Recent neural models for data-to-text generation are mostly based on data-driven end-to-end training over encoder-decoder networks. Even though the generated texts are mostly fluent and informative, they often generate descriptions that are not consistent with the input structured data. This is a critical issue especially in domains that require inference or calculations over raw data. In this paper, we attempt to improve the fidelity of neural data-to-text generation by utilizing pre-executed symbolic operations. We propose a framework called Operation-guided Attention-based sequence-to-sequence network (OpAtt), with a specifically designed gating mechanism as well as a quantization module for operation results to utilize information from pre-executed operations. Experiments on two sports datasets show our proposed method clearly improves the fidelity of the generated texts to the input structured data.<\/p>\n","protected":false},"excerpt":{"rendered":"
Recent neural models for data-to-text generation are mostly based on data-driven end-to-end training over encoder-decoder networks. Even though the generated texts are mostly fluent and informative, they often generate descriptions that are not consistent with the input structured data. This is a critical issue especially in domains that require inference or calculations over raw data. […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13556,13545],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-field-of-study":[246694,246673,246691,248845,247843,248872,248668,246685,248869,247558,248761],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-714700","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-research-area-human-language-technologies","msr-locale-en_us","msr-field-of-study-artificial-intelligence","msr-field-of-study-artificial-neural-network","msr-field-of-study-computer-science","msr-field-of-study-data-model","msr-field-of-study-fidelity","msr-field-of-study-high-fidelity","msr-field-of-study-inference","msr-field-of-study-machine-learning","msr-field-of-study-quantization-signal-processing","msr-field-of-study-raw-data","msr-field-of-study-text-generation"],"msr_publishername":"Association for Computational Linguistics","msr_edition":"","msr_affiliation":"","msr_published_date":"2018-9-8","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/www.aclweb.org\/anthology\/D18-1422.pdf","label_id":"243132","label":0},{"type":"doi","viewUrl":"false","id":"false","title":"10.18653\/V1\/D18-1422","label_id":"243106","label":0},{"type":"url","viewUrl":"false","id":"false","title":"http:\/\/arxiv-export-lb.library.cornell.edu\/abs\/1809.02735","label_id":"243109","label":0},{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/dblp.uni-trier.de\/db\/journals\/corr\/corr1809.html#abs-1809-02735","label_id":"243109","label":0},{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/ui.adsabs.harvard.edu\/abs\/2018arXiv180902735N\/abstract","label_id":"243109","label":0},{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/www.aclweb.org\/anthology\/D18-1422\/","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[],"msr-author-ordering":[{"type":"text","value":"Feng Nie","user_id":0,"rest_url":false},{"type":"text","value":"Jinpeng Wang","user_id":0,"rest_url":false},{"type":"text","value":"Jin-Ge Yao","user_id":0,"rest_url":false},{"type":"text","value":"Rong Pan","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Chin-Yew Lin","user_id":31493,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Chin-Yew Lin"}],"msr_impact_theme":[],"msr_research_lab":[199560],"msr_event":[],"msr_group":[144919],"msr_project":[717085],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/714700"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/714700\/revisions"}],"predecessor-version":[{"id":714703,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/714700\/revisions\/714703"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=714700"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=714700"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=714700"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=714700"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=714700"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=714700"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=714700"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=714700"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=714700"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=714700"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=714700"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=714700"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=714700"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=714700"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=714700"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}