Tasks of Natural Language Processing (Draft)


Notes:

Natural language processing (NLP) is a field of computer science, artificial intelligence, and computational linguistics that deals with the interactions between computers and human (natural) languages. It focuses on the development of algorithms and models that can understand and interpret natural language, and that can be used to solve a wide range of language-related tasks and problems.

Some of the main tasks of natural language processing include:

  • Text classification and categorization: This involves automatically assigning labels or categories to text documents or sentences based on their content and meaning. For example, a text classification system might be used to classify a news article as belonging to a specific topic or category, such as politics, sports, or entertainment.
  • Sentiment analysis: This involves automatically detecting and analyzing the emotional content of text, in order to determine the overall sentiment or attitude of the writer. For example, a sentiment analysis system might be used to analyze the sentiment of customer reviews, in order to determine the overall satisfaction or dissatisfaction of the customers.
  • Named entity recognition: This involves automatically identifying and classifying named entities, such as people, organizations, locations, and dates, in text. For example, a named entity recognition system might be used to identify the names of people, places, and organizations in a news article, in order to extract important information and facts.
  • Part-of-speech tagging: This involves automatically identifying and labeling the parts of speech, such as nouns, verbs, adjectives, and adverbs, in a sentence. For example, a part-of-speech tagging system might be used to identify the different parts of speech in a sentence, in order to analyze its structure and meaning.
  • Syntactic parsing: This involves automatically analyzing the grammatical structure of a sentence, and representing it in a parse tree or other formal representation. For example, a syntactic parser might be used to analyze the structure of a sentence, in order to identify its subject, verb, and object, and to determine the relationships between different words and phrases in the sentence.

Resources:

Wikipedia:

See also:

Anaphora | Automatic Summarization | Collocation Extraction | Language Identification | Lemmatization | Linguistic Empathy | Machine Translation | Named-entity Recognition | Part-of-speech Tagging | Phrase Chunking | Relationship Extraction | Semantic Role Labeling | Shallow Parsing | Stemming | Terminology Extraction | Text Segmentation | Textual Entailment | Tokenization | Truecasing


Tasks Of Natural Language Processing

 Major Evaluations And Tasks
1) Anaphora (Anaphora Resolver) .. a type of expression whose reference depends on another referential element ..

2) Automatic Summarization (Summarizer/Summariser) .. the creation of a shortened version of a text by a computer .. [API]

3) Collocation Extraction (Collocation Extractor) .. the task of extracting collocations automatically from a corpus ..

4) Language Identification .. language detection, the process of determining which natural language given content is .. [API]

5) Lemmatization (Lemmatizer/Lemmatiser) .. the process of grouping together the different inflected forms of a word, see stemming .. [API]

6) Linguistic Empathy .. the “point of view” in an anaphoric utterance ..

7) Machine Translation .. the use of software to translate text or speech from one natural language to another .. [API]

8) Named-Entity Recognition (Named-Entity Recognizer/Recogniser) .. entity extraction seeks to locate and classify atomic elements in text .. [API]

9) Natural Language Parsing? (Natural Language Parser/Parsers) .. parsing, or more formally syntactic analysis, is the process of analyzing a text ..

10) Part-of-speech Tagging (POS Tagger/Taggers) .. the process of marking up a word in a text (corpus) as corresponding to a particular part of speech .. [API]

11) Phrase Chunking (Phrase Chunker) .. separates and segments a sentence into its subconstituents ..

12) Relation Extraction (Relation Extractor) .. the detection and classification of semantic relationship mentions within a set .. [API]

13) Semantic Role Labeling (Semantic Role Labeler/Labeller) .. the detection of the semantic arguments associated with the predicate or verb ..

14) Sentence Boundary Disambiguation (Sentence Boundary Disambiguator/Disambiguators) .. the problem of deciding where sentences begin and end ..

15) Shallow Parsing (Shallow Parser) .. (versus deep parsing) or light parsing, see chunking (chunking module) ..

16) Stemming (Stemmer) .. the process for reducing inflected, or derived, words to their stem, base or root ..

17) Terminology Extraction (Term Extraction/Extractor) .. keyword extraction, automatically extract relevant terms .. [API]

18) Text Segmentation (Text Segmenter/Segmenters) .. dividing written text into meaningful units ..

19) Textual Entailment (Textual Entailer/Entailers) .. a directional relation between text fragments ..

20) Tokenization (Tokenizer/Tokeniser) .. breaking a stream of text up into words, phrases, symbols, or other meaningful elements ..

21) Truecasing (True-casing/Truecaser) .. determining the proper capitalization of words ..

22) Word-sense Disambiguation (Word-sense Disambiguator/Disambiguators) .. the process of identifying which sense of a word is used, when the word has multiple meanings ..

1) Automatic summarization

2) Coreference resolution

3) Discourse analysis

4) Lemmatization

5) Lexical semantics

6) Machine translation

7) Morphological segmentation

8) Named entity recognition

9) Natural language generation

10) Natural language understanding

11) Optical character recognition

12) Parsing

13) Part-of-speech tagging

14) Question answering

15) Recognizing Textual entailment

16) Relationship extraction

17) Sentence breaking

18) Sentiment analysis

19) Speech recognition (Speech-to-text)

20) Speech segmentation

21) Stemming

22) Terminology extraction

23) Text-to-speech (Speech synthesis)

24) Topic segmentation

25) Word segmentation

26) Word sense disambiguation

  1. Anaphora (linguistics)
  2. Automated essay scoring
  3. Automatic hyperlinking
  4. Automatic summarization
  5. Collocation extraction
  6. Entity linking
  7. Language identification
  8. Lemmatisation
  9. Linguistic empathy
  10. Machine translation
  11. Name resolution (semantics and text extraction)
  12. Named-entity recognition
  13. Natural language parsing
  14. Neural machine translation
  15. Open information extraction
  16. Part-of-speech tagging
  17. Phrase chunking
  18. Question answering
  19. Relationship extraction
  20. Semantic parsing
  21. Semantic role labeling
  22. Sentence boundary disambiguation
  23. Shallow parsing
  24. Stemming
  25. Terminology extraction
  26. Text segmentation
  27. Text simplification
  28. Textual entailment
  29. (Tokenization?)
  30. Truecasing
  31. Word-sense disambiguation
  1. Automatic summarization
  2. Coreference resolution
  3. Discourse analysis
  4. Lemmatization
  5. Lexical semantics
  6. Machine translation
  7. Morphological segmentation
  8. Named entity recognition
  9. Natural language generation
  10. Natural language understanding
  11. Optical character recognition
  12. Parsing (Natural language parsing)
  13. Part-of-speech tagging
  14. Question answering
  15. Recognizing Textual entailment
  16. Relationship extraction
  17. Sentence breaking
  18. Sentiment analysis
  19. Speech recognition (Speech-to-text)
  20. Speech segmentation
  21. Stemming
  22. Terminology extraction
  23. Text-to-speech (Speech synthesis)
  24. Topic segmentation
  25. Word segmentation
  26. Word sense disambiguation