Asset Details
Do you wish to reserve the book?
Machine reading comprehension combined with semantic dependency for Chinese zero pronoun resolution
Hey, we have placed the reservation for you!
By the way, why not check out events that you can attend while you pick your title.
Oops! Something went wrong.
Looks like we were not able to place the reservation. Kindly try again later.
Are you sure you want to remove the book from the shelf?
Machine reading comprehension combined with semantic dependency for Chinese zero pronoun resolution
Do you wish to request the book?
Machine reading comprehension combined with semantic dependency for Chinese zero pronoun resolution
Please be aware that the book you have requested cannot be checked out. If you would like to checkout this book, you can reserve another copy
We have requested the book for you!
Your request is successful and it will be processed during the Library working hours. Please check the status of your request in My Requests.
Oops! Something went wrong.
Looks like we were not able to place your request. Kindly try again later.
Journal Article
Machine reading comprehension combined with semantic dependency for Chinese zero pronoun resolution
2023
Overview
Pronoun-drop is a common phenomenon in Chinese, zero pronoun resolution aims to recover the pronoun and resolve the anaphora antecedent of the pronoun, which is important for NLP tasks such as machine translation, information extraction, etc. Most of the existing research methods predefined zero pronoun sets. Zero pronoun recovery is carried out through multi-classification, and then the coreference chains between each pronoun and the candidate antecedent are predicted in turn. However, most of the previous methods only focus on the relationship between pronouns and arguments, ignoring the deep semantic relationship between predicates and arguments as the core semantic component. In addition, the model takes the parse tree (gold tree) as a priori knowledge, which is costly in practical applications. In this paper, we propose a Machine Reading Comprehension model combined with Semantic Dependency (MRC-SD), which takes advantage of the feature that semantic dependencies can directly access deep semantic information across the surface syntactic structure of a sentence to capture the semantic relations between predicates and arguments, and enhance such semantic relations in the form of questions and answers through machine reading comprehension, to extract co-reference chains more accurately. In addition, we propose a method of combining semantic dependency with the language model to realize zero pronoun recovery from the deep semantic level. Experimental results on our self-constructed public opinion dataset (FS-PO) show that the MRC-SD model significantly outperforms the state-of-the-art zero-pronoun resolution model.
