{"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/trainable-greedy-decoding-for-neural-machine","title":"Trainable Greedy Decoding for Neural Machine Translation","arxiv_id":"1702.02429","date":"2017-02-08","proceeding":"EMNLP 2017 9","authors":["Jiatao Gu","Kyunghyun Cho","Victor O. K. Li"],"abstract":"Recent research in neural machine translation has largely focused on two\naspects; neural network architectures and end-to-end learning algorithms. The\nproblem of decoding, however, has received relatively little attention from the\nresearch community. In this paper, we solely focus on the problem of decoding\ngiven a trained neural machine translation model. Instead of trying to build a\nnew decoding algorithm for any specific decoding objective, we propose the idea\nof trainable decoding algorithm in which we train a decoding algorithm to find\na translation that maximizes an arbitrary decoding objective. More\nspecifically, we design an actor that observes and manipulates the hidden state\nof the neural machine translation decoder and propose to train it using a\nvariant of deterministic policy gradient. We extensively evaluate the proposed\nalgorithm using four language pairs and two decoding objectives and show that\nwe can indeed train a trainable greedy decoder that generates a better\ntranslation (in terms of a target decoding objective) with minimal\ncomputational overhead.","url_abs":"http://arxiv.org/abs/1702.02429v1","url_pdf":"http://arxiv.org/pdf/1702.02429v1.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":"trainable-greedy-decoding-for-neural-machine","repo_url":"https://github.com/kyunghyuncho/rl-pong","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1702.02429","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1702.02429"}},"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/kyunghyuncho/rl-pong","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"ran_draft_wrong":2,"unverified":3},"by_repo_kind":{"listed":{"samples":5,"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":0,"samples":[{"code_sha256_prefix":"158bf4c3a5f11f04","entry":"conv1x1","repo":"kyunghyuncho/rl-pong","repo_kind":"listed","path":"conv.py","file_url":"https://github.com/kyunghyuncho/rl-pong/blob/HEAD/conv.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"158bf4c3a5f11f04"}},{"code_sha256_prefix":"dd1114865f06f0fd","entry":"conv3x3","repo":"kyunghyuncho/rl-pong","repo_kind":"listed","path":"conv.py","file_url":"https://github.com/kyunghyuncho/rl-pong/blob/HEAD/conv.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"dd1114865f06f0fd"}},{"code_sha256_prefix":"2acd8dc5ee9ba958","entry":"Player","repo":"kyunghyuncho/rl-pong","repo_kind":"listed","path":"conv.py","file_url":"https://github.com/kyunghyuncho/rl-pong/blob/HEAD/conv.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"2acd8dc5ee9ba958"}},{"code_sha256_prefix":"adf6cf52852fcc06","entry":"collect_one_episode","repo":"kyunghyuncho/rl-pong","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/kyunghyuncho/rl-pong/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"adf6cf52852fcc06"}},{"code_sha256_prefix":"1c1c1a958ec013c9","entry":"normalize_obs","repo":"kyunghyuncho/rl-pong","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/kyunghyuncho/rl-pong/blob/HEAD/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"1c1c1a958ec013c9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}