Summarizing a Document by Trimming the Discourse Tree

Abstract

Recent studies on extractive text summarization formulate it as a combinatorial optimization problem, extracting the optimal subset from a set of the textual units that maximizes an objective function without violating the length constraint. Although these methods successfully improve automatic evaluation scores, they do not consider the discourse structure in the source document. Thus, summaries generated by these methods may lack logical coherence.In previous work, we proposed a method that exploits a discourse tree structure to produce coherent summaries. By transforming a traditional discourse tree, namely a rhetorical structure theory-based discourse tree (RST-DT), into a dependency-based discourse tree (DEP-DT), we formulated the summarization procedure as a Tree Knapsack Problem whose tree corresponds to the DEP-DT. This paper extends the work with a detailed discussion of the approach together with a novel efficient dynamic programming algorithm for solving the Tree Knapsack Problem. Experiments show that our method not only achieved the highest score in both automatic and human evaluation, but also obtained good performance in terms of the linguistic qualities of the summaries.

Abstractive Multi-Document Summarization Based on Semantic Link Network

“…(2) Information extraction-based approaches ( [33], [34], [35], [36]), which firstly extract important information units, such as Subject-Verb-Object triples, from documents and then generate new descriptions for them based on manually designed templates or patterns learned from corpus. (3) Paraphrasing based approaches ( [37], [38], [39], [40]), which paraphrase the original sentences with sentence rewriting rules, such as sentence compression, phrases substitution and co-reference resolution, to generate more informative and concise summaries. These approaches mainly rely on statistical or syntactical analysis on text rather than semantics of documents.…”

Block5GIntell: Blockchain for AI-Enabled 5G Networks

“…Generally, they are two approaches to summarize the data context: using new expressions to express the context in the Abstractive approach, or deploying only the original context in the Extractive approach. However, summaries generated by these approaches may lack logical coherence [60].…”

Survey of Scientific Document Summarization Techniques

“…The summarization procedure is considered as a Tree Knapsack problem; it can be formalized as the problem of finding the optimal rooted subtree from the discourse tree. The local properties (text cohesion) and global properties (text coherence) of the discourse structure are analyzed [23,45]. The coherence of a summary is important in order to understand the information contained in the original document.…”