Ziyan Jiang

icon indicating a website link https://xmhzz2018.github.io/

icon company University of California, Santa Barbara icon location CS Ph.D. @ UCSB; Research focuses on Natural Language Processing & Information Retrieval.

Results 3 comments of Ziyan Jiang

Question about process_wiki_page.py

Sure! It seems this error occurs during the data loading stage, before the dataset creation. Could you please try loading any .bz2 file (just a random one) to see if...

Could not reproduce the answer recall for NQ dataset

Hi @tyu008, thanks for raising this question. First, the nq/full-00000-of-00001.parquet corresponds to the num_retrieval_units = 4 line, not the num_retrieval_units = 8 line. The QA performance has shown that the...

Could not reproduce the answer recall for NQ dataset

@tyu008 Sure! I think I know the main reason here. I avoid cross-document chunking; for example, if a new document starts, it will be in the next chunk. Previously, when...