{"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/dependency-based-mixture-language-models","title":"Dependency-based Mixture Language Models","arxiv_id":"2203.10256","date":"2022-03-19","proceeding":"ACL 2022 5","authors":["Zhixian Yang","Xiaojun Wan"],"abstract":"Various models have been proposed to incorporate knowledge of syntactic structures into neural language models. However, previous works have relied heavily on elaborate components for a specific language model, usually recurrent neural network (RNN), which makes themselves unwieldy in practice to fit into other neural language models, such as Transformer and GPT-2. In this paper, we introduce the Dependency-based Mixture Language Models. In detail, we first train neural language models with a novel dependency modeling objective to learn the probability distribution of future dependent tokens given context. We then formulate the next-token probability by mixing the previous dependency modeling probability distributions with self-attention. Extensive experiments and human evaluations show that our method can be easily and effectively applied to different neural language models while improving neural text generation on various tasks.","url_abs":"https://arxiv.org/abs/2203.10256v1","url_pdf":"https://arxiv.org/pdf/2203.10256v1.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":"dependency-based-mixture-language-models","repo_url":"https://github.com/fadedcosine/dependency-guided-neural-text-generation","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"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":"text-generation","task_name":"Text Generation"}],"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":"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":"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-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"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":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.10256","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.10256"}},"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/fadedcosine/dependency-guided-neural-text-generation","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"ran":1,"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":"4b59eaae917b5a2d","entry":"cumsoftmax","repo":"fadedcosine/dependency-guided-neural-text-generation","repo_kind":"official","path":"DPLM-LSTM/ON_LSTM.py","file_url":"https://github.com/fadedcosine/dependency-guided-neural-text-generation/blob/HEAD/DPLM-LSTM/ON_LSTM.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4b59eaae917b5a2d"}},{"code_sha256_prefix":"7ae14efdfb766b41","entry":"build_subword_dependecy_head","repo":"fadedcosine/dependency-guided-neural-text-generation","repo_kind":"official","path":"DPLM-Transformer/util/build_bpe_dependency.py","file_url":"https://github.com/fadedcosine/dependency-guided-neural-text-generation/blob/HEAD/DPLM-Transformer/util/build_bpe_dependency.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":"7ae14efdfb766b41"}},{"code_sha256_prefix":"4207d98823b1dcea","entry":"build_word_to_bpe_index_list","repo":"fadedcosine/dependency-guided-neural-text-generation","repo_kind":"official","path":"DPLM-Transformer/util/build_bpe_dependency.py","file_url":"https://github.com/fadedcosine/dependency-guided-neural-text-generation/blob/HEAD/DPLM-Transformer/util/build_bpe_dependency.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":"4207d98823b1dcea"}},{"code_sha256_prefix":"62d148258bdd054f","entry":"embedded_dropout","repo":"fadedcosine/dependency-guided-neural-text-generation","repo_kind":"official","path":"DPLM-LSTM/embed_regularize.py","file_url":"https://github.com/fadedcosine/dependency-guided-neural-text-generation/blob/HEAD/DPLM-LSTM/embed_regularize.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":"62d148258bdd054f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}