-
## 🚀 Feature
Add `BaryScore`
### Sources:
- Paper: [Automatic Text Evaluation through the Lens of Wasserstein Barycenters](https://aclanthology.org/2021.emnlp-main.817.pdf) (EMNLP '21)
- [Rep…
-
Support for the Postgres vector package, _pgvector_, would make Serverpod a more viable option for working with generative AI. The primary use case is RAG (retrieval-augmented generation).
![vector…
-
@Sazan-Mahbub has volunteered to lead this section. It may grow to include others' contributions as well.
-
## 0. Paper
paper: [arxiv](https://arxiv.org/abs/1906.02715)
## 1. What is it?
They analyze contextualized word representations from BERT.
## 2. What is amazing compared to previous works?…
-
Hello. Thank you for publishing your research. While reading your SeqMix paper, I had trouble understanding the method you used to build your {word, embedding} table (as discussed in Section 3.2 and A…
-
Jurafsky, Daniel and James H. Martin. 2015. _Speech and Language Processing_. Chapter 10 [“Encoder-Decoder Models, Attention, and Contextual Embeddings"](https://web.stanford.edu/~jurafsky/slp3/10.pdf…
-
I'm using this model:
http://magnitude.plasticity.ai/elmo/medium/elmo_2x4096_512_2048cnn_2xhighway_5.5B_weights.magnitude
I've extracted ELMO embeddings for personality traits, computed pairwise…
-
### Feature Description
Anthropic has posted an impressive approach for reducing RAG errors by 67% and keeping costs reasonable in the process.
Blog post: https://www.anthropic.com/news/contextual-…
-
It would be nice to add this metric because Word Movers Distance uses information geometry and ELMo uses contextual embeddings. I'm not familiar with all of your metrics so please correct me if there …
-
https://aclanthology.org/D19-1053/