Knowledge-guided unsupervised rhetorical parsing for text summarization
نویسندگان
چکیده
منابع مشابه
Improving Summarization Through Rhetorical Parsing Tuning
We study the relationship between the structure of" discourse and a set of summarization heuristics that are employed by current systems. A tight coupling of the two enables us to learn genre-specific combinations of heuristics that can be used for disambiguation during discourse parsing. The same coupling enables us to construct discourse structures that yield summaries that contain textual un...
متن کاملImproving summarization through rhetorical parsing tuning
We study the relationship between the structure of discourse and a set of summarization heuristics that are employed by current systems. A tight coupling of the two enables us to learn genre-specific combinations of heuristics that can be used for disambiguation during discourse parsing. The same coupling enables us to construct discourse structures that yield summaries that contain textual uni...
متن کاملTowards a Suitable Rhetorical Representation for Arabic Text Summarization
Text summarization based on rhetorical structure theory has shown extremely interesting result. The process of extracting the text summary from the result of the rhetorical parser is not a singleton. Different rhetorical structure trees are generated from one text. Unfortunately, the result of the generated summary is not equivalent for those trees, and the correctness of the result is affected...
متن کاملThe Rhetorical Parsing, Summarization, and Generation of Natural Language Texts
This thesis is an inquiry into the nature of the high-level, rhetorical structure of unrestricted natural language texts, computational means to enable its derivation, and two applications (in automatic summarization and natural language generation) that follow from the ability to build such structures automatically. The thesis proposes a rst-order formalization of the high-level, rhetorical st...
متن کاملText summarization using unsupervised deep learning
We present methods of extractive query-oriented single-document summarization using a deep auto-encoder (AE) to compute a feature space from the term-frequency (tf ) input. Our experiments explore both local and global vocabularies. We investigate the effect of adding small random noise to local tf as the input representation of AE, and propose an ensemble of such noisy AEs which we call the En...
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: Information Systems
سال: 2020
ISSN: 0306-4379
DOI: 10.1016/j.is.2020.101615