN/Thai-NER-BiLSTM-WordCharEmbedding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"optimal-hyperparameters-for-deep-lstm","repo_url":"https://github.com/SuphanutN/Thai-NER-BiLSTMCRF-WordCharEmbedding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"optimal-hyperparameters-for-deep-lstm","repo_url":"https://github.com/jiesutd/NCRFpp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"optimal-hyperparameters-for-deep-lstm","repo_url":"https://github.com/jiesutd/PyTorchSeqLabel","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"optimal-hyperparameters-for-deep-lstm","repo_url":"https://github.com/jiesutd/yato","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"chunking","task_name":"Chunking"},{"task_slug":"event-detection","task_name":"Event Detection"},{"task_slug":"hyperparameter-optimization","task_name":"Hyperparameter Optimization"},{"task_slug":"named-entity-recognition-ner","task_name":"Named Entity Recognition (NER)"},{"task_slug":"pos","task_name":"POS"},{"task_slug":"word-embeddings","task_name":"Word Embeddings"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1707.06799","atlas_url":"https://app.syntology.ai/?focus=1707.06799","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1707.06799"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1707.06799\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1707.06799"},"call":"get_concepts_for_paper(arxiv_id=\"1707.06799\")"}],"by_repo":[{"repo":"UKPLab/emnlp2017-bilstm-cnn-crf","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1803.09578"],"harvested_for_calls":[{"arxiv_id":"1803.09578","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1803.09578"},"call":"get_harvested_code_for_paper(arxiv_id=\"1803.09578\")"}]},{"repo":"SuphanutN/Thai-NER-BiLSTM-WordCharEmbedding","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"SuphanutN/Thai-NER-BiLSTMCRF-WordCharEmbedding","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"jiesutd/NCRFpp","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2008.03736"],"harvested_for_calls":[{"arxiv_id":"2008.03736","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2008.03736"},"call":"get_harvested_code_for_paper(arxiv_id=\"2008.03736\")"}]},{"repo":"jiesutd/PyTorchSeqLabel","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1806.05626"],"harvested_for_calls":[{"arxiv_id":"1806.05626","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1806.05626"},"call":"get_harvested_code_for_paper(arxiv_id=\"1806.05626\")"}]},{"repo":"jiesutd/yato","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2023.emnlp-demo.11"],"harvested_for_calls":[]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"d29150c8ca14c0804a2c3113fcc2990dc45edb672481f5e2a086e1867da68953","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}