-
诸如damo/nlp_rom_passage-ranking_chinese-base等语义相关性排序模型，目前我看是用DuReader模型进行训练的，请问是否可以支持用自己语料进行微调？
-
Hi, nice work! Congratulations on the Outstanding Paper award!
Having thoroughly reviewed the arXiv version, I find myself with a question about the results of "NovelEval". I concur with the idea o…
-
Hi
Im trying to test your ranking with Vietnamese data and got a weird result like this:
```
Query: [Đầu tư căn hộ TP. Thủ Đức - Kỳ 2] Tiềm năng lợi nhuận đầu tư căn hộ TP. Thủ Đức như thế nào??
…
-
Hi, @okhat
Thanks for the great repo! I have a hard time understanding the code for reranking. Especially in this section: https://github.com/stanford-futuredata/ColBERT/blob/706a7265b06c6b8de1e3236…
-
# [RFC] Supporting sparse semantic retrieval based on neural models
## Background
Dense retrieval based on neural models has achieved great success in search relevance tasks. However, dense methods …
-
https://arxiv.org/pdf/2010.06467.pdf
다큐먼트 랭킹의 경우 symmetric하지 않음. 따라서 semantic similarity가 qeur-document 연관성을 그대로 측정하기는
어려울 수 있음.
MS MARCO: 데이터 셋
Text ranking의 formulation은 구조화되지 않은 corpus/t…
-
closely related to https://github.com/NewGraphEnvironment/dff-2022/discussions/154 which has been actioned piece by piece through this project and others
About to add a column (`assessment_comments…
-
**Issue:**
The date:time is changing in the `date_time_start` column when reading in the `form_pscis_2023.gpkg` from Q. Using site `8478` as an example, in Q `date_time_start = 2023-09-19 13:30:02 (U…
-
Some of the text classification tasks take two inputs just like similarity models, but since the problem is text classification, widget takes only one text, which confuses users on how to pass their t…
-
**Describe the bug**
I get an error at `Chat with documents` example using colab.
Here is the prompt:
```
What is N-gram language model? Respond in one short sentence as I'm already familiar wit…