Evaluating text coherence based on semantic similarity graph

Abstract

Coherence is a crucial feature of text because it is indispensable for conveying its communication purpose and meaning to its readers. In this paper, we propose an unsupervised text coherence scoring based on graph construction in which edges are established between semantically similar sentences represented by vertices. The sentence similarity is calculated based on the cosine similarity of semantic vectors representing sentences. We provide three graph construction methods establishing an edge from a given vertex to a preceding adjacent vertex, to a single similar vertex, or to multiple similar vertices. We evaluated our methods in the document discrimination task and the insertion task by comparing our proposed methods to the supervised (Entity Grid) and unsupervised (Entity Graph) baselines. In the document discrimination task, our method outperformed the unsupervised baseline but could not do the supervised baseline, while in the insertion task, our method outperformed both baselines.

Matching Document Pairs using Multi-Feature Semantic Fusion Based on Knowledge Graph

“…In the word graphs, the words in the document are used as fixed points, and edges are constructed based on syntax analysis [24], co-occurrence [1,25] or the previous relationship [26]. In text graphs, sentences, paragraphs or documents are all utilized as vertices, and use word co-occurrence, location [27], text similarity [28] or hyperlinks among documents [29] to build edges. We link the terms of documents to real-world concepts based on knowledge storehouses such as DBpedia [30] in the concept map, and construct edges based on semantic and syntactic rules.…”

Context-aware cognitive design assistant: Implementation and study of design rules recommendations

“…Authors use path analysis to compute similarity measurements between nodes in a graph [16], [52]. For example, authors use path analysis methods in semantic graphs to compute semantic similarities between texts, sentences or words [53]- [55]. In a recommender system based on this approach, a "user set" of nodes represents the user interest [56].…”

Assessment of text coherence using an ontology‐based relatedness measurement method

“…Accuracy is the number of times coherent texts are given a higher score than incoherent texts. Putra and Tokunaga (2017) Texts are transformed into semantic vector representations, and the similarities between sentences are calculated based on the cosine similarity between the vectors.…”

“…A text is attributed as coherent if its language elements are semantically interrelated. Several approaches have been proposed to assess text coherence (Barzilay & Lapata, ; Foltz, Kintsch, & Landauer, ; Guinaudeau & Strube, ; Nguyen & Joty, ; Novák, Mírovský, Rysová, & Rysová, ; Putra & Tokunaga, ). None of these approaches used ontologies for measuring semantic relatedness between sentences.…”