Compositional Semantics using Feature-Based Models from WordNet
This article describes a method to build semantic representations of composite expressions in a compositional way by using WordNet relations to represent the meaning of words. The meaning of a target word is modelled as a vector in which its semantically related words are assigned weights according to both the type of the relationship and the distance to the target word. Word vectors are compositionally combined by syntactic dependencies. Each syntactic dependency triggers two complementary compositional functions: the named head function and dependent function. The experiments show that the proposed compositional method outperforms the state-of-the-art for both intransitive subject-verb and transitive subject-verb-object constructions.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Multi-word Lexical Units Recognition in WordNet
WordNet is a state-of-the-art lexical resource used in many tasks in Natural Language Processing, also in multi-word expression (MWE) recognition. However, not all MWEs recorded in WordNet could be indisputably called le…
AllregressionLearning Graph Embeddings for Compositional Zero-shot Learning
In compositional zero-shot learning, the goal is to recognize unseen compositions (e.g. old dog) of observed visual primitives states (e.g. old, cute) and objects (e.g. car, dog) in the training set. This is challenging …
Compositional Zero-Shot LearningGraph EmbeddingTransfer LearningZero-Shot LearningConfirming the Non-compositionality of Idioms for Sentiment Analysis
An idiom is defined as a non-compositional multiword expression, one whose meaning cannot be deduced from the definitions of the component words. This definition does not explicitly define the compositionality of an idio…
Sentiment AnalysisAssessing Wordnets with WordNet Embeddings
An effective conversion method was proposed in the literature to obtain a lexical semantic space from a lexical semantic graph, thus permitting to obtain WordNet embeddings from WordNets. In this paper, we propose the ex…
Semantic SimilaritySemantic Textual SimilarityWord EmbeddingsToward the creation of WordNets for ancient Indo-European languages
This paper presents the work in progress toward the creation of a family of WordNets for Sanskrit, Ancient Greek, and Latin. Building on previous attempts in the field, we elaborate these efforts bridging together WordNe…