-
I was trying to reproduce the [MSMARCO Passage Retrieval experiment](https://github.com/castorini/pyserini/blob/master/docs/experiments-msmarco-passage.md) with the conda setup on Ubuntu using the Win…
-
The standard analyzer in lucene is not exactly unicode-friendly with regards to breaking text into words, especially with respect to non-alphabetic scripts. This is because it is unaware of unicode b…
-
**Describe your proposal/problem**
Adding models for retrieving / Question answering like :
- Dense passage retrieval (DPR)
- Retrieval Augmented generation (Rag)
- Fusion in the decoder (Fid)
…
-
**Describe the bug**
Index fail to be saved after retrieval training and embedding update, getting `TypeError: Object of type IndexFlat is not JSON serializable`. This also corrupt the existing index…
-
**Describe the bug**
Encounter an error while trying out the tutorial 9 for running a pre-existing DPR model on a custom dataset.
**Error message**
File "/projects/mrqa_jars/emanual/emanual/code…
-
@okhat
I am trying to use ColBERT for a document retrieval project I am working on and I'd like to ask if I have understood the procedure correctly. I am trying to perform a ranking task based on th…
-
Hi Jinhyuk,
I was trying to reproduce the third row of Table 1 in your paper (https://arxiv.org/pdf/2109.08133.pdf). I'm using the index and pre-trained ckpt on NQ you gave me several days ago. Her…
-
The [code for text extraction in BM25](https://github.com/princeton-nlp/EntityQuestions/blob/5da38e18ae03d7d134c4476712c0e10713e97185/bm25/bm25_retriever.py#L39) seems to incorrectly include the title…
-
- [x] Choose ~two~ one simple baseline model~s~ to assess based on model types and datasets they're trained on
- [x] Pick performance metric(s) (IOU? Better quality text?)
- [x] Assess performance of …
-
## Davinci (`OpenAI error: That model is currently overloaded with other requests. You can retry your request, or contact support@openai.com if the error persists. (Please include the request ID 1c1cb…