paper-with-me

Papers

Interpretable Word Embeddings via Informative Priors

2019-09-03 · IJCNLP 2019 11 · Miriam Hurtado Bodell, Martin Arvidsson, Måns Magnusson

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.

📄 PDF Abstract BibTeX arXiv:1909.01459

Code (0)

등록된 구현이 없습니다.

Tasks

Word Embeddings

Methods 이 논문이 사용한 방법론

Interpretability 설명 없음

Similar Papers 제목 키워드 기반

Identification, Interpretability, and Bayesian Word Embeddings

2019-06-01 · WS 2019 6 · Adam Lauretig

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 Embeddings

Identification, Interpretability, and Bayesian Word Embeddings

2019-04-02 · Adam M. Lauretig

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 Embeddings

Word Equations: Inherently Interpretable Sparse Word Embeddingsthrough Sparse Coding

2020-04-08 · Adly Templeton

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 Embeddings

Word Equations: Inherently Interpretable Sparse Word Embeddings through Sparse Coding

2021-11-01 · EMNLP (BlackboxNLP) 2021 11 · Adly Templeton

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 Embeddings

SPINE: SParse Interpretable Neural Embeddings

2017-11-23 · Anant Subramanian, Danish Pruthi, Harsh Jhamtani, Taylor Berg-Kirkpatrick 외

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