LTSG: Latent Topical Skip-Gram for Mutually Learning Topic Model and Vector Representations
This addresses the need for integrated learning in text mining, offering a novel approach that could enhance NLP applications, though it appears incremental as it builds on existing topic and embedding models.
The paper tackles the problem of separately trained topic models and vector representations by proposing a framework that enables them to mutually improve each other within the same corpus, using an EM-style algorithm, and it outperforms state-of-the-art methods on various NLP tasks.
Topic models have been widely used in discovering latent topics which are shared across documents in text mining. Vector representations, word embeddings and topic embeddings, map words and topics into a low-dimensional and dense real-value vector space, which have obtained high performance in NLP tasks. However, most of the existing models assume the result trained by one of them are perfect correct and used as prior knowledge for improving the other model. Some other models use the information trained from external large corpus to help improving smaller corpus. In this paper, we aim to build such an algorithm framework that makes topic models and vector representations mutually improve each other within the same corpus. An EM-style algorithm framework is employed to iteratively optimize both topic model and vector representations. Experimental results show that our model outperforms state-of-art methods on various NLP tasks.