thunlp/OpenMatch

Issues

• NQ adaptation

  #79 opened 2 years ago by Yu-Shi
  0

• avoid duplicated queries/docs generated in `Retriever`

  #77 opened 2 years ago by Yu-Shi
  0

• remove model from GPU before loading embeddings to GPU to save memory

  #75 opened 2 years ago by Yu-Shi
  0

• stream dataset bug

  #73 opened 2 years ago by Yu-Shi
  0

• eval during training DR

  #72 opened 2 years ago by Yu-Shi
  0

• Mapping Train Dataset

  #71 opened 2 years ago by OPkMn4X
  0

• reranking depth control

  #69 opened 2 years ago by Yu-Shi
  0

• support multiple run format

  #67 opened 2 years ago by Yu-Shi
  0

• remove temp files generated by reranker

  #65 opened 2 years ago by Yu-Shi
  0

• monoT5 reranker bugs

  #63 opened 2 years ago by Yu-Shi
  0

• set map_style to false by default

  #61 opened 2 years ago by Yu-Shi
  0

• Segfault

  #49 opened 2 years ago by corbyrosset
  0

• 复现Roberta-Large和ELECTRA-Large的问题

  #46 opened 3 years ago by yiyaxiaozhi
  1

• 如何处理中文数据？

  #48 opened 2 years ago by Berlin-98
  1

• electra-large和roberta-large过期

  #38 opened 3 years ago by countback
  4

• pretrained ir models different score every run

  #43 opened 3 years ago by aydv
  1

• RankSVM (OpenMatch) Coor-Ascent (OpenMatch)

  #40 opened 3 years ago by Jeryi-Sun
  3

• how is the file 'run.msmarco-passage.dev.small.trec' generated?

  #36 opened 3 years ago by KinvenW
  2

• pytorch 版本有点低，希望能支持 1.8

  #21 opened 3 years ago by harveechen
  1

• Why use gumbel softmax before sampling actions?

  #28 opened 3 years ago by KinvenW
  1

• Unable to Replicate the results for BERT-based models

  #19 opened 3 years ago by shirinssalehi
  7

• 这个msmarco-docs-firstp.tsv 文件是需要自己创建吗？

  #18 opened 4 years ago by xiaoyichao
  2

• Cannot Find File queries.train.small.tsv

  #17 opened 4 years ago by VickiCui
  2

• bert.py does not accept arguments that should be passed to transformers module

  #16 opened 4 years ago by ali-abz
  1

• ANCE firstP and maxP doc ranking leaderboard result reproduce

  #15 opened 4 years ago by jacklin64
  1

• ContrastQG code

  #12 opened 4 years ago by woshizouguo
  4

• what is the parameter score?

  #13 opened 4 years ago by gm0616
  1

• How is the ANCE FirstP training data generated?

  #14 opened 4 years ago by xyz8
  1

• Sparse Retrieval

  #11 opened 4 years ago by tangzhy
  4

• Ranking Loss

  #10 opened 4 years ago by CosimoRulli
  3

• inference.py 报错

  #9 opened 4 years ago by smart022
  1

• How to use the api to initialize model with .bin checkpoints

  #8 opened 4 years ago by zhenduow
  6

• Covoid train with reinfoselect

  #7 opened 4 years ago by xiaohong020408
  1

• How to generate TREC COVID?

  #6 opened 4 years ago by xiaohong020408
  2

• Where is dev_trec-covid-round1.jsonl ?

  #5 opened 4 years ago by xiaohong020408
  2

• Segmentation fault (core dumped)

  #4 opened 4 years ago by Maheshkumar094
  9

• The datasets

  #3 opened 4 years ago by doubleQ2018
  2

• Use OpenMatch as a library

  #2 opened 4 years ago by cmacdonald
  7

• Is valid_set needed？

  #1 opened 4 years ago by bayou3
  6