Task of NLP
本节对NLP-progress中所总结的NLP task进行总结，分析。原文链接：https://coggle.it/diagram/W01z0KfTAjJ-vuxw/t/nlp-progress-repo
Syntax/sentence analysis
本节的这些task都是sentence级别的，与此相对的是document级别的。在sentence级别，一类重要的task就是分析sentence的syntax，在下面所列的这些sentence级别的task中，名字中包含有syntax或parsing的和此类task密切相关，有一个问题是，这些task能否处理复合句？
| Task name | Explanation | |
|---|---|---|
| CCG | ||
| Shallow syntax/Chunking | Chunking, also known as shallow parsing, identifies continuous spans of tokens that form syntactic units such as noun phrases or verb phrases. | |
| Constituency parsing | Constituency parsing aims to extract a constituency-based parse tree from a sentence that represents its syntactic structure according to a phrase structure grammar. | |
| Dependency parsing | Dependency parsing is the task of extracting a dependency parse of a sentence that represents its grammatical structure and defines the relationships between “head” words and words, which modify those heads. | |
| Part-of-speech tagging | ||
| Semantic parsing | 包括： - AMR parsing - SQL parsing |
|
| Semantic role labeling | ||
| Coreference resolution | ||
| Named entity recognition | Named entity recognition (NER) is the task of tagging entities in text with their corresponding type. Approaches typically use BIO notation, which differentiates the beginning (B) and the inside (I) of entities. O is used for non-entity tokens. |
在语言学中，使用Grammar来描述语言，在计算机科学中，parsing往往指进行语法分析，所以下面名称中带有parsing的都具有此含义。
Document analysis
顾名思义，本节所描述的task都是文档级别的。
| Task name | Explanation | |
|---|---|---|
| Sentiment analysis | Sentiment analysis is the task of classifying the polarity of a given text. | |
| Temporal processing | ||
| Question answering | ||
| Semantic textual similarity | ||
| Open Information extraction | Open Information Extraction approaches leads to creation of large Knowledge bases (KB) from the web. | |
| Text classification | ||
| Summarization |