introduction to nlp and nlg introduction to nlp
play

Introduction to NLP and NLG Introduction to NLP Rules or - PowerPoint PPT Presentation

Introduction to NLP and NLG Introduction to NLP Rules or Statistics?? Lexical Analysis, Syntax Analysis, Semantic Analysis, Pragmatics Speech Processing (Phonetics, Punctuations, Prosody) Ambiguity Concepts


  1. Introduction to NLP and NLG

  2. Introduction to NLP ● Rules or Statistics?? ● Lexical Analysis, Syntax Analysis, Semantic Analysis, Pragmatics ● Speech Processing (Phonetics, Punctuations, Prosody) ● Ambiguity

  3. Concepts ● Tokenization “Dr. Watson, Mr. Sherlock Holmes”, said Stamford, introducing us. ‘"’ ‘Dr.’ ‘Watson’ ‘,’ ‘Mr.’ ‘Sherlock’ ‘Holmes’ ‘"’ ‘,’ ‘said’ ‘Stamford’ ‘,’ ‘introducing’ ‘us’ ‘.’ ● n-grams, collocations United States, Vice President ● Stemming “lying” -> “lie” ● Lemmatization “women” -> “woman”

  4. Concepts ● Segmentation of words and sentences ● Parts of Speech Tagging (POS) I/PRP picked/VBD up/RP a/DT ball/NN. ● Chunking : Partial Parsing [NP He ] [VP reckons ] [NP the current account deficit ] [VP will narrow ] [PP to ] [NP only $1.8 billion ] [PP in ] [NP September ] . ● Named Entity Recognition ○ Organization, Location, Date, Time, Person, Money, Facility, … ● Quantifier : Quantity Detector and Standardizer http://cogcomp.cs.illinois.edu/page/software_view/Quantifier

  5. Concepts ● Relation Extraction [ORG: ‘RPI’] in [LOC:’Troy’] ● Temporal information Extraction ● Event extraction ● Word Sense Disambiguation “I ducked as he hurled the stone at me”, “These ducks are beautiful”, “He ranged from ducks to centuries.” ● Coreference Resolution : Anaphora, Cataphora, Split Antecedent, Coreferring noun phrases, pleonasticity. ● Pronoun Resolution

  6. Concepts ● Dependency Parsing : Linking of close semantic relationships together She looks very beautiful nsubj(looks, She) acomp(looks, beautiful) advmod(beautiful, very) ● Semantic Role Labeling Parsing text into agents, actions etc.

  7. Tools ● Illinois NLP Tools (http://cogcomp.cs.illinois. edu/page/software/) ● Stanford CoreNLP (http://nlp.stanford.edu: 8080/corenlp/process) ● OpenNLP (https://opennlp.apache.org) ● NLTK (http://www.nltk.org) Shop for NLP tools throughout the web.

  8. Natural Language Generation ● Definition ● Architecture ● Example of NLG system

  9. Definition “Process of deliberately constructing a natural language text in order to meet specified communicative goals.” ~~[MacDonald, 1992]

  10. Example ( (type dailyweatherrecord) (date ((day 31) (month 05) NLG System (year 1994))) (temperature ((minimum ((unit degrees-c) (number 12))) (maximum ((unit degrees-c) (number 19))))) (rainfall ((unit millimetres) (number 3)))) The month was cooler and drier than average, with the average number of rain days,

  11. Architecture Content Determination, Communication Document Planning Document Structuring Goals Aggregation, Micro-planning Lexicalisation, Referring Knowledge Source Expression Generation Surface Realisation Linguistic Realisation NL Text

  12. NLG Systems ● OpenCCG (http://openccg.sourceforge.net) ● NLGen (http://novamente.net/example/nlp.html) ● ASTROGEN (http://people.dsv.su.se/~hercules/ASTROGEN/ASTROGEN. html) ● CLINT (http://www.cs.bgu.ac.il/~elhadad/clint.html) ● NaturalOWL (http://www.cs.bgu.ac.il/~elhadad/clint.html) ● KPML (http://www.purl.org/net/kpml) ● Multimodal Unification Grammar ( http://www.david-reitter. com/compling/mug/ )

  13. Combinatory Categorial Grammar ● Categorial Grammar : mapping from words to categories (atomic, complex) S: Sentence/Clause (S\NP) : verb phrase, intransitive verb NP: Noun phrase ((S\NP)/NP) : transitive verb (PP\NP) : Preposition N: Noun (NP/N): Determiner PP : Prepositional phrase Ref: Mark Steedman and Jason Baldridge. Combinatory Categorial Grammar. In Robert Borsley and Kersti Borjars (eds.) Constraint-based approaches to grammar: alternatives to transformational syntax. Oxford: Blackwell.

Recommend


More recommend