A Survey of Implicit Discourse Relation Recognition
نویسندگان
چکیده
A discourse containing one or more sentences describes daily issues and events for people to communicate their thoughts opinions. As are normally consist of multiple text segments, correct understanding the theme a should take into consideration relations in between segments. Although sometimes connective exists raw texts conveying relations, it is often cases that no two segments but some implicit relation does exist them. The task recognition (IDRR) detect classify its sense without connective. Indeed, IDRR important diverse downstream natural language processing tasks, such as summarization, machine translation so on. This article provides comprehensive up-to-date survey task. We first summarize definition data sources widely used field. categorize main solution approaches from viewpoint development history. In each category, we present analyze most representative methods, including origins, ideas, strengths weaknesses. also performance comparisons those solutions experimented on public corpus with standard procedures. Finally, discuss future research directions analysis.
منابع مشابه
Improving Implicit Discourse Relation Recognition with Discourse-specific Word Embeddings
We introduce a simple and effective method to learn discourse-specific word embeddings (DSWE) for implicit discourse relation recognition. Specifically, DSWE is learned by performing connective classification on massive explicit discourse data, and capable of capturing discourse relationships between words. On the PDTB data set, using DSWE as features achieves significant improvements over base...
متن کاملPredicting Discourse Connectives for Implicit Discourse Relation Recognition
Existing works indicate that the absence of explicit discourse connectives makes it difficult to recognize implicit discourse relations. In this paper we attempt to overcome this difficulty for implicit relation recognition by automatically inserting discourse connectives between arguments with the use of a language model. Then we propose two algorithms to use these predicted connectives. One i...
متن کاملBilingually-constrained Synthetic Data for Implicit Discourse Relation Recognition
To alleviate the shortage of labeled data, we propose to use bilingually-constrained synthetic implicit data for implicit discourse relation recognition. These data are extracted from a bilingual sentence-aligned corpus according to the implicit/explicit mismatch between different languages. Incorporating these data via a multi-task neural network model achieves significant improvements over ba...
متن کاملImplicit Discourse Relation Recognition with Context-aware Character-enhanced Embeddings
For the task of implicit discourse relation recognition, traditional models utilizing manual features can suffer from data sparsity problem. Neural models provide a solution with distributed representations, which could encode the latent semantic information, and are suitable for recognizing semantic relations between argument pairs. However, conventional vector representations usually adopt em...
متن کاملMemory Augmented Attention Model for Chinese Implicit Discourse Relation Recognition
Recently, Chinese implicit discourse relation recognition has attracted more and more attention, since it is crucial to understand the Chinese discourse text. In this paper, we propose a novel memory augmented attention model which represents the arguments using an attention-based neural network and preserves the crucial information with an external memory network which captures each discourse ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: ACM Computing Surveys
سال: 2023
ISSN: ['0360-0300', '1557-7341']
DOI: https://doi.org/10.1145/3574134