{"type":"ScholarlyArticle","title":"Self-Adaptive Hierarchical Sentence Model","authors":[{"name":"Han Zhao","slug":"han-zhao","given":"Han","family":"Zhao","affiliation":""},{"name":"Zhengdong Lu","slug":"zhengdong-lu","given":"Zhengdong","family":"Lu","affiliation":""},{"name":"Pascal Poupart","slug":"pascal-poupart","given":"Pascal","family":"Poupart","affiliation":""}],"abstract":"The ability to accurately model a sentence at varying stages (e.g., word-phrase-sentence) plays a central role in natural language processing. As an effort towards this goal we propose a self-adaptive hierarchical sentence model (AdaSent). AdaSent effectively forms a hierarchy of representations from words to phrases and then to sentences through recursive gated local composition of adjacent segments. We design a competitive mechanism (through gating networks) to allow the representations of the same sentence to be engaged in a particular learning task (e.g., classification), therefore effectively mitigating the gradient vanishing problem persistent in other recursive models. Both qualitative and quantitative analysis shows that AdaSent can automatically form and select the representations suitable for the task at hand during training, yielding superior classification performance over competitor models on 5 benchmark data sets.","doi":null,"url":"https://ijcai.org/proceedings/2015/571","pdf":"https://ijcai.org/proceedings/2015/0571.pdf","markdown":"https://ijcai.org/proceedings/2015/571.md","bibtex":"https://ijcai.org/proceedings/2015/bibtex/571","volume":{"slug":"2015","title":"Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2015","url":"https://ijcai.org/proceedings/2015/","year":2015,"location":"Buenos Aires, Argentina","dates":"25–31 July 2015","editors":"Qiang Yang and Michael Wooldridge","isbn":"978-1-57735-738-4","publisher":"International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":"Special Track on Machine Learning","track":"Special Track on Machine Learning","number":571,"pages":{"first":4077,"last":4083},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}