arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2012.03370cs.CLcs.LG
收藏

跨情境词汇学习中的竞争:一项计算研究

Competition in Cross-situational Word Learning: A Computational Study

DeepMind(深度思维);University of Toronto(多伦多大学);Princeton University(普林斯顿大学)

Aida Nematzadeh, Zahra Shekarchi, Thomas L. Griffiths, Suzanne Stevenson

摘要:

孩子们通过挖掘不同情况下使用单词的共性来学习单词的含义,并克服早期单词学习经历中的高度不确定性。我们提出了一个建模框架,以调查的作用,相互排斥的偏见-断言一对一的映射词和它们的含义-在减少不确定性的单词学习。在一组计算研究中,我们表明,要成功地学习词义的不确定性面前,学习者需要使用两种类型的竞争:字竞争的关联到一个指涉学习时,从观察和指涉竞争一个字时,使用这个词。我们的工作突出了算法级分析的重要性,以阐明可以实现相同计算级理论的不同机制的效用。

英文摘要:

Children learn word meanings by tapping into the commonalities across different situations in which words are used and overcome the high level of uncertainty involved in early word learning experiences. We propose a modeling framework to investigate the role of mutual exclusivity bias - asserting one-to-one mappings between words and their meanings - in reducing uncertainty in word learning. In a set of computational studies, we show that to successfully learn word meanings in the face of uncertainty, a learner needs to use two types of competition: words competing for association to a referent when learning from an observation and referents competing for a word when the word is used. Our work highlights the importance of an algorithmic-level analysis to shed light on the utility of different mechanisms that can implement the same computational-level theory.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑