Efficient Sentence Embedding via Semantic Subspace Analysis
This addresses the problem of efficient sentence representation for NLP applications, but it appears incremental as it builds on existing word embedding concepts.
The paper tackles sentence embedding by proposing S3E, a method based on semantic subspace analysis, which achieves comparable or better performance than state-of-the-art on textual similarity and supervised tasks with lower complexity.
A novel sentence embedding method built upon semantic subspace analysis, called semantic subspace sentence embedding (S3E), is proposed in this work. Given the fact that word embeddings can capture semantic relationship while semantically similar words tend to form semantic groups in a high-dimensional embedding space, we develop a sentence representation scheme by analyzing semantic subspaces of its constituent words. Specifically, we construct a sentence model from two aspects. First, we represent words that lie in the same semantic group using the intra-group descriptor. Second, we characterize the interaction between multiple semantic groups with the inter-group descriptor. The proposed S3E method is evaluated on both textual similarity tasks and supervised tasks. Experimental results show that it offers comparable or better performance than the state-of-the-art. The complexity of our S3E method is also much lower than other parameterized models.