Paraphrase means re-expressing the original meaning in different words,especially words that are easier and simpler to understand.It plays an important role in improving the studying quality.Many students just know th...Paraphrase means re-expressing the original meaning in different words,especially words that are easier and simpler to understand.It plays an important role in improving the studying quality.Many students just know the surface meaning and tend to neglect the implication.So their competence of dealing with problems independently is difficult to cultivate.This thesis aims to investigate paraphrasing strategies employed by Chinese college students.Based on the statistic results of questionnaire and interview,the author tries to sum up the paraphrasing strategies frequently used by students and the rare ones,to reflect the drawback and come up with effective suggestions in the hope of improving students' paraphrase ability and finally strengthening the their competence of language application.展开更多
Paraphrase is an expression of a text with alternative words and orders to achieve a better clarity. Paraphrases have been found vital for augmenting training dataset, which aid to enhance performance of machine learn...Paraphrase is an expression of a text with alternative words and orders to achieve a better clarity. Paraphrases have been found vital for augmenting training dataset, which aid to enhance performance of machine learning models that intended for various natural language processing (NLP) tasks. Thus, recently, automatic paraphrase generation has received increasing attention. However, evaluating quality of generated paraphrases is technically challenging. In the literature, the importance of generated paraphrases is tended to be determined by their impact on the performance of other NLP tasks. This kind of evaluation is referred as extrinsic evaluation, which requires high computational resources to train and test the models. So far, very little attention has been paid to the role of intrinsic evaluation in which quality of generated paraphrase is judged against predefined ground truth (reference paraphrases). In fact, it is also very challenging to find ideal and complete reference paraphrases. Therefore, in this study, we propose semantic or meaning oriented automatic evaluation metric that helps to evaluate quality of generated paraphrases against the original text, which is an intrinsic evaluation approach. Further, we evaluate quality of the paraphrases by assessing their impact on other NLP tasks, which is an extrinsic evaluation method. The goal is to explore the relationship between intrinsic and extrinsic evaluation methods. To ensure the effectiveness of proposed evaluation methods, extensive experiments are done on different publicly available datasets. The experimental results demonstrate that our proposed intrinsic and extrinsic evaluation strategies are promising. The results further reveal that there is a significant correlation between intrinsic and extrinsic evaluation approaches.展开更多
文摘Paraphrase means re-expressing the original meaning in different words,especially words that are easier and simpler to understand.It plays an important role in improving the studying quality.Many students just know the surface meaning and tend to neglect the implication.So their competence of dealing with problems independently is difficult to cultivate.This thesis aims to investigate paraphrasing strategies employed by Chinese college students.Based on the statistic results of questionnaire and interview,the author tries to sum up the paraphrasing strategies frequently used by students and the rare ones,to reflect the drawback and come up with effective suggestions in the hope of improving students' paraphrase ability and finally strengthening the their competence of language application.
文摘Paraphrase is an expression of a text with alternative words and orders to achieve a better clarity. Paraphrases have been found vital for augmenting training dataset, which aid to enhance performance of machine learning models that intended for various natural language processing (NLP) tasks. Thus, recently, automatic paraphrase generation has received increasing attention. However, evaluating quality of generated paraphrases is technically challenging. In the literature, the importance of generated paraphrases is tended to be determined by their impact on the performance of other NLP tasks. This kind of evaluation is referred as extrinsic evaluation, which requires high computational resources to train and test the models. So far, very little attention has been paid to the role of intrinsic evaluation in which quality of generated paraphrase is judged against predefined ground truth (reference paraphrases). In fact, it is also very challenging to find ideal and complete reference paraphrases. Therefore, in this study, we propose semantic or meaning oriented automatic evaluation metric that helps to evaluate quality of generated paraphrases against the original text, which is an intrinsic evaluation approach. Further, we evaluate quality of the paraphrases by assessing their impact on other NLP tasks, which is an extrinsic evaluation method. The goal is to explore the relationship between intrinsic and extrinsic evaluation methods. To ensure the effectiveness of proposed evaluation methods, extensive experiments are done on different publicly available datasets. The experimental results demonstrate that our proposed intrinsic and extrinsic evaluation strategies are promising. The results further reveal that there is a significant correlation between intrinsic and extrinsic evaluation approaches.
