Informal Linguistic Utterance
- AKA: Slang.
- It can break Grammatical Conventions. (Minkov et al., 2005)
- It can contain grammatical and spelling errors. (Minkov et al., 2005)
- It can use group- and task-specific abbreviations. (Minkov et al., 2005)
- It can be (not) self-contained. (Minkov et al., 2005)
- It can be directed at a restricted audience. (Minkov et al., 2005)
- “my burton rawks dude!”
- "Mend your speech a little, lest it mar your fortune.” --William Shakespeare
- "The published word has remarkable persistence.” --Matthew & Matthew
- See: Formal Linguistic Utterance.
- 1. (linguistics) Language outside of conventional usage.
- 2. (linguistics) Language that is unique to a particular profession or subject; jargon.
- 3. (linguistics) The specialized language of a social group, sometimes used to make what is said unintelligible to those not members of the group; cant.
- (Minkov et al., 2005) ⇒ Einat Minkov, Richard C. Wang, and William W. Cohen. (2005). “Extracting Personal Names from Email: Applying named entity recognition to informal text.” In: Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing (EMNLP 2005). doi:10.3115/1220575.1220631
- QUOTE: … Important genres that do not share these properties include instant messaging logs, newsgroup postings and email messages. We refer to these genres as “informal” text. Informal text is harder to process automatically. Informal documents do not obey strict grammatical conventions. They contain grammatical and spelling errors. Further, since the audience is more restricted, informal documents often use group- and task-specific abbreviations and are not self-contained. Because of these differences, existing NER methods may require modifications to perform well on informal text.