Enriching Word Embeddings with Temporal and Spatial Information
This addresses the need for refined semantics in time- or location-aware applications like cultural trend analysis, though it is incremental as it builds on existing embedding methods.
The authors tackled the problem of word embeddings lacking temporal and spatial information by developing a model that learns word representations conditioned on time and location, showing it captures semantics across these dimensions and compares favorably with state-of-the-art for time-specific embeddings while serving as a new benchmark for location-specific ones.
The meaning of a word is closely linked to sociocultural factors that can change over time and location, resulting in corresponding meaning changes. Taking a global view of words and their meanings in a widely used language, such as English, may require us to capture more refined semantics for use in time-specific or location-aware situations, such as the study of cultural trends or language use. However, popular vector representations for words do not adequately include temporal or spatial information. In this work, we present a model for learning word representation conditioned on time and location. In addition to capturing meaning changes over time and location, we require that the resulting word embeddings retain salient semantic and geometric properties. We train our model on time- and location-stamped corpora, and show using both quantitative and qualitative evaluations that it can capture semantics across time and locations. We note that our model compares favorably with the state-of-the-art for time-specific embedding, and serves as a new benchmark for location-specific embeddings.