Natural Language Processing
Download as PPT, PDF3 likes933 views
The document discusses different approaches to generating biographies through natural language processing, including information extraction and language modeling. It describes using information extraction patterns learned from Wikipedia to extract fields like date of birth and place of birth, and bouncing between Wikipedia and Google search results to learn patterns for other fields with less structured data. It also proposes selecting and ranking sentences from search results to improve recall when information extraction may miss relevant sentences. The goal is to build biographies by combining these techniques for high precision on structured fields and better recall on more complex fields.
![Statistical Word Sense Disambiguation
20
Context within the sentence determines which sense is
correct
The candidate picked up [sense6] thousands of
additional votes.
He picked up [sense2] the book and started to read.
Her performance in school picked up [sense13].
The swimmers got out of the river and climbed the
bank [sloping land] to retrieve their towels.
The investors took their money out of the bank
[financial institution] and moved it into stocks and
bonds.](https://image.slidesharecdn.com/naturallanguageprocessing-141029145916-conversion-gate01/85/Natural-Language-Processing-20-320.jpg)
![34
PRODUCE A BIOGRAPHY OF [PERON].
Only these fields are Relevant:
1. Name(s), aliases:
2. *Date of Birth or Current Age:
3. *Date of Death:
4. *Place of Birth:
5. *Place of Death:
6. Cause of Death:
7. Religion (Affiliations):
8. Known locations and dates:
9. Last known address:
10. Previous domiciles:
11. Ethnic or tribal affiliations:
12. Immediate family members
13. Native Language spoken:
14. Secondary Languages spoken:
15. Physical Characteristics
16. Passport number and country of issue:
17. Professional positions:
18. Education
19. Party or other organization affiliations:
20. Publications (titles and dates):](https://image.slidesharecdn.com/naturallanguageprocessing-141029145916-conversion-gate01/85/Natural-Language-Processing-34-320.jpg)
Natural Language Processing
- 2. 2 Why “natural language”? Natural vs. artificial Language vs. English
- 3. 3 Why “natural language”? Natural vs. artificial Not precise, ambiguous, wide range of expression Language vs. English English, French, Japanese, Spanish
- 4. 4 Why “natural language”? Natural vs. artificial Not precise, ambiguous, wide range of expression Language vs. English English, French, Japanese, Spanish Natural language processing = programs, theories towards understanding a problem or question in natural language and answering it
- 5. 5 Approaches System building Interactive Understanding only Generation only Theoretical Draws on linguistics, psychology, philosophy
- 6. 6 Building an NL system is hard Unlikely to be possible without solid theoretical underpinnings
- 7. 7 Natural language is useful Question-answering systems http://tangra.si.umich.edu/clair/NSIR/NSIR.cgi Mixed initiative systems http://www.cs.columbia.edu/~noemie/match.mpg Information extraction http://nlp.cs.nyu.edu/info-extr/biomedical-snapshot.jpg Systems that write/speak http://www-2.cs.cmu.edu/~awb/synthesizers.html MAGIC Machine translation http://world.altavista.com/babelfish
- 8. 8 Topics Syntax Semantics Pragmatics Statistical NLP: combining learning and NL processing
- 9. 9 Goal of Interpretation Identify sentence meaning Do something with meaning Need some representation of action/meaning
- 10. 10 Analysis of form: Syntax Which parts were damaged by larger machines? Which parts damaged larger machines? Which larger machines damaged parts? Approaches: Statistical part of speech tagging Parsing using a grammar Shallow parsing: identify meaningful chunks
- 11. 11 Which parts were damaged by larger machines? S (Q) NP VP N NP (Q) machines V (past) damage Det (Q) N which parts ADJ larger
- 12. 12 Which parts were damaged by machines? – with functional roles S (Q) NP (SUBJ) VP N NP (Q) (OBJ) machines V (past) damage Det (Q) N which parts ADJ larger
- 13. 13 Which parts damaged machines? – with functional roles S (Q) NP (OBJ) VP N machines V (past) damage parts NP (Q) (SUBJ) Det (Q) N which ADJ larger
- 14. 14 Parsers Grammar S -> NP VP NP -> DET {ADJ*} N Different types of grammars Context Free vs. Context Sensitive Lexical Functional Grammar vs. Tree Adjoining Grammars Different ways of acquiring grammars Hand-encoded vs. machine learned Domain independent (TreeBank, Wall Street Journal) Domain dependent (Medical texts)
- 15. 15 Semantics: analysis of meaning Word meaning John picked up a bad cold John picked up a large rock. John picked up Radio Netherlands on his radio. John picked up a hitchhiker on Highway 66. Phrasal meaning Baby bonuses -> allocations Senior citizens -> personnes agees Causing havoc -> seme le dessaroi Approaches Representing meaning Statistical word disambiguation Symbolic rule-based vs. shallow statistical semantics
- 16. 16 Representing Meaning - WordNet
- 17. 17
- 18. 18 OMEGA http://omega.isi.edu:8007/index http://omega.is.edu/doc/browsers.html
- 19. 19
- 20. Statistical Word Sense Disambiguation 20 Context within the sentence determines which sense is correct The candidate picked up [sense6] thousands of additional votes. He picked up [sense2] the book and started to read. Her performance in school picked up [sense13]. The swimmers got out of the river and climbed the bank [sloping land] to retrieve their towels. The investors took their money out of the bank [financial institution] and moved it into stocks and bonds.
- 21. 21 Goal A program which can predict which sense is the correct sense given a new sentence containing “pick up” or “bank” Avoid manually itemizing all words which can occur in sentences with different meanings Can we use machine learning?
- 22. 22 What do we need? Data Features Machine Learning algorithm Decision tree vs. SVM/Naïve Bayes Inspecting the output Accuracy of these methods
- 23. 23 Using Categories from Roget’s Thesaurus (e.g., machine vs. animal) for training
- 24. 24 Training data for “machines”
- 25. 25
- 26. 26 Predicting the correct sense in unseen text Use presence of the salient words in context 50 word window Use Baye’s rule to compute probabilities for different categories
- 27. 27 “Crane” Occurred 74 times in Grolliers, 36 as animal, 38 as machine Prediction in new sentences were 99% correct Example: lift water and to grind grain .PP Treadmills attached to cranes were used to lift heavy objects from Roman times.
- 28. 28
- 29. 29
- 30. 30 Going Home – A play in one act Scene 1: Pennsylvania Station, NYC Bonnie: Long Beach? Passerby: Downstairs, LIRR Station Scene 2: ticket counter: LIRR Bonnie: Long Beach? Clerk: $4.50 Scene 3: Information Booth, LIRR Bonnie: Long Beach? Clerk: 4:19, Track 17 Scene 4: On the train, vicinity of Forest Hills Bonnie: Long Beach? Conductor: Change at Jamaica Scene 5: On the next train, vicinity of Lynbrook Bonnie: Long Beach? Conductor: Rigtht after Island Park.
- 31. 31 Question Answering on the web Input: English question Data: documents retrieved by a search engine from the web Output: The phrase(s) within the documents that answer the question
- 32. 32 Examples When was X born? When was Mozart born? Mozart was born in 1756. When was Gandhi born? Gandhi (1869-1948) Where are the Rocky Mountains located? What is nepotism?
- 33. 33 Common Approach Create a query from the question When was Mozart born -> Mozart born Use WordNet to expand terms and increase recall: Which high school was ranked highest in the US in 1998? “high school” -> (high&school)| (senior&high&school)|(senior&high(|high| highschool Use search engine to find relevant documents Pinpoint passage within document that has answer using patterns From IR to NLP
- 34. 34 PRODUCE A BIOGRAPHY OF [PERON]. Only these fields are Relevant: 1. Name(s), aliases: 2. *Date of Birth or Current Age: 3. *Date of Death: 4. *Place of Birth: 5. *Place of Death: 6. Cause of Death: 7. Religion (Affiliations): 8. Known locations and dates: 9. Last known address: 10. Previous domiciles: 11. Ethnic or tribal affiliations: 12. Immediate family members 13. Native Language spoken: 14. Secondary Languages spoken: 15. Physical Characteristics 16. Passport number and country of issue: 17. Professional positions: 18. Education 19. Party or other organization affiliations: 20. Publications (titles and dates):
- 35. 35 Biography of Han Ming Han Ming, born 1944 March in Pyongyan, South Korean Lei Fa Women’s University in French law, literature, a former female South Korean people, chairman of South Korea women’s groups,…Han, 62, has championed women’s rights and liberal political ideas. Han was imprisoned from 1979 to 1981 on charges of teaching pro-Communist ideas to workers, farmers and low-income women. She became the first minister of gender equality in 2001 and later served as an environment minister.
- 36. 36 Biography – two approaches To obtain high precision, we handle each slot independently using bootstrapping to learn IE patterns. To improve the recall, we utilize a biography Language Model.
- 37. 37 Approach Characteristics of the IE approach Training resource: Wikipedia and its manual annotations Bootstrapping interleaves two corpora to improve precision Wikipedia: reliable but small Web: noisy but many relevant documents No manual annotation or automatic tagging of corpus Use seed tuples (person, date-of-birth) to find patterns This approach is scalable for any corpus Irrespective of size Irrespective of whether it is static or dynamic The IE system is augmented with language models to increase recall
- 38. 38 Biography as an IE task We need patterns to extract information from a sentence Creating patterns manually is a time consuming task, and not scalable We want to find these patterns automatically
- 39. 39 Biography patterns from Wikipedia
- 40. 40 Biography patterns from Wikipedia • Martin Luther King, Jr., (January 15, 1929 – April 4, 1968) was the most … • Martin Luther King, Jr., was born on January 15, 1929, in Atlanta, Georgia.
- 41. 41 Run IdFinder on these sentences <Person> Martin Luther King, Jr. </Person>, (<Date>January 15, 1929</Date> – <Date> April 4, 1968</Date>) was the most… <Person> Martin Luther King, Jr. </Person>, was born on <Date> January 15, 1929 </Date>, in <GPE> Atlanta, Georgia </GPE>. Take the token sequence that includes the tags of interest + some context (2 tokens before and 2 tokens after)
- 42. 42 Convert to Patterns: <My_Person> (<My_Date> – <Date>) was the <My_Person> , was born on <My_Date>, in Remove more specific patterns – if there is a pattern that contains other, take the smallest > k tokens. <MY_Person> , was born on <My_Date> <My_Person> (<My_Date> – <Date>) Finally, verify the patterns manually to remove irrelevant patterns.
- 43. 43 Examples of Patterns: 502 distinct place-of-birth patterns: 600 <MY_Person> was born in <MY_GPE> 169 <MY_Person> ( born <Date> in <MY_GPE> ) 44 Born in <MY_GPE> <MY_Person> 10 <MY_Person> was a native <MY_GPE> 10 <MY_Person> 's hometown of <MY_GPE> 1 <MY_Person> was baptized in <MY_GPE> … 291 distinct date-of-death patterns: 770 <MY_Person> ( <Date> - <MY_Date> ) 92 <MY_Person> died on <MY_Date> 19 <MY_Person> <Date> - <MY_Date> 16 <MY_Person> died in <GPE> on <MY_Date> 3 < MY_Person> passed away on < MY_Date > 1 < MY_Person> committed suicide on <MY_Date> …
- 44. 44 Biography as an IE task This approach is good for the consistently annotated fields in Wikipedia: place of birth, date of birth, place of death, date of death Not all fields of interests are annotated, a different approach is needed to cover the rest of the slots
- 45. 45 Bouncing between Wikipedia and Google Use one seed only: <my person> and <target field> Google: “Arafat” “civil engineering”, we get:
- 46. 46
- 47. 47 Bouncing between Wikipedia and Google Use one seed only: <my person> and <target field> Google: “Arafat” “civil engineering”, we get: Þ Arafat graduated with a bachelor’s degree in civil engineering Þ Arafat studied civil engineering Þ Arafat, a civil engineering student Þ … Using these snippets, corresponding patterns are created, then filtered out manually.
- 48. 48 Bouncing between Wikipedia and Google Use one seed tuple only: <my person> and <target field> Google: “Arafat” “civil engineering”, we get: Þ Arafat graduated with a bachelor’s degree in civil engineering Þ Arafat studied civil engineering Þ Arafat, a civil engineering student Þ … Using these snippets, corresponding patterns are created, then filtered out manually To get more seed pairs, go to Wikipedia biography pages only and search for: “graduated with a bachelor’s degree in” We get:
- 49. 49
- 50. 50 Bouncing between Wikipedia and Google New seed tuples: “Burnie Thompson” “political science“ “Henrey Luke” “Environment Studies” “Erin Crocker” “industrial and management engineering” “Denise Bode” “political science” … Go back to Google and repeat the process to get more seed patterns!
- 51. 51 Bouncing between Wikipedia and Google This approach worked well for a few fields such as: education, publication, Immediate family members, and Party or other organization affiliations Did not provide good patterns for every field, such as: Religion, Ethnic or tribal affiliations, and Previous domiciles), we got a lot of noise For some slots, we created some patterns manually
- 52. 52 Biography as Sentence Selection and Ranking To obtain high recall, we also want to include sentences that IE may miss, perhaps due to ill-formed sentences (ASR and MT) Get the top 100 documents from Indri Extract all sentences that contain the person or reference to him/her Use a variety of features to rank these sentence…