{"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/conditioning-lstm-decoder-and-bi-directional","title":"Conditioning LSTM Decoder and Bi-directional Attention Based Question Answering System","arxiv_id":"1905.02019","date":"2019-05-02","proceeding":null,"authors":["Heguang Liu"],"abstract":"Applying neural-networks on Question Answering has gained increasing\npopularity in recent years. In this paper, I implemented a model with\nBi-directional attention flow layer, connected with a Multi-layer LSTM encoder,\nconnected with one start-index decoder and one conditioning end-index decoder.\nI introduce a new end-index decoder layer, conditioning on start-index output.\nThe Experiment shows this has increased model performance by 15.16%. For\nprediction, I proposed a new smart-span equation, rewarding both short answer\nlength and high probability in start-index and end-index, which further\nimproved the prediction accuracy. The best single model achieves an F1 score of\n73.97% and EM score of 64.95% on test set.","url_abs":"http://arxiv.org/abs/1905.02019v1","url_pdf":"http://arxiv.org/pdf/1905.02019v1.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":"conditioning-lstm-decoder-and-bi-directional","repo_url":"https://github.com/hyuna915/squad","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"question-answering","task_name":"Question Answering"}],"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":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}