Interpretable Word Embeddings via Informative Priors
Word embeddings have demonstrated strong performance on NLP tasks. However, lack of interpretability and the unsupervised nature of word embeddings have limited their use within computational social science and digital humanities. We propose the use of informative priors to create interpretable and domain-informed dimensions for probabilistic word embeddings. Experimental results show that sensible priors can capture latent semantic concepts better than or on-par with the current state of the art, while retaining the simplicity and generalizability of using priors.
Code (0)
등록된 구현이 없습니다.
Tasks
Word EmbeddingsMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Identification, Interpretability, and Bayesian Word Embeddings
Social scientists have recently turned to analyzing text using tools from natural language processing like word embeddings to measure concepts like ideology, bias, and affinity. However, word embeddings are difficult to …
regressionWord EmbeddingsIdentification, Interpretability, and Bayesian Word Embeddings
Social scientists have recently turned to analyzing text using tools from natural language processing like word embeddings to measure concepts like ideology, bias, and affinity. However, word embeddings are difficult to …
regressionWord EmbeddingsWord Equations: Inherently Interpretable Sparse Word Embeddingsthrough Sparse Coding
Word embeddings are a powerful natural language processing technique, but they are extremely difficult to interpret. To enable interpretable NLP models, we create vectors where each dimension is inherently interpretable.…
Word EmbeddingsWord Equations: Inherently Interpretable Sparse Word Embeddings through Sparse Coding
Word embeddings are a powerful natural language processing technique, but they are extremely difficult to interpret. To enable interpretable NLP models, we create vectors where each dimension is inherently interpretable.…
Word EmbeddingsSPINE: SParse Interpretable Neural Embeddings
Prediction without justification has limited utility. Much of the success of neural models can be attributed to their ability to learn rich, dense and expressive representations. While these representations capture the u…
DenoisingWord Embeddings