A combined syntactic-semantic embedding model based on lexicalized tree-adjoining grammar. (July 2021)

• Record Type: Journal Article
• Authors: Dang, Hoang-Vu; Le-Hong, Phuong
• Is Part Of: Computer speech & language. Volume 68(2021)
• Publication Date: 2021-07
• Subjects: Syntactic-semantic embedding -- Distributed representations -- Lexicalized-tree adjoining grammar -- Grammar formalism; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2021.101202
• Languages: English
• ISSNs: 0885-2308

Abstract

Highlights: A joint syntactic-semantic embedding model which both enriches word embeddings and generates distributed representations for syntactic structures. The syntactic formalism used in experiments is the lexicalized tree-adjoining grammar. The proposed embedding model help improve a number of natural language processing tasks. Abstract: This paper presents a joint syntactic-semantic embedding model which not only uses syntactic information to enrich the word embeddings but also generates distributed representations for the syntactic structures themselves. The syntactic input to our model comes from a Lexicalized Tree-Adjoining Grammar parser. The word embeddings from our model outperform the Skip-gram embeddings in several word similarity and sentiment classification experiments. The syntactic structure embeddings help improve a transition-based dependency parser by a clear margin.