{"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/encoding-sentences-with-graph-convolutional","title":"Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling","arxiv_id":"1703.04826","date":"2017-03-14","proceeding":"EMNLP 2017 9","authors":["Diego Marcheggiani","Ivan Titov"],"abstract":"Semantic role labeling (SRL) is the task of identifying the\npredicate-argument structure of a sentence. It is typically regarded as an\nimportant step in the standard NLP pipeline. As the semantic representations\nare closely related to syntactic ones, we exploit syntactic information in our\nmodel. We propose a version of graph convolutional networks (GCNs), a recent\nclass of neural networks operating on graphs, suited to model syntactic\ndependency graphs. GCNs over syntactic dependency trees are used as sentence\nencoders, producing latent feature representations of words in a sentence. We\nobserve that GCN layers are complementary to LSTM ones: when we stack both GCN\nand LSTM layers, we obtain a substantial improvement over an already\nstate-of-the-art LSTM SRL model, resulting in the best reported scores on the\nstandard benchmark (CoNLL-2009) both for Chinese and English.","url_abs":"http://arxiv.org/abs/1703.04826v4","url_pdf":"http://arxiv.org/pdf/1703.04826v4.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":"encoding-sentences-with-graph-convolutional","repo_url":"https://github.com/diegma/neural-dep-srl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"encoding-sentences-with-graph-convolutional","repo_url":"https://github.com/kervyRivas/Graph-convolutional-","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"semantic-role-labeling","task_name":"Semantic Role Labeling"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"gcn","method_name":"GCN"},{"method_slug":"graph-convolutional-networks","method_name":"Graph Convolutional Networks"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.04826","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.04826"}},"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/kervyRivas/Graph-convolutional-","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/diegma/neural-dep-srl","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":7,"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":"1dc26906d3c51f7c","entry":"constrained_decoder","repo":"diegma/neural-dep-srl","repo_kind":"official","path":"nnet/run/srl/decoder.py","file_url":"https://github.com/diegma/neural-dep-srl/blob/HEAD/nnet/run/srl/decoder.py","link_basis":"first_harvest_node","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":"1dc26906d3c51f7c"}},{"code_sha256_prefix":"03ec976fc275f65e","entry":"create_optimizer","repo":"diegma/neural-dep-srl","repo_kind":"official","path":"nnet/optimization.py","file_url":"https://github.com/diegma/neural-dep-srl/blob/HEAD/nnet/optimization.py","link_basis":"first_harvest_node","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":"03ec976fc275f65e"}},{"code_sha256_prefix":"4c479ebba02233aa","entry":"evaluate","repo":"diegma/neural-dep-srl","repo_kind":"official","path":"nnet/run/srl/util.py","file_url":"https://github.com/diegma/neural-dep-srl/blob/HEAD/nnet/run/srl/util.py","link_basis":"first_harvest_node","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":"4c479ebba02233aa"}},{"code_sha256_prefix":"d4f5b750462926e0","entry":"from_2009","repo":"diegma/neural-dep-srl","repo_kind":"official","path":"nnet/run/srl/conll.py","file_url":"https://github.com/diegma/neural-dep-srl/blob/HEAD/nnet/run/srl/conll.py","link_basis":"first_harvest_node","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":"d4f5b750462926e0"}},{"code_sha256_prefix":"e0065abcdfbffc27","entry":"get_spans","repo":"diegma/neural-dep-srl","repo_kind":"official","path":"nnet/run/srl/util.py","file_url":"https://github.com/diegma/neural-dep-srl/blob/HEAD/nnet/run/srl/util.py","link_basis":"first_harvest_node","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":"e0065abcdfbffc27"}},{"code_sha256_prefix":"48705fe3d2dffd5e","entry":"make_bio_sample","repo":"diegma/neural-dep-srl","repo_kind":"official","path":"nnet/run/srl/training_sample.py","file_url":"https://github.com/diegma/neural-dep-srl/blob/HEAD/nnet/run/srl/training_sample.py","link_basis":"first_harvest_node","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":"48705fe3d2dffd5e"}},{"code_sha256_prefix":"8f7be7fe47c15745","entry":"process_frame_2009","repo":"diegma/neural-dep-srl","repo_kind":"official","path":"nnet/run/srl/conll.py","file_url":"https://github.com/diegma/neural-dep-srl/blob/HEAD/nnet/run/srl/conll.py","link_basis":"first_harvest_node","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":"8f7be7fe47c15745"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}