{"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/teasel-a-transformer-based-speech-prefixed","title":"TEASEL: A Transformer-Based Speech-Prefixed Language Model","arxiv_id":"2109.05522","date":"2021-09-12","proceeding":null,"authors":["Mehdi Arjmand","Mohammad Javad Dousti","Hadi Moradi"],"abstract":"Multimodal language analysis is a burgeoning field of NLP that aims to simultaneously model a speaker's words, acoustical annotations, and facial expressions. In this area, lexicon features usually outperform other modalities because they are pre-trained on large corpora via Transformer-based models. Despite their strong performance, training a new self-supervised learning (SSL) Transformer on any modality is not usually attainable due to insufficient data, which is the case in multimodal language learning. This work proposes a Transformer-Based Speech-Prefixed Language Model called TEASEL to approach the mentioned constraints without training a complete Transformer model. TEASEL model includes speech modality as a dynamic prefix besides the textual modality compared to a conventional language model. This method exploits a conventional pre-trained language model as a cross-modal Transformer model. We evaluated TEASEL for the multimodal sentiment analysis task defined by CMU-MOSI dataset. Extensive experiments show that our model outperforms unimodal baseline language models by 4% and outperforms the current multimodal state-of-the-art (SoTA) model by 1% in F1-score. Additionally, our proposed method is 72% smaller than the SoTA model.","url_abs":"https://arxiv.org/abs/2109.05522v1","url_pdf":"https://arxiv.org/pdf/2109.05522v1.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":"teasel-a-transformer-based-speech-prefixed","repo_url":"https://github.com/tjdevWorks/TEASEL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"multimodal-sentiment-analysis","task_name":"Multimodal Sentiment Analysis"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"roberta","method_name":"RoBERTa"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/multimodal-sentiment-analysis-on-cmu-mosi","task":"Multimodal Sentiment Analysis","dataset":"CMU-MOSI","model":"TEASEL","rank_in_archive_order":5,"of":12,"metrics":{"Acc-2":"87.5","Acc-7":"47.52","Corr":"0.836","F1":"85","MAE":"0.64"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2109.05522","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.05522"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/tjdevWorks/TEASEL","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":4},"by_repo_kind":{"listed":{"samples":4,"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":"5cea9353bf9a31cb","entry":"fetch_datasets","repo":"tjdevWorks/TEASEL","repo_kind":"listed","path":"dataset/utils.py","file_url":"https://github.com/tjdevWorks/TEASEL/blob/HEAD/dataset/utils.py","link_basis":"harvester_set","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":"5cea9353bf9a31cb"}},{"code_sha256_prefix":"5d719c8bf75f49ef","entry":"fetch_mosi_datasets","repo":"tjdevWorks/TEASEL","repo_kind":"listed","path":"dataset/utils.py","file_url":"https://github.com/tjdevWorks/TEASEL/blob/HEAD/dataset/utils.py","link_basis":"harvester_set","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":"5d719c8bf75f49ef"}},{"code_sha256_prefix":"85dc36593047cd6a","entry":"read_config","repo":"tjdevWorks/TEASEL","repo_kind":"listed","path":"fine_tune_mosi.py","file_url":"https://github.com/tjdevWorks/TEASEL/blob/HEAD/fine_tune_mosi.py","link_basis":"harvester_set","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":"85dc36593047cd6a"}},{"code_sha256_prefix":"9193f7ddaa9cf98e","entry":"train_loop","repo":"tjdevWorks/TEASEL","repo_kind":"listed","path":"fine_tune_mosi.py","file_url":"https://github.com/tjdevWorks/TEASEL/blob/HEAD/fine_tune_mosi.py","link_basis":"harvester_set","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":"9193f7ddaa9cf98e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}