# LG AI Research — How far has LG AI Research’s MRC Project come thus far?

- Company: LG AI Research (lgresearch.ai)
- Announced: 2021-09-09
- Category: research-paper
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://www.lgresearch.ai/blog/view?seq=141
- Record: https://forck.live/items/4982-how-far-has-lg-ai-research-s-mrc-project-come-thus-far
- Subject: EXAONE

LG AI Research describes the progress of its MRC (Machine Reading Comprehension) project, including a Korean BERT-based model that achieved KorQuAD No. 1 in July 2020, research on Open-domain QA using the R3 structure, Table MRC for understanding tabular data, and TV MRC for video content search.

## Evidence

Verbatim from https://www.lgresearch.ai/blog/view?seq=141:

> Last year, LG AI Research Language Lab successfully developed a Korean language model based on BERT (Bidirectional Encoder Representations from Transformers) to which salient span masking and stack-attention are applied. This model currently shows a performance level exceeding that of a human’s reading comprehension ( KorQuAD No. 1, July 2020 ).

---

Record: https://forck.live/items/4982-how-far-has-lg-ai-research-s-mrc-project-come-thus-far
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md