SRL
From Knowitall
More Examples (March 1)
- Attribution or enabling condition that affects factualness.
- She believed that chocolate milk came from brown cows.
- believe.01 A0=She; A1=came
- come.03 A1=milk; A2=from
- (She, believed, that chocolate milk came from brown cows)
- (chocolate milk, came, from brown cows) context: She believed
- http://nlpweb.cs.washington.edu/log/835
- She convinced me that chocolate milk came from brown cows.
- convince.01 A0=She; A2=me; A1=came
- come.03 A1=milk; A2=from
- (She, convinced, me, that chocolate milk came from brown cows)
- (chocolate milk, came, from brown cows) context: She convinced me
- http://nlpweb.cs.washington.edu/log/831
- John hopes that Mary visits him.
- hope.01 A0=John; A1=visit
- visit.01 A0=Mary; A1=him
- (John, hopes,, that Mary visits him)
- (Mary, visits, him) context: John hopes
- http://nlpweb.cs.washington.edu/log/843
- She believed that chocolate milk came from brown cows.
- No extraction from VBN or VBG that serves as restrictive modifier.
- The polyphenols found in green tea can cause kidney damage.
- find.01 A1=polyphenols; AM-LOC=in
- cause.01 A0=polyphenols; AM-MOD=can; A1=damage
- x (The polyphenols, found, in green tea)
- (The polyphenols found in green tea, can cause, kidney damage)
- http://nlpweb.cs.washington.edu/log/863
- The polyphenols existing in green tea can cause kidney damage.
- exist.01 A1=polyphenols; AM-LOC=in
- cause.01 A0=polyphenols; AM-MOD=can; A1=damage
- x (The polyphenols, existing, in green tea)
- (The polyphenols found in green tea, can cause, kidney damage)
- http://nlpweb.cs.washington.edu/log/870
- The polyphenols found in green tea can cause kidney damage.
- Create an extraction when VBN or VBG is second verb for arg1.
- California sea lions are social animals, living in groups along the coast.
- be.01 A1=lions; A2=animals
- live.01 A0=lions; AM-LOC=in
- (California sea lions, are, social animals)
- (California sea lions, living ,in groups along the coast)
- http://nlpweb.cs.washington.edu/log/846
- California sea lions are social animals, found in groups along the coast.
- be.01 A1=lions; A2=animals
- find.01 A0=lions; AM-LOC=in
- (California sea lions, are, social animals)
- (California sea lions, found, in groups along the coast)
- California sea lions are social animals, living in groups along the coast.
More Examples (Feb. 25)
- What do we want to extract from "If ..., then ..." constructions.
- The dependency parse in this example has "If Grandma had wheels" as an advcl modifier to the main clause.
- If Grandma had wheels, she would be a tea trolley.
- have.03 A0=Grandma; A1=wheels
- be.01 AM_ADV=had; A1=she; AM_MOD=would; A2=trolley
- (Grandma, had, wheels) mode:hypothetical
- (she, would be, a tea trolley) context: if (Grandma, had, wheels)
- http://nlpweb.cs.washington.edu/log/794
- If Grandma had wheels, she would be a tea trolley.
- The dependency parse in this example has "If Grandma had wheels" as an advcl modifier to the main clause.
- How far to go in extending arg2 with post modifying clauses?
- The dependency graph has appositive link from sedative to drug and we have (Alcohol, is, a drug) -- do we infer the last two tuples?
- Alcohol is a drug, a sedative, which depresses the central nervous system
- be.01 A1=Alcohol; A2=drug
- depress.02 A0=sedative; UnknownRole(R-A0)=which; A1=system
- ? (Alcohol, is, a drug, a sedative, which depresses the central nervous system)
- (Alcohol, is, a drug)
- (a sedative, depresses, the central nervous system)
- ? (a drug, depresses, the central nervous system)
- ? (Alcohol, depresses, the central nervous system)
- http://nlpweb.cs.washington.edu/log/795
- Alcohol is a drug, a sedative, which depresses the central nervous system
- The dependency graph has appositive link from sedative to drug and we have (Alcohol, is, a drug) -- do we infer the last two tuples?
- Don't create Time: from every AM_TMP
- Clay holds water well , sometimes perhaps too well
- hold.01 A0=Clay; A1=water; AM_MNR=well; AM_TMP=sometimes
- (Clay, holds, water)
- x (Clay, holds, water) Time: sometimes too well
- http://nlpweb.cs.washington.edu/log/796
- Clay holds water well , sometimes perhaps too well
- Here is a new arg role AM-PRR. Treat it like any other arg2.
- The verb with ".LV" seems to be a "light verb" construction, with the noun frame mistake.01
- The frame for become.01 has A2 = "immune to various antibiotics" -- shift the adj to the relation.
- Most people make this mistake and over time can become immune to various antibiotics .
- make.LV A0=people; AM-PRR=mistake
- mistake.01 A0=people; C-V=make
- become.01 A1=people; AM-TMP=over; AM-MOD=can; A2=immune
- (Most people, make, this mistake)
- (Most people, can become immune, to various antibiotics) Time: over time
- http://nlpweb.cs.washington.edu/log/804
- Most people make this mistake and over time can become immune to various antibiotics .
- Nested verbs with the same arg1 where arg2 of one includes rel+arg2 of the other.
- The band continued writing music and playing local shows .
- continue.01 A0=band; A1=writing
- write.01 A0=band; A1=music
- play.01 A0=band; A1=shows
- (The band, continued writing, music)
- (The band, continued playing, local shows)
- http://nlpweb.cs.washington.edu/log/806
- The band continued writing music and playing local shows .
- Nested relations where embedded frame is reduced relative clause
- No extraction from the second frame where verb has pos-tag VN.
- Meteorites are the oldest rocks found on Earth
- be.01 A1=Meteorites; A2=rocks
- find.01 A1=rocks; AM-LOC=on
- (Meteorites, are, the oldest rocks found on Earth)
- tr (Meteorites, are the oldest rocks found, on Earth)
- x (the oldest rocks, found, on Earth)
- Meteorites are the oldest rocks found on Earth
- No extraction from the second frame where verb has pos-tag VN.
Examples of SRL to Extraction Rules
- Create a tuple for every A1 Verb A2 where A1 and A2 are any of {A0, A1, A2, …, A5}
- John was reading a book.
- A0: John read.01 A1: a book
- (John, was reading, a book)
- http://nlpweb.cs.washington.edu/log/811
- John sat in the library.
- A1: John sit.01 A2: in the library
- (John, sat, in the library)
- http://nlpweb.cs.washington.edu/log/812
- John was reading a book.
- Ignore AM_MNR but use dependency graph to include adverbials in relation
- John was reading quietly.
- A0: John read.01 AM_MNR: quietly
- (John, was reading quietly, )
- http://nlpweb.cs.washington.edu/log/813
- John sat quietly in the library.
- A1: John sit.01 AM_MNR: quietly A2: in the library
- (John, sat quietly, in the library)
- http://nlpweb.cs.washington.edu/log/814
- John was reading quietly.
- Multiple arg2 with same arg1, second arg2 starts with a verb.
- Create two tuples, use both verbs in relation for arg2 that starts with verb.
- Don’t create the tuple with embedded verb.
- John hopes to read the book.
- A0: John hope.01 A1:to read the book
- A0: John read.01 A1: the book
- ? (John, hopes, to read the book)
- (John, hopes to read, the book)
- x (John, to read, the book)
- http://nlpweb.cs.washington.edu/log/815
- John sat in the library, reading a book.
- A1: John sit.01 A2: in the library AM_PRD: reading a book
- A0: John read.01 A1: a book
- (John, sat, in the library)
- (John, sat reading, a book)
- x(John, reading, a book)
- http://nlpweb.cs.washington.edu/log/818
- John reads books to stimulate his mind.
- A0: John read.01 A1: books AM_PRP: to stimulate his mind
- A0: John stimulate.01 A1: his mind
- (John, reads, books)
- ? (John, reads books, to stimulate his mind)
- (John, reads to stimulate, his mind)
- x (John, to stimulate, his mind)
- http://nlpweb.cs.washington.edu/log/819
- John hopes to read the book.
- Multiple arg2 with same arg1, second arg2 starts with preposition.
- Append the arg that starts with a preposition to the previous arg2.
- John reads books for stimulating his mind.
- A0: John read.01 A1: books AM_PRP: for stimulating his mind
- A0: John stimulate.01 A1: mind
- (John, reads, books, for stimulating his mind)
- ? (John, reads books, for stimulating his mind)
- Tr (John, reads, books for stimulating his mind)
- Tr (John, reads, books)
- x (John, stimulating, his mind)
- http://nlpweb.cs.washington.edu/log/820
- John reads books for stimulating his mind.
- Append the arg that starts with a preposition to the previous arg2.
- Ignore args that start R-*
- John read a book that discussed philosophy.
- A0: John read.01 A1: a book that discussed philosophy
- A0: a book discuss.01 R-A0: that A1: philosophy
- (John, read, a book that discussed philosophy)
- (a book, discussed, philosophy)
- http://nlpweb.cs.washington.edu/log/821
- John read a book in which philosophy was discussed.
- A0: John read.01 A1: a book in which philosophy was discussed
- A0: a book discuss.01 R-AM-LOC: in which A1: philosophy
- (John, read, a book in which philosophy was discussed)
- (a book, discussed, philosophy)
- http://nlpweb.cs.washington.edu/log/822
- John read a book that discussed philosophy.
- Designate the AM_TMP in tuples as Time:
- John read the book last Thursday.
- A0: John read.01 A1: the book AM_TMP: last Thursday
- (John, read, the book) Time: last Thursday
- http://nlpweb.cs.washington.edu/log/823
- Obama was elected in 2008.
- A0: Obama elect.01 A1: in 2008 AM_TMP: in 2008
- (Obama, was elected, in 2008) Time: in 2008
- http://nlpweb.cs.washington.edu/log/824
- John read the book last Thursday.
- Designate the AM_LOC in tuples as Location:
- John read the book in Paris.
- A0: John read.01 A1: the book AM_LOC: in Paris
- (John, read, the book) Location: in Paris
- http://nlpweb.cs.washington.edu/log/825
- Inslee was elected in Washington State.
- A0: Inslee elect.01 A1: in Washington State AM_LOC: in Washington State
- (Inslee, was elected, in 2008) Location: in Washington State
- http://nlpweb.cs.washington.edu/log/827
- John read the book in Paris.