知识卡片
共指消解应结合文本证据
共指任务把代词或指示表达关联到先前提及对象,如人称代词与人物、there与地点。姓名统计只能是可能带偏的线索,不能替代句法、上下文和明确指代信息,更不应仅凭模型猜测决定现实人物的代词。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
- · 神经网络基础
原书出处 · 1 处
- · 查看原书依据
There is an important challenge in NLP called coreference resolution, which is when an NLP algorithm identifies the object or words associated with pronouns in natural language text.16 For example, consider the pronouns in these sentences: “Maria was born in Ukraine. Her father was a physicist. 15 years later she left there for Israel.” You may not realize it, but you resolved three coreferences in
参考来源
- 位置:《Natural Language Processing in Action, Second Edition》第05章《神经网络基础》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Natural Language Processing in Action, Second Edition/_epub-src/OEBPS/Text/chapter-5.html)
- 结论依据:摘录中关于共指消解应结合文本证据的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。
- 原始内容:There is an important challenge in NLP called coreference resolution, which is when an NLP algorithm identifies the object or words associated with pronouns in natural language text.16 For example, consider the pronouns in these sentences: “Maria was born in Ukraine. Her father was a physicist. 15 years later she left there for Israel.” You may not realize it, but you resolved three coreferences in