We introduce s-graph grammars, a new grammar formalism for computing graph-based semantic representations. Semantically annotated corpora which use graphs as semantic representations have recently become available, and there have been a number of data-driven systems for semantic parsing that can be trained on these corpora. However, it is hard to map the linguistic assumptions of these systems ...

In this paper, we discuss two graphs in Wikipedia (i) the article graph, and (ii) the category graph. We perform a graphtheoretic analysis of the category graph, and show that it is a scale-free, small world graph like other well-known lexical semantic networks. We substantiate our findings by transferring semantic relatedness algorithms defined on WordNet to the Wikipedia category graph. To as...

Abstract This paper introduces , a new semantic role labeling method that transforms text into frame-oriented knowledge graph. It performs dependency parsing, identifies the words evoke lexical frames, locates roles and fillers for each frame, runs coercion techniques, formalizes results as formal representation complies with frame semantics used in Framester, factual-linguistic linked data res...

The swift development of autonomous vehicles raises the necessity semantically mapping environment by producing distinguishable representations to recognise similar areas. To this end, in article, we present an efficient technique cut up a robot’s trajectory into consistent communities based on graph-inspired descriptors. This allows agent localise itself future tasks under different environmen...

In recent years, powered by the learned discriminative representation via graph neural network (GNN) models, deep matching methods have made great progresses in task of semantic features. However, these usually rely on heuristically generated patterns, which may introduce unreliable relationships to hurt performance. this paper, we propose a joint learning and network, named GLAM, explore relia...

The Scene Graph Generation (SGG) task aims to detect all the objects and their pairwise visual relationships in a given image. Although SGG has achieved remarkable progress over last few years, almost existing models follow same training paradigm: they treat both object predicate classification as single-label problem, ground-truths are one-hot target labels. However, this prevalent paradigm ov...

Code retrieval is to find the code snippet from a large corpus of source repositories that highly matches query natural language description. Recent work mainly uses processing techniques process both texts (i.e., human language) and snippets machine programming language), however neglecting deep structured features codes, which contain rich semantic information. In this paper, we propose an en...

Abstract The amount of Internet data is increasing day by with the rapid development information technology. To process massive amounts and solve overload, researchers proposed recommender systems. Traditional recommendation methods are mainly based on collaborative filtering algorithms, which have sparsity problems. At present, most model-based algorithms can only capture first-order semantic ...