Natural Language Processing · 免费预览

共指消解与实体链接

提及、所指与非指称表达，提及对与跨度排序解析算法，MUC 与 B3 评估，以及将名称链接到知识库条目。

1. Coreference Resolution and Entity Linking

Coreference Resolution and Entity Linking

2. Pairwise, ranking and span-based resolution

Pairwise, ranking and span-based resolution

3. Scoring chains with MUC and B3

Scoring chains with MUC and B3

4. Linking names to the world

Linking names to the world

5. Which it is nothing at all

In It rained hard during the crossing, and the skipper logged it in the book, what should a mention detector do with the two occurrences of it?

6. The zero that means no antecedent

In the end-to-end span-ranking coreference model, the antecedent variable ranges over earlier spans plus a dummy $\epsilon$ whose score is fixed at 0. What does scoring $\epsilon$ at exactly 0 accomplish?

7. Counting candidate spans

An end-to-end coreference model considers every contiguous span in a $21$ -word document before length truncation. How many candidate spans are there?

8. One mention's B3 recall

For a given mention, the hypothesis chain containing it has $2$ mentions, of which $1$ also appear in the gold chain, and the gold chain has $5$ mentions. Compute the mention's B3 recall, rounding to three decimals.

9. Two metrics, two philosophies

A system splits one gold four-mention chain into two two-mention chains and leaves a gold singleton untouched. How do MUC and B3 respond?

进入交互式练习

免费注册 · 即时批改 · 自动安排间隔复习。

免费开始这门课