CLLGMLDec 23, 2018

Improving Context-Aware Semantic Relationships in Sparse Mobile Datasets

arXiv:1812.09650v1
Originality Incremental advance
AI Analysis

This work addresses the problem of improving semantic understanding in sparse mobile datasets for applications like social media analysis, though it appears incremental as it builds on existing embedding methods with multimodal additions.

The paper tackled the problem of semantic similarity models failing to capture external context in sparse mobile datasets by developing algorithms that incorporate multimodal features like time and geolocation into sentence embeddings. The result showed that applying PCA with eight components and appending these features yielded a considerable improvement over pure text-based approaches for discovering similar tweets.

Traditional semantic similarity models often fail to encapsulate the external context in which texts are situated. However, textual datasets generated on mobile platforms can help us build a truer representation of semantic similarity by introducing multimodal data. This is especially important in sparse datasets, making solely text-driven interpretation of context more difficult. In this paper, we develop new algorithms for building external features into sentence embeddings and semantic similarity scores. Then, we test them on embedding spaces on data from Twitter, using each tweet's time and geolocation to better understand its context. Ultimately, we show that applying PCA with eight components to the embedding space and appending multimodal features yields the best outcomes. This yields a considerable improvement over pure text-based approaches for discovering similar tweets. Our results suggest that our new algorithm can help improve semantic understanding in various settings.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes