{"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/shift-reduce-constituent-parsing-with-neural","title":"Shift-Reduce Constituent Parsing with Neural Lookahead Features","arxiv_id":"1612.00567","date":"2016-12-02","proceeding":"TACL 2017 1","authors":["Jiangming Liu","Yue Zhang"],"abstract":"Transition-based models can be fast and accurate for constituent parsing.\nCompared with chart-based models, they leverage richer features by extracting\nhistory information from a parser stack, which spans over non-local\nconstituents. On the other hand, during incremental parsing, constituent\ninformation on the right hand side of the current word is not utilized, which\nis a relative weakness of shift-reduce parsing. To address this limitation, we\nleverage a fast neural model to extract lookahead features. In particular, we\nbuild a bidirectional LSTM model, which leverages the full sentence information\nto predict the hierarchy of constituents that each word starts and ends. The\nresults are then passed to a strong transition-based constituent parser as\nlookahead features. The resulting parser gives 1.3% absolute improvement in WSJ\nand 2.3% in CTB compared to the baseline, given the highest reported accuracies\nfor fully-supervised parsing.","url_abs":"http://arxiv.org/abs/1612.00567v1","url_pdf":"http://arxiv.org/pdf/1612.00567v1.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":"shift-reduce-constituent-parsing-with-neural","repo_url":"https://github.com/SUTDNLP/LookAheadConparser","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"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":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1612.00567","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}