{"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/assemble-foundation-models-for-automatic-code","title":"Assemble Foundation Models for Automatic Code Summarization","arxiv_id":"2201.05222","date":"2022-01-13","proceeding":null,"authors":["Jian Gu","Pasquale Salza","Harald C. Gall"],"abstract":"Automatic code summarization is beneficial to daily software development since it could help reduce the requirement of manual writing. Currently, artificial intelligence is undergoing a paradigm shift. The foundation models pretrained on massive data and finetuned to downstream tasks surpass specially customized models. This trend inspired us to consider reusing foundation models instead of learning from scratch. Thereby, we propose a flexible and robust approach for automatic code summarization, based on neural models. We assemble available foundation models, such as CodeBERT and GPT-2, into a single neural model named AdaMo. Moreover, we utilize Gaussian noise as the simulation of contextual information to optimize the latent representation. Furthermore, we introduce two adaptive schemes from the perspective of knowledge transfer, namely continuous pretraining and intermediate finetuning, and design intermediate stage tasks for general sequence-to-sequence learning. Finally, we evaluate AdaMo against a benchmark dataset for code summarization, by comparing it with state-of-the-art models.","url_abs":"https://arxiv.org/abs/2201.05222v2","url_pdf":"https://arxiv.org/pdf/2201.05222v2.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":"assemble-foundation-models-for-automatic-code","repo_url":"https://github.com/jianguda/afm4acs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"code-documentation-generation","task_name":"Code Documentation Generation"},{"task_slug":"code-summarization-1","task_name":"Code Summarization"},{"task_slug":"sequence-to-sequence-language-modeling","task_name":"Sequence-to-sequence Language Modeling"},{"task_slug":"code-summarization","task_name":"Source Code Summarization"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"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":"codebert","method_name":"CodeBERT"},{"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":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/source-code-summarization-on-codesearchnet","task":"Source Code Summarization","dataset":"CodeSearchNet - Python","model":"AdaMo-basic","rank_in_archive_order":1,"of":1,"metrics":{"BLEU-4":"16.46","METEOR":"12.51%"},"uses_additional_data":false},{"leaderboard":"/sota/source-code-summarization-on-deepcom-java","task":"Source Code Summarization","dataset":"DeepCom-Java","model":"AdaMo-noise","rank_in_archive_order":1,"of":2,"metrics":{"BLEU-4":"45.35","METEOR":"28.25%"},"uses_additional_data":false},{"leaderboard":"/sota/source-code-summarization-on-deepcom-java","task":"Source Code Summarization","dataset":"DeepCom-Java","model":"AdaMo-basic","rank_in_archive_order":2,"of":2,"metrics":{"BLEU-4":"45.3","METEOR":"28.19%"},"uses_additional_data":false},{"leaderboard":"/sota/source-code-summarization-on-hybrid-deepcom","task":"Source Code Summarization","dataset":"Java scripts","model":"AdaMo-basic","rank_in_archive_order":1,"of":1,"metrics":{"BLEU-4":"37.64","METEOR":"25.59%"},"uses_additional_data":false},{"leaderboard":"/sota/source-code-summarization-on-parallelcorpus","task":"Source Code Summarization","dataset":"ParallelCorpus-Python","model":"AdaMo-noise","rank_in_archive_order":1,"of":2,"metrics":{"BLEU-4":"34.05","METEOR":"21.92%"},"uses_additional_data":false},{"leaderboard":"/sota/source-code-summarization-on-parallelcorpus","task":"Source Code Summarization","dataset":"ParallelCorpus-Python","model":"AdaMo-basic","rank_in_archive_order":2,"of":2,"metrics":{"BLEU-4":"33.85","METEOR":"21.68%"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers","held":null,"reason":"arxiv_id_not_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"by_repo":[{"repo":"jianguda/afm4acs","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"826e3ea54fdcc8854df7d1def40ef2e4890ce186223699921b3a9d7b8a3094dc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}