Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.
Information Extraction with
Linked Data
Isabelle Augenstein
Department of Computer Science, University of Sheffield, UK
i....
2Why Information Extraction?
Isabelle Augenstein
3Why Information Extraction?
Isabelle Augenstein
semi-structured information
unstructured information
4Why Information Extraction?
semi-structured information
unstructured information
How to link this information to a
knowle...
5Why Information Extraction?
semi-structured information
unstructured information
How to link this information to a
knowle...
6
Information Extraction
Isabelle Augenstein
The Arctic Monkeys almost exclusively played songs from their
new album AM at...
7
Information Extraction
Isabelle Augenstein
The Arctic Monkeys almost exclusively played songs from their
new album AM at...
8
Information Extraction
Isabelle Augenstein
The Arctic Monkeys almost exclusively played songs from their
new album AM at...
9
Information Extraction
Isabelle Augenstein
The Arctic Monkeys almost exclusively played songs from their
new album AM at...
10
Named Entities: Definition
Named Entities: Proper nouns, which refer to real-life entities
Named Entity Recognition: De...
11
Relations
Isabelle Augenstein
The Arctic Monkeys almost exclusively played songs from their
new album AM at Summerfest ...
12
Relations
Isabelle Augenstein
The Arctic Monkeys almost exclusively played songs from their
new album AM at Summerfest ...
13
Relations
Isabelle Augenstein
The Arctic Monkeys almost exclusively played songs from their
new album AM at Summerfest ...
14
Relations, Time Expressions
and Events: Definition
Relations: Two or more entities which relate to one another in
real ...
15
Summary: Introduction
•  Information extraction (IE) methods such as named entity
recognition (NER), named entity class...
16
NERC: Methods
•  Possible methodologies
•  Rule-based approaches: write manual extraction rules
•  Machine learning bas...
17
NERC: Methods
Developing a NERC involves programming based around APIs..
Isabelle Augenstein
18
NERC: Methods
Developing a NERC involves programming based around APIs..
which can be frustrating at times
Isabelle Aug...
19
NERC: Methods
and (at least basic) knowledge about linguistics
Isabelle Augenstein
20
Background: Linguistics
Sentences
Tokens
Morphemes
Words
Sentences
Meaning
Isabelle Augenstein
Lexicon
Morphology
The f...
21
Background: NLP Tasks
Sentences
Tokens
Morphemes
Words
Sentences
Meaning
Isabelle Augenstein
Sentence splitting
Tokenis...
22
Background: Linguistics
Sentences
Tokens
Morphemes
Words
Sentences
Meaning
Isabelle Augenstein
New York-basedLexicon
Mo...
23
Background: Linguistics
Sentences
Tokens
Morphemes
Words
Sentences
Meaning
Isabelle Augenstein
New York-based
[New, Yor...
24
Background: Linguistics
Sentences
Tokens
Morphemes
Words
Sentences
Meaning
Isabelle Augenstein
Lexicon
Morphology
Synta...
25
Background: Linguistics
Sentences
Tokens
Morphemes
Words
Sentences
Meaning
Isabelle Augenstein
Lexicon
Morphology
Synta...
26
Background: Linguistics
Sentences
Tokens
Morphemes
Words
Sentences
Meaning
Isabelle Augenstein
Lexicon
Morphology
Synta...
27
Background: Linguistics
Sentences
Tokens
Morphemes
Words
Sentences
Meaning
Isabelle Augenstein
Lexicon
Morphology
Synta...
28
Background: Linguistics
Sentences
Tokens
Morphemes
Words
Sentences
Meaning
Isabelle Augenstein
Lexicon
Morphology
Synta...
29
Background: Linguistics
Sentences
Tokens
Morphemes
Words
Sentences
Meaning
Isabelle Augenstein
Lexicon
Morphology
Synta...
30
Background: Linguistics
Sentences
Tokens
Morphemes
Words
Sentences
Meaning
Isabelle Augenstein
Lexicon
Morphology
Synta...
31
Background: Linguistics
Sentences
Tokens
Morphemes
Words
Sentences
Meaning
Isabelle Augenstein
Lexicon
Morphology
Synta...
32
Background: Linguistics
Sentences
Tokens
Morphemes
Words
Sentences
Meaning
Isabelle Augenstein
Lexicon
Morphology
Synta...
33
Background: Linguistics
Sentences
Tokens
Morphemes
Words
Sentences
Meaning
Isabelle Augenstein
Lexicon
Morphology
Synta...
34
Information Extraction
Language is ambiguous..
Can we still build named entity extractors that extract all
entities fro...
35
Information Extraction
Language is ambiguous..
Can we still build named entity extractors that extract all
entities fro...
36
Information Extraction
Language is ambiguous..
Can we still build named entity extractors that extract all
entities fro...
37
NERC: Features
What can help to recognise and/or classify named entities?
•  Words:
•  Words in window before and after...
38
NERC: Features
What can help to recognise and/or classify named entities?
•  Morphology:
•  Capitalisation: is upper ca...
39
NERC: Features
What can help to recognise and/or classify named entities?
•  POS (part of speech) tags
•  Most named en...
40Morphology: Penn Treebank POS tags
41Morphology: Penn Treebank POS tags
Nouns
(all start
with N)
Verbs (all
start with V)
Adjectives
(all start
with J)
42
NERC: Features
What can help to recognise and/or classify named entities?
•  POS (part of speech) tags
•  Most named en...
43
NERC: Features
What can help to recognise and/or classify named entities?
•  Gazetteers
•  Retrieved from HTML lists or...
44
NERC: Training Models
Extensive choice of machine learning algorithms for training NERCs
45
NERC: Training Models
•  Unfortunately, there isn’t enough time to explain machine learning
algorithms in detail
•  CRF...
46
NLP & ML Software
Natural Language Processing:
-  GATE (general purpose architecture, includes other NLP and ML
softwar...
47
NLP & ML Software
Ready to use NERC software:
-  ANNIE (rule-based, part of GATE)
-  Wikifier (based on Wikipedia)
-  F...
48
Application: Opinion Mining
•  Extracting opinions or sentiments in text
•  It’s about finding out what people think
Un...
49
Application: Opinion Mining
•  Opinion Mining is big business
•  Someone just bought an album by a
music artist
•  Writ...
50
Application: Opinion Mining
•  “Miley Cyrus's attempts to shock would be
more effective if she had songs to back up
the...
51
Application: Opinion Mining
Why is opinion mining and sentiment analysis challenging?
•  Relatively easy to find sentim...
52
Application: Opinion Mining
Why is opinion mining and sentiment analysis challenging?
•  Relatively easy to find sentim...
53
Application: Opinion Mining
Why is opinion mining and sentiment analysis challenging?
•  Relatively easy to find sentim...
54
Application: Opinion Mining
Why is opinion mining and sentiment analysis challenging?
•  Relatively easy to find sentim...
55
Application: Opinion Mining
Why is opinion mining and sentiment analysis challenging?
•  Relatively easy to find sentim...
56
Application: Opinion Mining
Why is opinion mining and sentiment analysis challenging?
•  It’s not just about finding se...
57
Application: Opinion Mining
Why is opinion mining and sentiment analysis challenging?
•  How much should every single o...
58
Application: Opinion Mining
Subtopics
•  Opinion extraction: extract the piece of text which represents the
opinion
•  ...
59
Application: Opinion Mining
Subtopics
•  Feature-opinion association: given a text with target features and
opinions ex...
60
Application: Opinion Mining
Opinion Mining Resources
Bing Liu’s English Sentiment Lexicon
•  2006 pos words, 4783 neg w...
61
Application: Opinion Mining
Opinion Mining Resources
WordNet Affect
•  Extension of WordNet with affect words
•  Useful...
62Information Extraction with Linked Data
Thank you for
your attention!(And thank you to Diana Maynard for allowing me to ...
Upcoming SlideShare
Loading in …5
×

Information Extraction with Linked Data

1,342 views

Published on

Slides for my tutorial at the ESWC Summer School 2015, giving an introduction to information extraction with Linked Data and an introduction to one of the applications of information extraction, opinion mining.

Published in: Software

Information Extraction with Linked Data

  1. 1. Information Extraction with Linked Data Isabelle Augenstein Department of Computer Science, University of Sheffield, UK i.augenstein@sheffield.ac.uk 2 September 2015 Information Extraction with Linked Data Tutorial, ESWC Summer School 2015
  2. 2. 2Why Information Extraction? Isabelle Augenstein
  3. 3. 3Why Information Extraction? Isabelle Augenstein semi-structured information unstructured information
  4. 4. 4Why Information Extraction? semi-structured information unstructured information How to link this information to a knowledge base automatically?
  5. 5. 5Why Information Extraction? semi-structured information unstructured information How to link this information to a knowledge base automatically? Information Extraction!
  6. 6. 6 Information Extraction Isabelle Augenstein The Arctic Monkeys almost exclusively played songs from their new album AM at Summerfest 2014 at Miller Lite Oasis in Milwaukee on 25 June 2014.
  7. 7. 7 Information Extraction Isabelle Augenstein The Arctic Monkeys almost exclusively played songs from their new album AM at Summerfest 2014 at Miller Lite Oasis in Milwaukee on 25 June 2014. Named Entity Recognition
  8. 8. 8 Information Extraction Isabelle Augenstein The Arctic Monkeys almost exclusively played songs from their new album AM at Summerfest 2014 at Miller Lite Oasis in Milwaukee on 25 June 2014. Named Entity Recognition Named Entity Classification (NEC): Arctic Monkeys: mo:MusicArtist AM: mo:SignalGroup Summerfest 2014: mo:Festival Miller Lite Oases: geo:SpatialThing Milwaukee: geo:SpatialThing
  9. 9. 9 Information Extraction Isabelle Augenstein The Arctic Monkeys almost exclusively played songs from their new album AM at Summerfest 2014 at Miller Lite Oasis in Milwaukee on 25 June 2014. Named Entity Recognition Named Entity Classification (NEC): Named Entity Linking (NEL): Arctic Monkeys: mo:MusicArtist Arctic Monkeys: mo:artist/ada7a83 ... AM: mo:SignalGroup AM: mo:release-group/a348ba2f-f8b3 … Summerfest 2014: mo:Festival Summerfest 2014: mo:event/3fc3 … Miller Lite Oases: geo:SpatialThing Miller Lite Oases: mo:place/3f26acf … Milwaukee: geo:SpatialThing Milwaukee: mo:area/4dc3fa97-cf9b- …
  10. 10. 10 Named Entities: Definition Named Entities: Proper nouns, which refer to real-life entities Named Entity Recognition: Detecting boundaries of named entities (NEs) Named Entity Classification: Assigning classes to NEs, such as PERSON, LOCATION, ORGANISATION, MISC or fine-grained classes such as SIGNAL GROUP Named Entity Linking / Disambiguation: Linking NEs to concrete entries in knowledge base, example: Milwaukee -> LOC: largest city in the U.S. state of Wisconsin -> LOC: Milwaukee, Oregon, named after the city in Wisconsin -> LOC: Milwaukee County, Wisconsin -> ORG: Milwaukee Tool Corp, a manufacturer of electric power tools -> MISC: early codename for what was to become the Macintosh II -> …
  11. 11. 11 Relations Isabelle Augenstein The Arctic Monkeys almost exclusively played songs from their new album AM at Summerfest 2014 at Miller Lite Oasis in Milwaukee on 25 June 2014. Named Entity Recognition Relation Extraction foaf:made gn:parentFeature mo:Festival
  12. 12. 12 Relations Isabelle Augenstein The Arctic Monkeys almost exclusively played songs from their new album AM at Summerfest 2014 at Miller Lite Oasis in Milwaukee on 25 June 2014. Named Entity Recognition Relation Extraction Temporal Extraction foaf:made gn:parentFeature mo:Festival 2014-06-25
  13. 13. 13 Relations Isabelle Augenstein The Arctic Monkeys almost exclusively played songs from their new album AM at Summerfest 2014 at Miller Lite Oasis in Milwaukee on 25 June 2014. Named Entity Recognition Relation Extraction Temporal Extraction foaf:made gn:parentFeature mo:Festival 2014-06-25 Event Extraction Event: mo:Festival: Summerfest 2014 foaf:Agent: Arctic Monkeys time:TemporalEntity: 2014-06-25 geo:SpatialThing: Miller Lite Oasis
  14. 14. 14 Relations, Time Expressions and Events: Definition Relations: Two or more entities which relate to one another in real life Relation Extraction: Detecting relations between entities and assigning relation types to them, such as LOCATED-IN Temporal Extraction: Recognising and normalising time expressions: times (e.g. “3 in the afternoon”), dates (“tomorrow”), durations (“since yesterday”), and sets (e.g. “twice a month”) Events: Real-life events that happened at some point in space and time, e.g. music festival, album release Event Extraction: Extracting events consisting of the name and type of event, agent, time and location
  15. 15. 15 Summary: Introduction •  Information extraction (IE) methods such as named entity recognition (NER), named entity classification (NEC), named entity linking, relation extraction (RE), temporal extraction, and event extraction can help to add markup to Web pages •  Information extraction approaches can serve two purposes: •  Annotating every single mention of an entity, relation or event, e.g. to add markup to Web pages •  Aggregating those mentions to populate knowledge bases, e.g. based on confidence values and majority voting Milwaukee LOC 0.9 Milwaukee LOC 0.8 Milwaukee ORG 0.4 à Milwaukee LOC Isabelle Augenstein
  16. 16. 16 NERC: Methods •  Possible methodologies •  Rule-based approaches: write manual extraction rules •  Machine learning based approaches •  Supervised learning: manually annotate text, train machine learning model •  Unsupervised learning: extract language patterns, cluster similar ones •  Semi-supervised learning: start with a small number of language patterns, iteratively learn more (bootstrapping) •  Gazetteer-based method: use existing list of named entities •  Combination of the above Isabelle Augenstein
  17. 17. 17 NERC: Methods Developing a NERC involves programming based around APIs.. Isabelle Augenstein
  18. 18. 18 NERC: Methods Developing a NERC involves programming based around APIs.. which can be frustrating at times Isabelle Augenstein
  19. 19. 19 NERC: Methods and (at least basic) knowledge about linguistics Isabelle Augenstein
  20. 20. 20 Background: Linguistics Sentences Tokens Morphemes Words Sentences Meaning Isabelle Augenstein Lexicon Morphology The farmer hit the donkey. Syntax Lexicon Semantics, Discourse The, farmer, hit, the, donkey, . wait + ed -> waited, cat -> cat wait -> V, cat -> N The (D) farmer (N) hit (V) the (D) donkey (N). NP Every farmer who owns a donkey beats it. ∀x∀y (farmer(x) ∧ donkey(y) ∧ own(x, y) → beat(x, y)) NP
  21. 21. 21 Background: NLP Tasks Sentences Tokens Morphemes Words Sentences Meaning Isabelle Augenstein Sentence splitting Tokenisation Lexicon Morphology Syntax Lemmatisation or stemming, part of speech (POS) tagging Chunking, parsing Lexicon Semantics, Discourse Semantic and discourse analysis, anaphora resolution
  22. 22. 22 Background: Linguistics Sentences Tokens Morphemes Words Sentences Meaning Isabelle Augenstein New York-basedLexicon Morphology Syntax Lexicon Semantics, Discourse
  23. 23. 23 Background: Linguistics Sentences Tokens Morphemes Words Sentences Meaning Isabelle Augenstein New York-based [New, York-based] or [New, York, -, based] Lexicon Morphology Syntax Lexicon Semantics, Discourse
  24. 24. 24 Background: Linguistics Sentences Tokens Morphemes Words Sentences Meaning Isabelle Augenstein Lexicon Morphology Syntax Lexicon She’d Semantics, Discourse New York-based [New, York-based] or [New, York, -, based]
  25. 25. 25 Background: Linguistics Sentences Tokens Morphemes Words Sentences Meaning Isabelle Augenstein Lexicon Morphology Syntax Lexicon She’d -> she would, she had Semantics, Discourse New York-based [New, York-based] or [New, York, -, based]
  26. 26. 26 Background: Linguistics Sentences Tokens Morphemes Words Sentences Meaning Isabelle Augenstein Lexicon Morphology Syntax Lexicon She’d -> she would, she had Semantics, Discourse New York-based [New, York-based] or [New, York, -, based] Time flies like an arrow
  27. 27. 27 Background: Linguistics Sentences Tokens Morphemes Words Sentences Meaning Isabelle Augenstein Lexicon Morphology Syntax Lexicon She’d -> she would, she had Semantics, Discourse New York-based [New, York-based] or [New, York, -, based] Time flies(V/N) like(V/P) an arrow
  28. 28. 28 Background: Linguistics Sentences Tokens Morphemes Words Sentences Meaning Isabelle Augenstein Lexicon Morphology Syntax Lexicon She’d -> she would, she had Semantics, Discourse New York-based [New, York-based] or [New, York, -, based] Time flies(V/N) like(V/P) an arrow The woman saw the man with the binoculars.
  29. 29. 29 Background: Linguistics Sentences Tokens Morphemes Words Sentences Meaning Isabelle Augenstein Lexicon Morphology Syntax Lexicon She’d -> she would, she had Semantics, Discourse New York-based [New, York-based] or [New, York, -, based] Time flies(V/N) like(V/P) an arrow The woman saw the man with the binoculars. -> Who had the binoculars?
  30. 30. 30 Background: Linguistics Sentences Tokens Morphemes Words Sentences Meaning Isabelle Augenstein Lexicon Morphology Syntax Lexicon She’d -> she would, she had Semantics, Discourse New York-based [New, York-based] or [New, York, -, based] Time flies(V/N) like(V/P) an arrow The woman saw the man with the binoculars. -> Who had the binoculars? Somewhere in Britain, some woman has a child every thirty seconds.
  31. 31. 31 Background: Linguistics Sentences Tokens Morphemes Words Sentences Meaning Isabelle Augenstein Lexicon Morphology Syntax Lexicon She’d -> she would, she had Semantics, Discourse New York-based [New, York-based] or [New, York, -, based] Time flies(V/N) like(V/P) an arrow The woman saw the man with the binoculars. -> Who had the binoculars? Somewhere in Britain, some woman has a child every thirty seconds. -> Same woman or different women?
  32. 32. 32 Background: Linguistics Sentences Tokens Morphemes Words Sentences Meaning Isabelle Augenstein Lexicon Morphology Syntax Lexicon She’d -> she would, she had Semantics, Discourse New York-based [New, York-based] or [New, York, -, based] Time flies(V/N) like(V/P) an arrow The woman saw the man with the binoculars. -> Who had the binoculars? Somewhere in Britain, some woman has a child every thirty seconds. -> Same woman or different women? Ambiguities on every level
  33. 33. 33 Background: Linguistics Sentences Tokens Morphemes Words Sentences Meaning Isabelle Augenstein Lexicon Morphology Syntax Lexicon She’d -> she would, she had Semantics, Discourse New York-based [New, York-based] or [New, York, -, based] Time flies(V/N) like(V/P) an arrow The woman saw the man with the binoculars. -> Who had the binoculars? Somewhere in Britain, some woman has a child every thirty seconds. -> Same woman or different women? Ambiguities on every level Y U SO AMBIGUOUS?
  34. 34. 34 Information Extraction Language is ambiguous.. Can we still build named entity extractors that extract all entities from unseen text correctly? Isabelle Augenstein
  35. 35. 35 Information Extraction Language is ambiguous.. Can we still build named entity extractors that extract all entities from unseen text correctly? Isabelle Augenstein
  36. 36. 36 Information Extraction Language is ambiguous.. Can we still build named entity extractors that extract all entities from unseen text correctly? However, we can try to extract most of them correctly using linguistic cues and background knowledge! Isabelle Augenstein
  37. 37. 37 NERC: Features What can help to recognise and/or classify named entities? •  Words: •  Words in window before and after mention •  Sequences •  Bags of words Summerfest 2014 took place at Miller Lite Oasis in Milwaukee on 25 June 2014. w: Milwaukee w-1: in w-2: Oasis w+1: on w+2: 25 seq[-]: Oasis in seq[+]: on 25 bow: Milwaukee bow[-]: in bow[-]: Oasis bow[+]: on bow[+]: 25 Isabelle Augenstein
  38. 38. 38 NERC: Features What can help to recognise and/or classify named entities? •  Morphology: •  Capitalisation: is upper case (China), all upper case (IBM), mixed case (eBay) •  Symbols: contains $, £, €, roman symbols (IV), .. •  Contains period (google.com), apostrophe (Mandy’s), hyphen (speed-o- meter), ampersand (Fisher & Sons) •  Stem or Lemma (cats -> cat), prefix (disadvantages -> dis), suffix (cats -> s), interfix (speed-o-meter -> o) Isabelle Augenstein
  39. 39. 39 NERC: Features What can help to recognise and/or classify named entities? •  POS (part of speech) tags •  Most named entities are nouns •  Prokofyev (2014) Isabelle Augenstein 4.1 Part-of-Speech Tags Part-Of-Speech (POS) tags have often been considered as an important discriminative feature for term identification. Many works on key term identification apply either fixed or regular expression POS tag patterns to improve their ef- fectiveness. Nonetheless, POS tags alone cannot produce high-quality results. As can be seen from the overall POS tag distribution graph extracted from one of our collections (see Figure 3), many of the most frequent tag patterns (e.g., JJ NN tagging adjectives and nouns6 ) are far from yielding perfect results. Figure 3: Top 6 most frequent part-of-speech tag comma, while the n-gram “au tion”, which is indeed a valid the beginning or at the end The contingency tables giv trate this: The +punctuation respectively, the counts of the punctuation mark in any of of the n-grams that have no occurrences. From the tables of punctuation marks (+pun an n-gram occurs twice as o valid entities compared to th that the absence of punctuat pens less frequently for the va ones. Table 1: Contingency ta appearing immediately be Va +punctuation 16 punctuation 65 Totals 81 Table 2: Contingency ta appearing immediately af Va
  40. 40. 40Morphology: Penn Treebank POS tags
  41. 41. 41Morphology: Penn Treebank POS tags Nouns (all start with N) Verbs (all start with V) Adjectives (all start with J)
  42. 42. 42 NERC: Features What can help to recognise and/or classify named entities? •  POS (part of speech) tags •  Most named entities are nouns •  Prokofyev (2014) Isabelle Augenstein 4.1 Part-of-Speech Tags Part-Of-Speech (POS) tags have often been considered as an important discriminative feature for term identification. Many works on key term identification apply either fixed or regular expression POS tag patterns to improve their ef- fectiveness. Nonetheless, POS tags alone cannot produce high-quality results. As can be seen from the overall POS tag distribution graph extracted from one of our collections (see Figure 3), many of the most frequent tag patterns (e.g., JJ NN tagging adjectives and nouns6 ) are far from yielding perfect results. Figure 3: Top 6 most frequent part-of-speech tag comma, while the n-gram “au tion”, which is indeed a valid the beginning or at the end The contingency tables giv trate this: The +punctuation respectively, the counts of the punctuation mark in any of of the n-grams that have no occurrences. From the tables of punctuation marks (+pun an n-gram occurs twice as o valid entities compared to th that the absence of punctuat pens less frequently for the va ones. Table 1: Contingency ta appearing immediately be Va +punctuation 16 punctuation 65 Totals 81 Table 2: Contingency ta appearing immediately af Va
  43. 43. 43 NERC: Features What can help to recognise and/or classify named entities? •  Gazetteers •  Retrieved from HTML lists or tables [1] •  Using regular expressions patterns and search engines (e.g. “Popular artists such as * ”) •  Retrieved from knowledge bases [1] https://en.wikipedia.org/wiki/Billboard_200 Isabelle Augenstein
  44. 44. 44 NERC: Training Models Extensive choice of machine learning algorithms for training NERCs
  45. 45. 45 NERC: Training Models •  Unfortunately, there isn’t enough time to explain machine learning algorithms in detail •  CRFs (conditional random fields) are one of the most widely used algorithms for NERC •  Graphical models, view NERC as a sequence labelling task •  Named entities consist of a beginning token (B), inside tokens (I), and outside tokens (O) took(O) place(O) at(O) Miller(B-LOC) Lite(I-LOC) Oasis(I-LOC) in(O) •  For now, we will rule- and gazetteer-based NERC •  It is fairly easy to write manual extraction rules for NEs, can achieve a high performance when combined with gazetteers •  This can be done with the GATE software (general architecture for text engineering) and Jape rules -> Hands-on session Isabelle Augenstein
  46. 46. 46 NLP & ML Software Natural Language Processing: -  GATE (general purpose architecture, includes other NLP and ML software as plugins) -  Stanford NLP (Java) -  OpenNLP (Java) -  NLTK (Python) Machine Learning: -  scikit-learn (Python, rich documentation, highly recommended!) -  Mallet (Java) -  WEKA (Java) -  Alchemy (graphical models, Java) -  FACTORIE, wolfe (graphical models, Scala) -  CRFSuite (efficient implementation of CRFs, Python) Isabelle Augenstein
  47. 47. 47 NLP & ML Software Ready to use NERC software: -  ANNIE (rule-based, part of GATE) -  Wikifier (based on Wikipedia) -  FIGER (based on Wikipedia, fine-grained Freebase NE classes) Almost ready to use NERC software: -  CRFSuite (already includes Python implementation for feature extraction, you just need to feed it with training data, which you can also download) Ready to use RE software: -  ReVerb (Open IE, extracts patterns for any kind of relation) -  MultiR (Distant supervision, relation extractor trained on Freebase) Web Content Extraction software: -  Boilerpipe (extract main text content from Web pages) -  Jsoup (traverse elements of Web pages individually, also allows to extract text) Isabelle Augenstein
  48. 48. 48 Application: Opinion Mining •  Extracting opinions or sentiments in text •  It’s about finding out what people think University of Sheffield, NLP It's about finding out what people think...
  49. 49. 49 Application: Opinion Mining •  Opinion Mining is big business •  Someone just bought an album by a music artist •  Writes a review about it •  Someone else wants to buy an album •  Looks up reviews by fans and music critics •  Music artist and music producer •  Get feedback from fans •  Improve their product •  Improve their marketing strategy
  50. 50. 50 Application: Opinion Mining •  “Miley Cyrus's attempts to shock would be more effective if she had songs to back up the posturing.” – The Guardian •  “Bangerz is an Amazing album with great lyrics and we can see the Miley Cyrus' musical evolution. Would love to buy it and I already did. ALBUM OF THE YEAR. Peace” – Rodolfoalmeida3
  51. 51. 51 Application: Opinion Mining Why is opinion mining and sentiment analysis challenging? •  Relatively easy to find sentiment words in sentences, difficult to identify which topic they are about
  52. 52. 52 Application: Opinion Mining Why is opinion mining and sentiment analysis challenging? •  Relatively easy to find sentiment words in sentences, difficult to identify which topic they are about •  “The album comes with a free bonus CD but I don't like the cover art much.” Does this refer to the cover art of the bonus CD or the album?
  53. 53. 53 Application: Opinion Mining Why is opinion mining and sentiment analysis challenging? •  Relatively easy to find sentiment words in sentences, difficult to identify which topic they are about
  54. 54. 54 Application: Opinion Mining Why is opinion mining and sentiment analysis challenging? •  Relatively easy to find sentiment words in sentences, difficult to identify which topic they are about •  Whitney Houston was quite unpopular… University of Sheffield, NLP Whitney Houston wasn't very popular...
  55. 55. 55 Application: Opinion Mining Why is opinion mining and sentiment analysis challenging? •  Relatively easy to find sentiment words in sentences, difficult to identify which topic they are about •  Whitney Houston was quite unpopular… or was she? •  Death confuses opinion mining tools University of Sheffield, NLP Or was she?
  56. 56. 56 Application: Opinion Mining Why is opinion mining and sentiment analysis challenging? •  It’s not just about finding sentiment words, context is important too •  “It's a great movie if you have the taste and sensibilities of a 5- year-old boy.” •  “It's terrible Candidate X did so well in the debate last night.” •  “I'd have liked the track a lot more if it had been a bit shorter.” •  If sentiment words are neutral, negative or positive depends on domain •  “a long track” vs “a long walk” vs “a long battery life”
  57. 57. 57 Application: Opinion Mining Why is opinion mining and sentiment analysis challenging? •  How much should every single opinion be worth? •  experts vs non-experts •  relationship trust •  reputation trust •  spammers •  frequent vs infrequent posters •  “experts” in one area may not be expert in another •  how frequently do other people agree?
  58. 58. 58 Application: Opinion Mining Subtopics •  Opinion extraction: extract the piece of text which represents the opinion •  Cyrus has made a 23-song, purposely strange psych-rock record. Make no mistake, some of this album is unlistenable. But Cyrus is also too skilled of an artist to not place some beauty inside this madness, and Miley Cyrus and Her Dead Petz swerves into thoughtful territory when it’s least expected. •  Sentiment classification/orientation: extract the polarity of the opinion (e.g. positive, negative, neutral, or classify on a numerical scale) •  negative: purposely strange, some is unlistenable •  positive: skilled artist, beauty inside madness, thoughful •  Opinion summarisation: summarise the overall opinion about something •  Strange, some unlistenable: negative, skilled artist, beauty, thoughful: positive, Overall 6/10
  59. 59. 59 Application: Opinion Mining Subtopics •  Feature-opinion association: given a text with target features and opinions extracted, decide which opinions comment on which features. •  “The tracks are good but not so keen on the cover art” •  Target identification: which thing is the opinion referring to? •  Source identification: who is holding the opinion?
  60. 60. 60 Application: Opinion Mining Opinion Mining Resources Bing Liu’s English Sentiment Lexicon •  2006 pos words, 4783 neg words •  Useful properties: includes misspellings, morphological variants, slang •  Available from: http://www.cs.uic.edu/~liub/FBS/opinion-lexicon-English.rar The MPQA Subjectivity Lexicon •  Polarities: positive, negative, both, neutral •  Subjectivity: strongsubj or weaksubj •  Download from: http://mpqa.cs.pitt.edu/lexicons/subj_lexicon/
  61. 61. 61 Application: Opinion Mining Opinion Mining Resources WordNet Affect •  Extension of WordNet with affect words •  Useful properties: includes POS categories •  Available from: http://wndomains.fbk.eu/wnaffect.html Hands-on session: Applying standard opinion mining lexicons with GATE •  Spoiler: general purpose lexicons do not always perform well, for better performance, domain- or context-specific lexicons are necessary
  62. 62. 62Information Extraction with Linked Data Thank you for your attention!(And thank you to Diana Maynard for allowing me to adapt and reuse her Opinion Mining slides!) Questions? Isabelle Augenstein

×