{"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/improving-automatic-source-code-summarization","title":"Improving Automatic Source Code Summarization via Deep Reinforcement Learning","arxiv_id":"1811.07234","date":"2018-11-17","proceeding":null,"authors":["Yao Wan","Zhou Zhao","Min Yang","Guandong Xu","Haochao Ying","Jian Wu","Philip S. Yu"],"abstract":"Code summarization provides a high level natural language description of the\nfunction performed by code, as it can benefit the software maintenance, code\ncategorization and retrieval. To the best of our knowledge, most\nstate-of-the-art approaches follow an encoder-decoder framework which encodes\nthe code into a hidden space and then decode it into natural language space,\nsuffering from two major drawbacks: a) Their encoders only consider the\nsequential content of code, ignoring the tree structure which is also critical\nfor the task of code summarization, b) Their decoders are typically trained to\npredict the next word by maximizing the likelihood of next ground-truth word\nwith previous ground-truth word given. However, it is expected to generate the\nentire sequence from scratch at test time. This discrepancy can cause an\n\\textit{exposure bias} issue, making the learnt decoder suboptimal. In this\npaper, we incorporate an abstract syntax tree structure as well as sequential\ncontent of code snippets into a deep reinforcement learning framework (i.e.,\nactor-critic network). The actor network provides the confidence of predicting\nthe next word according to current state. On the other hand, the critic network\nevaluates the reward value of all possible extensions of the current state and\ncan provide global guidance for explorations. We employ an advantage reward\ncomposed of BLEU metric to train both networks. Comprehensive experiments on a\nreal-world dataset show the effectiveness of our proposed model when compared\nwith some state-of-the-art methods.","url_abs":"http://arxiv.org/abs/1811.07234v1","url_pdf":"http://arxiv.org/pdf/1811.07234v1.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":"improving-automatic-source-code-summarization","repo_url":"https://github.com/mf1832146/tree-transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"improving-automatic-source-code-summarization","repo_url":"https://github.com/mf1832146/tree_transformer_2.0","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"code-summarization-1","task_name":"Code Summarization"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"code-summarization","task_name":"Source Code Summarization"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1811.07234","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1811.07234"}},"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/mf1832146/tree-transformer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mf1832146/tree_transformer_2.0","reach":{"status":"ok"}}],"summary":{"ran_violates":1,"ran_honours":1,"unverified":1},"by_repo_kind":{"listed":{"samples":3,"ran":2,"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":3,"samples":[{"code_sha256_prefix":"e0fac7161842b06c","entry":"padding_mask","repo":"mf1832146/tree-transformer","repo_kind":"listed","path":"tree_transformer.py","file_url":"https://github.com/mf1832146/tree-transformer/blob/HEAD/tree_transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e0fac7161842b06c"}},{"code_sha256_prefix":"c85046b5d3a3729d","entry":"sequence_mask","repo":"mf1832146/tree-transformer","repo_kind":"listed","path":"tree_transformer.py","file_url":"https://github.com/mf1832146/tree-transformer/blob/HEAD/tree_transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c85046b5d3a3729d"}},{"code_sha256_prefix":"7b43508245646f85","entry":"relative_mul","repo":"mf1832146/tree-transformer","repo_kind":"listed","path":"tree_transformer.py","file_url":"https://github.com/mf1832146/tree-transformer/blob/HEAD/tree_transformer.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":"7b43508245646f85"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}