It is a known fact that monolingual children will take advantage of the principle of mutual exclusivity(ME)in the process of early word learning,i.e.,the names of two different objects are mutually exclusive(one label...It is a known fact that monolingual children will take advantage of the principle of mutual exclusivity(ME)in the process of early word learning,i.e.,the names of two different objects are mutually exclusive(one label for one referent).With the help of ME,they can expand their vocabulary effectively with a rapid speed.However,for bilingual children,it seems this principle is not that friendly to them,since they are exposed to two languages at the same time,so there could be at least two labels for the same referent.Hence bilingual children may be confused and encounter difficulties in learning words,which will slower their word learning process.This paper tries to,based on earlier research,probe into the question that how bilingual children acquire words without the help of ME,and explore whether there are advantages of not using ME in word learning for bilingual children.展开更多
Word embedding has drawn a lot of attention due to its usefulness in many NLP tasks. So far a handful of neural-network based word embedding algorithms have been proposed without considering the effects of pronouns in...Word embedding has drawn a lot of attention due to its usefulness in many NLP tasks. So far a handful of neural-network based word embedding algorithms have been proposed without considering the effects of pronouns in the training corpus. In this paper, we propose using co-reference resolution to improve the word embedding by extracting better context. We evaluate four word embeddings with considerations of co-reference resolution and compare the quality of word embedding on the task of word analogy and word similarity on multiple data sets.Experiments show that by using co-reference resolution, the word embedding performance in the word analogy task can be improved by around 1.88%. We find that the words that are names of countries are affected the most,which is as expected.展开更多
文摘It is a known fact that monolingual children will take advantage of the principle of mutual exclusivity(ME)in the process of early word learning,i.e.,the names of two different objects are mutually exclusive(one label for one referent).With the help of ME,they can expand their vocabulary effectively with a rapid speed.However,for bilingual children,it seems this principle is not that friendly to them,since they are exposed to two languages at the same time,so there could be at least two labels for the same referent.Hence bilingual children may be confused and encounter difficulties in learning words,which will slower their word learning process.This paper tries to,based on earlier research,probe into the question that how bilingual children acquire words without the help of ME,and explore whether there are advantages of not using ME in word learning for bilingual children.
基金supported by the National HighTech Research and Development(863)Program(No.2015AA015401)the National Natural Science Foundation of China(Nos.61533018 and 61402220)+2 种基金the State Scholarship Fund of CSC(No.201608430240)the Philosophy and Social Science Foundation of Hunan Province(No.16YBA323)the Scientific Research Fund of Hunan Provincial Education Department(Nos.16C1378 and 14B153)
文摘Word embedding has drawn a lot of attention due to its usefulness in many NLP tasks. So far a handful of neural-network based word embedding algorithms have been proposed without considering the effects of pronouns in the training corpus. In this paper, we propose using co-reference resolution to improve the word embedding by extracting better context. We evaluate four word embeddings with considerations of co-reference resolution and compare the quality of word embedding on the task of word analogy and word similarity on multiple data sets.Experiments show that by using co-reference resolution, the word embedding performance in the word analogy task can be improved by around 1.88%. We find that the words that are names of countries are affected the most,which is as expected.
