您現在的位置:首頁> 外文會議>Annual meeting of the Society for Computation in Linguistics >文獻詳情

Learning exceptionality and variation with lexically scaled MaxEnt

機器翻譯使用詞匯縮放的maxEnt學習異常和變異

原文傳遞 原文傳遞并翻譯 加入購物車 收藏
3.3 【6hr】

【摘要】A growing body of research in phonology addresses the representation and learning of variable processes and exceptional, lexically conditioned processes. Linzen et al. (2013) present a MaxEnt model with additive lexical scales to account for data exhibiting both variation and exceptionality. In this paper, we implement a learning model for lexically scaled MaxEnt grammars which we show to be successful across a range of data containing patterns of variation and exceptionality. We also explore how the model's parameters and the rate of exceptionality in the data influence its performance and predictions for novel forms.

【作者】Coral Hughto; Andrew Lamont; Brandon Prickett; Gaja Jarosz;

【作者單位】University of Massachusetts Amherst; University of Massachusetts Amherst; University of Massachusetts Amherst; University of Massachusetts Amherst;

【年(卷),期】2019,,

【頁碼】91-101

【總頁數】11

【正文語種】eng

【中圖分類】;

【關鍵詞】;


激情球迷怎么玩 腾讯分分时时計劃 华东15选5走势图200期 搞金融都很赚钱 脫衣發牌的app 3d赚钱 麻将赌博微信发红包 手机单机象棋 快乐12复式的投注方法 高频彩购买 老龄化社会什么行业赚钱 全网影视vip年卡代理赚钱吗 大乐透双色球合买协议 w彩票网游戏 问道最新赚钱 中顺qka斗地主赢话费 自动扫码怎么赚钱