{"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/embedded-named-entity-recognition-using","title":"Embedded Named Entity Recognition using Probing Classifiers","arxiv_id":"2403.11747","date":"2024-03-18","proceeding":null,"authors":["Nicholas Popovič","Michael Färber"],"abstract":"Streaming text generation has become a common way of increasing the responsiveness of language model powered applications, such as chat assistants. At the same time, extracting semantic information from generated text is a useful tool for applications such as automated fact checking or retrieval augmented generation. Currently, this requires either separate models during inference, which increases computational cost, or destructive fine-tuning of the language model. Instead, we propose an approach called EMBER which enables streaming named entity recognition in decoder-only language models without fine-tuning them and while incurring minimal additional computational cost at inference time. Specifically, our experiments show that EMBER maintains high token generation rates, with only a negligible decrease in speed of around 1% compared to a 43.64% slowdown measured for a baseline. We make our code and data available online, including a toolkit for training, testing, and deploying efficient token classification models optimized for streaming text generation.","url_abs":"https://arxiv.org/abs/2403.11747v2","url_pdf":"https://arxiv.org/pdf/2403.11747v2.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":"embedded-named-entity-recognition-using","repo_url":"https://github.com/nicpopovic/stoke","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"embedded-named-entity-recognition-using","repo_url":"https://github.com/nicpopovic/ember","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"fact-checking","task_name":"Fact Checking"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"cg","task_name":"NER"},{"task_slug":"named-entity-recognition-1","task_name":"Named Entity Recognition"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"retrieval-augmented-generation","task_name":"Retrieval-augmented Generation"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"token-classification","task_name":"Token Classification"},{"task_slug":"named-entity-recognition","task_name":"named-entity-recognition"},{"task_slug":"token-classification","task_name":"token-classification"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"discriminative-fine-tuning","method_name":"Discriminative Fine-Tuning"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-2","method_name":"GPT-2"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"speed","method_name":"SPEED"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.11747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.11747"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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":"deterministic:regex_extraction","url":"https://github.com/nicpopovic/EMBER","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/nicpopovic/STOKE","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/nicpopovic/stoke","reach":{"status":"ok"}}],"summary":{"ran":4,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"repositories":2}},"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":5,"samples":[{"code_sha256_prefix":"1460ab09f18253e0","entry":"MLP","repo":"nicpopovic/EMBER","repo_kind":"official","path":"src/classifier/ner.py","file_url":"https://github.com/nicpopovic/EMBER/blob/HEAD/src/classifier/ner.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1460ab09f18253e0"}},{"code_sha256_prefix":"4f3755dec4374b0c","entry":"MLPProbe","repo":"nicpopovic/stoke","repo_kind":"official","path":"stoke/src/classifier/probes.py","file_url":"https://github.com/nicpopovic/stoke/blob/HEAD/stoke/src/classifier/probes.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4f3755dec4374b0c"}},{"code_sha256_prefix":"4095b9a1ec256dea","entry":"find_best_checkpoint","repo":"nicpopovic/STOKE","repo_kind":"official","path":"stoke/src/selection/simple.py","file_url":"https://github.com/nicpopovic/STOKE/blob/HEAD/stoke/src/selection/simple.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4095b9a1ec256dea"}},{"code_sha256_prefix":"e96085dd6ce7b498","entry":"find_best_checkpoint_in_folder","repo":"nicpopovic/STOKE","repo_kind":"official","path":"stoke/src/selection/simple.py","file_url":"https://github.com/nicpopovic/STOKE/blob/HEAD/stoke/src/selection/simple.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e96085dd6ce7b498"}},{"code_sha256_prefix":"dc01bccf3a114bb1","entry":"map_value_to_color","repo":"nicpopovic/STOKE","repo_kind":"official","path":"chat.py","file_url":"https://github.com/nicpopovic/STOKE/blob/HEAD/chat.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dc01bccf3a114bb1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}