Temporal Reasoning Intro to TimeML - PowerPoint PPT Presentation

About This Presentation
Title:

Temporal Reasoning Intro to TimeML

Description:

(relations between events and temporal expressions) temporal ordering ... Solovyou celebrated his 50th birthday during his six-month space voyage.' An example ' ... – PowerPoint PPT presentation

Number of Views:107
Avg rating:3.0/5.0
Slides: 33
Provided by: JamesPus8
Category:

less

Transcript and Presenter's Notes

Title: Temporal Reasoning Intro to TimeML


1
Temporal ReasoningIntro to TimeML
  • cs112
  • October, 2004

2
TimeML what it is
  • Standard language for the mark-up of
  • temporal expressions
  • events
  • temporal anchoring of events
  • (relations between events and temporal
    expressions)
  • temporal ordering of events
  • (relations between events and other events)

3
TimeML goals
  • Long term aim provide the basic background for
  • Temporal inference
  • QAS to be able to answer questions like
  • Is Gates currently CEO of Microsoft?
  • Were there any meetings between the hijackers and
    Iraq before the WTC event?
  • Creation of a gold standard corpus with temporal
    expressions, events and basic temporal relations
    marked up.

4
An example
  • Two Russians and a Frenchman left the Mir and
    endured a rough landing on the snow-covered
    plains of Central Asia on Thursday. The two
    Russians arrived on the Mir last August. Solovyou
    celebrated his 50th birthday during his six-month
    space voyage.

5
An example
  • Two Russians and a Frenchman left the Mir and
    endured a rough landing on the snow-covered
    plains of Central Asia on Thursday. The two
    Russians arrived on the Mir last August. Solovyou
    celebrated his 50th birthday during his six-month
    space voyage.

6
What to annotate
  • Time Expressions (timex)
  • Events
  • Signals
  • Links

Well mark them up with a set of attributes.
7
What to annotate TIMEX3
8
What to annotate TIMEX3
  • Durations
  • 4 hours, the whole week, half a year,
  • Calendar dates (points in time equal or bigger
    than a day)
  • Precise dates March 16, 2003 two years ago
    today yesterday
  • Vague dates few days ago ending of March
  • Week references the 2nd week of January
    several weeks later
  • Yearly quarters and halves the 4th quarter
    beginning last semester
  • Seasons last Summer Fall 1998
  • Year references the 60s, 1920
  • Decades, centuries and millenia the last decade
  • Times of Day (points in time smaller than a
    day)
  • Precise times 730am Tuesday, March 25 at
    1200pm
  • Vague times several minutes before
  • Parts of day Saturday afternoon, yesterday
    early in the morning
  • Sets (reoccurring time expressions)
  • Two times a week, every day,

9
Attributes for the tag TIMEX3
  • Timex ID (automatically assigned)
  • Type
  • DATE, for expressions describing a calendar
    date
  • the second of December, yesterday, the summer of
    1971, Tuesday, ...
  • TIME, for expressions describing a times of day
  • five minuts past eight 730am 900 am Friday,
    October 1, 1755
  • DURATION
  • 2 months, 48 hours, all last night, three weeks.
  • SET
  • Value
  • ISO value for the time expression.
  • Feb 27, 1998 0814 1998-02-27T081400
  • twelve weeks P12W

10
Attributes for the tag TIMEX3 (2)
  • Mod

11
Attributes for the tag TIMEX3 (3)
  • temporalFunction binary attribute
  • F the timex provides all the info
  • Twelve oclock January 3, 1969
  • Summer of 1964
  • T the timex doesnt contain all the info needed
    to locate it at a specific point of time
    (therefore, a temporal function needs to be
    applied)
  • eleven in the morning
  • yesterday
  • next year
  • anchorTimeID
  • Use only when temporalFunction attribute is set
    to TRUE
  • Refers to the temporal anchor for the
    incomplete timex.

12
Attributes for the tag TIMEX3 (4)
  • functionInDocument
  • CREATION TIME
  • MODIFICATION TIME
  • PUBLICATION TIME
  • RELEASE TIME
  • RECEPTION TIME
  • NONE
  • At most, once per document
  • Generally CREATION TIME

13
Example of annotated TIMEXs
  • Mary left on Thursday and John arrived the day
    after.
  • Mary left
  • on
  • ltTIMEX3 tid"t1" type"DATE value"1998-WXX-4"
    temporalFunction"true anchorTimeID"t0"gt
  • Thursday
  • lt/TIMEX3gt
  • and John arrived
  • ltTIMEX3 tid"t2" type"DATE value"1998-WXX-5"
    temporalFunction"true anchorTimeID"t1"gt
  • the day
  • lt/TIMEX3gt
  • after

14
Example of annotated TIMEXs
  • TERQAS Workshop will resume Monday, July 15. The
    session will start at 900 a.m.
  • TERQAS Workshop will resume
  • ltTIMEX3 tid"t1" type"DATE" value"2002-07-15
  • temporalFunction"true" anchorTimeID"t0"gt
  • Monday, July 15
  • lt/TIMEX3gt
  • . The session will start at
  • ltTIMEX3 tid"t2" type"TIME" value" 2002-07-15
    T900" temporalFunction"true" anchorTimeID"t1"gt
  • 900 a.m.
  • lt/TIMEX3gt

15
What to annotate EVENTs
16
What to annotate EVENTs
  • Tensed Verbs
  • A fresh flow of lava, gas and debris erupted
    there Saturday.
  • Untensed verbs
  • Prime Minister Benjamin Netanyahu called the
    prime minister of the Netherlands to thank him
    for thousands of gas masks his country has
    already contributed.
  • Nominalizations
  • Israel will ask the US to delay a military strike
    against Iraq until the Jewish state is fully
    prepared for a possible Iraqi attack.
  • Adjectives
  • A Philippine volcano, dormant for six centuries,
    began exploding with searing gases, thick ash and
    deadly debris.
  • Prepositional phrases
  • All 75 people on board the Aeroflot Airbus died.
  • Predicative Clauses
  • "There is no reason why we would not be
    prepared," Mordechai told the Yediot Ahronot
    daily.

17
Attributes for the tag EVENT
  • Event ID (automatically assigned)
  • Class
  • REPORTING say, report, announce,
  • PERCEPTION see, hear, watch, feel.
  • ASPECTUAL begin, start, finish, stop, continue.
  • I_ACTION attempt, try, promise, offer, regret,
  • I_STATE believe, want, wish,
  • STATE be on board, kidnapped, recovering, love,
    ..
  • OCCURRENCE die, crash, build, merge, sell, take
    advantage of, ..

18
Example of annotated EVENTs
  • Israel may ask the United States to delay a
    military strike against Iraq until the Jewish
    state is fully prepared for a possible Iraqi
    attack.
  • Israel may
  • ltEVENT eid"e1" class"I_ACTIONgt
  • ask lt/EVENTgt
  • the United States not to
  • ltEVENT eid"e2" class"I_ACTIONgt
  • delay lt/EVENTgt
  • a military
  • ltEVENT eid"e3" class"OCCURRENCEgt
  • strike lt/EVENTgt
  • against Iraq until the Jewish state is fully
  • ltEVENT eid"e4" class"I_STATEgt
  • prepared lt/EVENTgt
  • for a possible Iraqi
  • ltEVENT eid"e5" class"OCCURRENCEgt
  • attack lt/EVENTgt

19
What to annotate MAKEINSTANCEs
20
Attributes for MAKEINSTANCE
  • Event Instance ID (automatically assigned)
  • Event ID (automatically assigned)
  • Tense (only pertinent for verbs)
  • PAST John decided/had decided not to go.
  • PRESENT John decides/has decided not to go.
  • FUTURE John will decide/will have decided not to
    go.
  • NONE John decided not to go / Johns decision
    ...
  • Aspect (only pertinent for verbs)
  • PROGRESSIVE BE -ing John is/was/will
    be eating
  • PERFECTIVE HAVE Ppart John
    has/had/will have eaten
  • PERFECTIVE_PROGRESSIVE John has/had been
    eating
  • NONE John eats/ate/will eat

21
Attributes for MAKEINSTANCE
  • nf_morph
  • NOUN Johns decision was not to go.
  • ADJECTIVE Sue was ashamed of Johns decision.
  • INFINITIVE John decided not to go.
  • PRESPART While playing, John broke his leg.
  • PASTPART Steel plates found at the scene are
    being analyzed by experts.
  • Polarity
  • POS no negation present John went.
  • NEG negation present John did not go.
  • Modality
  • Modal Auxiliars like could, can, might, may,
    must, should,
  • Signal_ID --see the guidelines
  • Cardinality --see the guidelines

22
Example of annotated MIs
Israel may ask the United States to delay a
military strike against Iraq Israel may ltEVENT
eid"e1" class"I_ACTIONgt ask lt/EVENTgt ltMI
eiidei1 eide1 tenseNONE aspectNONE
nf_morphNONE modalitymay/gt the United
States to ltEVENT eid"e2" class"I_ACTIONgt
delay lt/EVENTgt ltMI eiidei2 eide2
tenseNONE aspectNONE nf_morphINFINITIVE/gt
a military ltEVENT eid"e3" class"OCCURRENCE"gt
strike lt/EVENTgt ltMI eiidei3 eide3
tenseNONE aspectNONE nf_morphNOUN/gt
23
What to annotate SIGNALs
24
What to annotate SIGNALs
  • Temporal prepositions
  • on, in, at, from, to, before, after, during,
    etc.
  • Temporal conjunctions
  • before, after, while, when, etc.
  • Temporal modifiers (only when modifying events)
  • twice, every, three times, etc.
  • Special characters
  • - and /, in temporal expressions denoting
    ranges (September, 4-6, Apr. 1999/Jul. 1999,
    etc.).

25
Attributes for the tag SIGNAL
  • Signal ID automatically assigned
  • (they are very boring!)

26
Example of annotated SIGNALs
  • Temporal Prepositions, Conjunctions and
    Modifiers
  • John taught ltSIGNAL sid"s1"gtonlt/SIGNALgt Monday
  • All passengers died ltSIGNAL sid"s1"gtwhenlt/SIGNAL
    gt the plane crashed into the mountain.

27
What to annotate LINKs
28
What to annotate LINKs
  • Temporal TLINK
  • It represents the temporal relationship holding
    between events or between an event and a timex
  • Mary arrived in Boston last Thursday.
  • Aspectual ALINK
  • It represent the relationship between an
    aspectual event and its argument event.
  • She finished assembling the table.
  • Subordination SLINK
  • It is used for contexts introducing relations
    between an I-ACTION/I-STATE event and its event
    argument, or an event and a negation or modal
  • She tried to buy some wine.

29
relType the attribute for TLINK
  • Simultaneous (only for pairs of events)
  • Mary was watching TV while John was frying the
    eggs.
  • Before/After
  • Mary had decided not to help him. (wrt
    watching or frying in the previous sentence).
  • Immediately before/Immediately after
  • One of the eggs crashed as soon as it touched
    the pan.
  • Including/Being included
  • Mary arrived in Boston last Thursday.
  • During (states or events that persist through a
    duration)
  • John fried eggs for 20 minutes on Monday.
  • Beginning/Begun by
  • John fried eggs from 600pm to 620pm.
  • Ending/Ended by
  • John fried eggs from 600pm to 620pm.
  • Identity (only for pairs of events)
  • Mary was resting for a while. After her rest,
    she took a bath.

30
relType the attribute for SLINK
  • Modal, introduced mainly by
  • I_States Mary wanted John to buy some wine.
  • I_Actions John tried to get ticket for the
    final.
  • Factive, for I-events introducing some
    presupposition
  • John forgot he was in Boston last year.
  • Counter-factive, for I-events introducing a
    presupposition about the non-veracity of its
    argument
  • forget (to), prevent, cancel, avoid, decline,
    etc.
  • Evidential, mainly introduced by Reporting and
    Perception events
  • say, report, see, hear, ..
  • Negative Evidential, introduced by Reporting
    events that convey negative polarity
  • John denied he bought only beer.

31
relType the attribute for ALINK
  • Initiation
  • John started to read.
  • Culmination
  • John finished assembling the table.
  • Termination
  • John stopped talking.
  • Continuation
  • John kept talking.

32
Final remark
  • Please, read the Annotation Guidelines!
Write a Comment
User Comments (0)
About PowerShow.com