-
**Describe the bug**
I have created an index with very specific tweet texts and then a simple pipeline along the lines of
`
pipeline = (tuned_bm25 >>
pt.text.get_text(index_ref, ["r…
-
Hi.
Thank you for this great package!
I am trying to use the semantic search example in order to detect sentences belonging to specific topics. I translated the different topics to query sentences…
-
Based on what I know, how the Embeddings underlying feature works is the same as the bi-encoder method. If I am using a model that is not trained to be used in a bi-encoder method like this [bert-mult…
-
Hi, I am Gordon Lee.
Sorry to bother you with this issue.
Thanks for your excellent work on sematic-retrieval models.
Recently, MLNLP and I have made a search tool to collect top-tier conference up…
-
_jaydesen created the following on Feb 01:_
Plan is to use AS2 for selecting a diverse set of top ranked sentences and then train a generative pipeline using ELI5 data.
An example from ELI5 dat…
-
The FST uses a single contiguous byte[] under the hood, which in java is indexed by int so we cannot grow this over Integer.MAX_VALUE. It also internally encodes references to this array as vInt.
We…
-
I'm trying to reproduce the BLEU score reported at http://matrix.statmt.org/matrix/output/1914?score_id=37605 and described here https://github.com/pytorch/fairseq/tree/master/examples/wmt19
Would …
-
**Question**
I'm using Haystack to search a massive website, including webpage, documents, social network pages related to that website.
The website has several topics, one of them is about IoT (…
-
This issue is a WIP!
## Background
This issue is not about any user-facing features of BM25. The general idea is that we want to develop user-facing features that make use of BM25 and therefore …
-
I found you have uploaded the ' monot5-large-msmarco' on huggingface. You said, "For more details on how to use it, check pygaggle.ai" However, I cannot find where is 'pygaggle.ai'...
Can you share…