{"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/enhancing-the-transformer-with-explicit-1","title":"Enhancing the Transformer with Explicit Relational Encoding for Math Problem Solving","arxiv_id":"1910.06611","date":"2019-10-15","proceeding":null,"authors":["Imanol Schlag","Paul Smolensky","Roland Fernandez","Nebojsa Jojic","Jürgen Schmidhuber","Jianfeng Gao"],"abstract":"We incorporate Tensor-Product Representations within the Transformer in order to better support the explicit representation of relation structure. Our Tensor-Product Transformer (TP-Transformer) sets a new state of the art on the recently-introduced Mathematics Dataset containing 56 categories of free-form math word-problems. The essential component of the model is a novel attention mechanism, called TP-Attention, which explicitly encodes the relations between each Transformer cell and the other cells from which values have been retrieved by attention. TP-Attention goes beyond linear combination of retrieved values, strengthening representation-building and resolving ambiguities introduced by multiple layers of standard attention. The TP-Transformer's attention maps give better insights into how it is capable of solving the Mathematics Dataset's challenging problems. Pretrained models and code will be made available after publication.","url_abs":"https://arxiv.org/abs/1910.06611v2","url_pdf":"https://arxiv.org/pdf/1910.06611v2.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":"enhancing-the-transformer-with-explicit-1","repo_url":"https://github.com/ischlag/TP-Transformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"enhancing-the-transformer-with-explicit-1","repo_url":"https://github.com/jlrussin/interpret-math-transformer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"enhancing-the-transformer-with-explicit-1","repo_url":"https://github.com/andrear632/ProjectDeepLearning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"math","task_name":"Math"},{"task_slug":"question-answering","task_name":"Question Answering"}],"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":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"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":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-mathematics-dataset","task":"Question Answering","dataset":"Mathematics Dataset","model":"TP-Transformer","rank_in_archive_order":1,"of":3,"metrics":{"Accuracy":"0.8192"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1910.06611","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.06611"}},"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/ischlag/TP-Transformer","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jlrussin/interpret-math-transformer","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/andrear632/ProjectDeepLearning","reach":{"status":"ok"}}],"summary":{"ran_honours":1,"unverified":10},"by_repo_kind":{"official":{"samples":11,"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":"f6b944f50d3f15ae","entry":"count_parameters","repo":"ischlag/TP-Transformer","repo_kind":"official","path":"utils/lib.py","file_url":"https://github.com/ischlag/TP-Transformer/blob/HEAD/utils/lib.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f6b944f50d3f15ae"}},{"code_sha256_prefix":"ce9444c4e1d8e4a6","entry":"build_transformer","repo":"ischlag/TP-Transformer","repo_kind":"official","path":"models/transformer.py","file_url":"https://github.com/ischlag/TP-Transformer/blob/HEAD/models/transformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ce9444c4e1d8e4a6"}},{"code_sha256_prefix":"a20c7972eaaca117","entry":"get_read_streams","repo":"ischlag/TP-Transformer","repo_kind":"official","path":"merge_all_dm_math.py","file_url":"https://github.com/ischlag/TP-Transformer/blob/HEAD/merge_all_dm_math.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a20c7972eaaca117"}},{"code_sha256_prefix":"3ad1dc245ff6f211","entry":"get_write_stream","repo":"ischlag/TP-Transformer","repo_kind":"official","path":"merge_all_dm_math.py","file_url":"https://github.com/ischlag/TP-Transformer/blob/HEAD/merge_all_dm_math.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ad1dc245ff6f211"}},{"code_sha256_prefix":"d570016512f5c4f5","entry":"is_nan","repo":"ischlag/TP-Transformer","repo_kind":"official","path":"models/tp-transformer.py","file_url":"https://github.com/ischlag/TP-Transformer/blob/HEAD/models/tp-transformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d570016512f5c4f5"}},{"code_sha256_prefix":"0823d2f457cf6ad5","entry":"is_nan_string","repo":"ischlag/TP-Transformer","repo_kind":"official","path":"models/tp-transformer.py","file_url":"https://github.com/ischlag/TP-Transformer/blob/HEAD/models/tp-transformer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0823d2f457cf6ad5"}},{"code_sha256_prefix":"944be7e833810869","entry":"make_jit_pairs_and_indexes","repo":"ischlag/TP-Transformer","repo_kind":"official","path":"process_dm_math.py","file_url":"https://github.com/ischlag/TP-Transformer/blob/HEAD/process_dm_math.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"944be7e833810869"}},{"code_sha256_prefix":"40146ea057e31174","entry":"pick_new_seed","repo":"ischlag/TP-Transformer","repo_kind":"official","path":"utils/lib.py","file_url":"https://github.com/ischlag/TP-Transformer/blob/HEAD/utils/lib.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"40146ea057e31174"}},{"code_sha256_prefix":"552c0d8df4dd0117","entry":"read_files","repo":"ischlag/TP-Transformer","repo_kind":"official","path":"process_dm_math.py","file_url":"https://github.com/ischlag/TP-Transformer/blob/HEAD/process_dm_math.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"552c0d8df4dd0117"}},{"code_sha256_prefix":"5186e518cde7c126","entry":"split_into_x_y","repo":"ischlag/TP-Transformer","repo_kind":"official","path":"process_dm_math.py","file_url":"https://github.com/ischlag/TP-Transformer/blob/HEAD/process_dm_math.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5186e518cde7c126"}},{"code_sha256_prefix":"73a42887d25c7f1c","entry":"tensor_find","repo":"ischlag/TP-Transformer","repo_kind":"official","path":"utils/lib.py","file_url":"https://github.com/ischlag/TP-Transformer/blob/HEAD/utils/lib.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"73a42887d25c7f1c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}