{"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/hierarchical-pre-training-for-sequence","title":"Hierarchical Pre-training for Sequence Labelling in Spoken Dialog","arxiv_id":"2009.11152","date":"2020-09-23","proceeding":"Findings of the Association for Computational Linguistics 2020","authors":["Emile Chapuis","Pierre Colombo","Matteo Manica","Matthieu Labeau","Chloe Clavel"],"abstract":"Sequence labelling tasks like Dialog Act and Emotion/Sentiment identification are a key component of spoken dialog systems. In this work, we propose a new approach to learn generic representations adapted to spoken dialog, which we evaluate on a new benchmark we call Sequence labellIng evaLuatIon benChmark fOr spoken laNguagE benchmark (\\texttt{SILICONE}). \\texttt{SILICONE} is model-agnostic and contains 10 different datasets of various sizes. We obtain our representations with a hierarchical encoder based on transformer architectures, for which we extend two well-known pre-training objectives. Pre-training is performed on OpenSubtitles: a large corpus of spoken dialog containing over $2.3$ billion of tokens. We demonstrate how hierarchical encoders achieve competitive results with consistently fewer parameters compared to state-of-the-art models and we show their importance for both pre-training and fine-tuning.","url_abs":"https://arxiv.org/abs/2009.11152v3","url_pdf":"https://arxiv.org/pdf/2009.11152v3.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":[],"tasks":[{"task_slug":"dialogue-act-classification","task_name":"Dialogue Act Classification"},{"task_slug":"emotion-recognition-in-conversation","task_name":"Emotion Recognition in Conversation"},{"task_slug":"text-classification","task_name":"Text Classification"}],"methods":[],"datasets_introduced":[{"slug":"silicone-benchmark","name":"SILICONE Benchmark","full_name":"SILICONE"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/dialogue-act-classification-on-icsi-meeting","task":"Dialogue Act Classification","dataset":"ICSI Meeting Recorder Dialog Act (MRDA) corpus","model":"Pretrained Hierarchical Transformer","rank_in_archive_order":1,"of":8,"metrics":{"Accuracy":"92.4"},"uses_additional_data":false},{"leaderboard":"/sota/dialogue-act-classification-on-switchboard","task":"Dialogue Act Classification","dataset":"Switchboard corpus","model":"Pretrained Hierarchical Transformer","rank_in_archive_order":8,"of":11,"metrics":{"Accuracy":"79.2"},"uses_additional_data":false},{"leaderboard":"/sota/emotion-recognition-in-conversation-on-3","task":"Emotion Recognition in Conversation","dataset":"DailyDialog","model":"Pretrained Hierarchical Transformer","rank_in_archive_order":6,"of":22,"metrics":{"Micro-F1":"60.14"},"uses_additional_data":false},{"leaderboard":"/sota/emotion-recognition-in-conversation-on","task":"Emotion Recognition in Conversation","dataset":"IEMOCAP","model":"Pretrained Hierarchical Transformer","rank_in_archive_order":42,"of":59,"metrics":{"Accuracy":"66.05","Weighted-F1":"65.37"},"uses_additional_data":false},{"leaderboard":"/sota/emotion-recognition-in-conversation-on-meld","task":"Emotion Recognition in Conversation","dataset":"MELD","model":"Pretrained Hierarchical Transformer","rank_in_archive_order":51,"of":68,"metrics":{"Weighted-F1":"61.90"},"uses_additional_data":false},{"leaderboard":"/sota/emotion-recognition-in-conversation-on-2","task":"Emotion Recognition in Conversation","dataset":"SEMAINE","model":"Pretrained Hierarchical Transformer","rank_in_archive_order":2,"of":3,"metrics":{"MAE (Arousal)":"0.16","MAE (Expectancy)":"0.16","MAE (Power)":"7.70","MAE (Valence)":"0.16"},"uses_additional_data":false},{"leaderboard":"/sota/text-classification-on-silicone-benchmark","task":"Text Classification","dataset":"SILICONE Benchmark","model":"Pretrained Hierarchical Transformer","rank_in_archive_order":1,"of":1,"metrics":{"1:1 Accuracy":"71.25"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2009.11152","atlas_url":"https://app.syntology.ai/?focus=2009.11152","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":"2009.11152"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2009.11152\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2009.11152"},"call":"get_concepts_for_paper(arxiv_id=\"2009.11152\")"}],"by_repo":[],"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":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"3297ebe017d9ea05864c949a5498dbb073ecbbb39e47440ef8b57422eb2334eb","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}