Concept-Based Embeddings for Natural Language Processing
This work addresses the challenge of leveraging both concepts and words for improved NLP systems, but appears incremental as it builds on existing embedding methods without introducing a new paradigm.
The paper tackled the problem of integrating concept-level and word-level information in NLP by projecting them into a lower-dimensional space to retain critical semantics, and applied this fused embedding to tasks like named entity detection, speech recognition reranking, and targeted sentiment analysis, but did not report specific numerical results.
In this work, we focus on effectively leveraging and integrating information from concept-level as well as word-level via projecting concepts and words into a lower dimensional space while retaining most critical semantics. In a broad context of opinion understanding system, we investigate the use of the fused embedding for several core NLP tasks: named entity detection and classification, automatic speech recognition reranking, and targeted sentiment analysis.