SlideShare a Scribd company logo
Introduction           Reichenbach’s Model of Tense             RTMML   Using the markup             Conclusion




           An Annotation Scheme for Reichenbach’s Verbal
                          Tense Structure

                            Leon Derczynski and Robert Gaizauskas

                                               University of Sheffield


                                               11 January 2011




Leon Derczynski and Robert Gaizauskas                                                      University of Sheffield
An Annotation Scheme for Reichenbach’s Verbal Tense Structure
Introduction           Reichenbach’s Model of Tense             RTMML   Using the markup             Conclusion




Outline


       1 Introduction

       2 Reichenbach’s Model of Tense

       3 RTMML

       4 Using the markup

       5 Conclusion




Leon Derczynski and Robert Gaizauskas                                                      University of Sheffield
An Annotation Scheme for Reichenbach’s Verbal Tense Structure
Introduction           Reichenbach’s Model of Tense             RTMML   Using the markup             Conclusion




Introduction to RTMML




         We present RTMML - a markup schema for a model of tense in
         language - that helps us better automatically process temporal
                               information in text.




Leon Derczynski and Robert Gaizauskas                                                      University of Sheffield
An Annotation Scheme for Reichenbach’s Verbal Tense Structure
Introduction           Reichenbach’s Model of Tense             RTMML   Using the markup             Conclusion




Temporal Annotation


               Relating time is an essential part of discourse.
               To automatically process time information in documents, we
               can record data with a temporal annotation.
               Data annotated might include: times, events, the relations
               between them.
               Existing standards - TIMEX, TimeML
               Existing corpora - TimeBank, AQUAINT TimeML corpus,
               WikiWars
               We focus on two sub-tasks: relating events, and processing
               temporal expressions.


Leon Derczynski and Robert Gaizauskas                                                      University of Sheffield
An Annotation Scheme for Reichenbach’s Verbal Tense Structure
Introduction           Reichenbach’s Model of Tense             RTMML   Using the markup             Conclusion




Relating events



               Temporal expressions and events may be seen as intervals.
               Defining relations between two intervals permits temporal
               ordering.
               Human readers can usually temporally relate events in a
               discourse using cues.
               Automatic labelling of temporal links is a difficult research
               problem.




Leon Derczynski and Robert Gaizauskas                                                      University of Sheffield
An Annotation Scheme for Reichenbach’s Verbal Tense Structure
Introduction           Reichenbach’s Model of Tense             RTMML   Using the markup             Conclusion




Temporal expressions



               Wednesday; December 4, 1997; for two weeks
               A temporal expression is text that describes a time or period.
               The process of mapping temporal expressions to an absolute
               calendar is normalisation.
               Wednesday ⇒ 2011/01/12 T 00:00:00 - 2011/01/12 T
               23:59:59




Leon Derczynski and Robert Gaizauskas                                                      University of Sheffield
An Annotation Scheme for Reichenbach’s Verbal Tense Structure
Introduction           Reichenbach’s Model of Tense             RTMML   Using the markup             Conclusion




Outline


       1 Introduction

       2 Reichenbach’s Model of Tense

       3 RTMML

       4 Using the markup

       5 Conclusion




Leon Derczynski and Robert Gaizauskas                                                      University of Sheffield
An Annotation Scheme for Reichenbach’s Verbal Tense Structure
Introduction           Reichenbach’s Model of Tense             RTMML   Using the markup             Conclusion




The Model



               When describing an event, we can call the time of the event E .
               The event is described at speech time S.
               “I will walk the dog.” ⇒ S < E
               Reichenbach introduces a reference point, an abstract time
               from which events are viewed.
               “I ran home” ⇒ E < S
               “I had run home” ⇒ E < R < S




Leon Derczynski and Robert Gaizauskas                                                      University of Sheffield
An Annotation Scheme for Reichenbach’s Verbal Tense Structure
Introduction           Reichenbach’s Model of Tense             RTMML   Using the markup             Conclusion




Special properties of the reference point


               permanence: when sentences or clauses are combined,
               grammatical rules constrain the set of available tenses. These
               rules work such that R has the same position in all cases.
               “I had run home when I heard the noise”
               positional use: when a time is found in the same clause as a
               verbal event, R is bound to the time.
               “It was six o’clock and John had prepared” – the preparation,
               E , occurs before six o’clock, R.




Leon Derczynski and Robert Gaizauskas                                                      University of Sheffield
An Annotation Scheme for Reichenbach’s Verbal Tense Structure
Introduction            Reichenbach’s Model of Tense            RTMML   Using the markup             Conclusion




Motivation

                   At least 10% of normalisation errors are due to incorrect R 1 .
                   There is a “need to develop sophisticated methods for
                   temporal focus tracking if we are to extend current
                   time-stamping technologies”2 .

                   If can relate the S and R of multiple event verbs, we can
                   reason about and label the relation between event times.

                   Tracking S, E and R according to Reichenbach’s model helps
                   generate correct tense and aspect for NLG3 .

               1
                 Mani & Wilson, 2000
               2
                 Mazur & Dale, 2010
               3
                 Elson & McKeown, 2010
Leon Derczynski and Robert Gaizauskas                                                      University of Sheffield
An Annotation Scheme for Reichenbach’s Verbal Tense Structure
Introduction           Reichenbach’s Model of Tense             RTMML   Using the markup             Conclusion




Outline


       1 Introduction

       2 Reichenbach’s Model of Tense

       3 RTMML

       4 Using the markup

       5 Conclusion




Leon Derczynski and Robert Gaizauskas                                                      University of Sheffield
An Annotation Scheme for Reichenbach’s Verbal Tense Structure
Introduction           Reichenbach’s Model of Tense             RTMML   Using the markup             Conclusion




What to annotate?


               RTMML is intended to describe Reichenbach’s verbal event
               structure.
               First primitive: verb groups describing an event (had snowed,
               is running, will have given).
               Second primitive: text describing a time (next two weeks, last
               April).
               We are more concerned with the relations between times than
               the absolute position of the times.




Leon Derczynski and Robert Gaizauskas                                                      University of Sheffield
An Annotation Scheme for Reichenbach’s Verbal Tense Structure
Introduction           Reichenbach’s Model of Tense             RTMML   Using the markup             Conclusion




Annotation Schema


               RTMML is an XML-based standoff annotation standard that
               may be standalone or integrated with TimeML.
               <doc> defines document creation/utterance time, which is
               also the default speech time.
               <verb> denotes verb groups, including tense, and relations
               between S, E and R. These points may be expressed in terms
               of other times in the annotation or new labels.
               <timerefx> denotes a time-referring expression, which can be
               optionally specified in TIMEX3 format.



Leon Derczynski and Robert Gaizauskas                                                      University of Sheffield
An Annotation Scheme for Reichenbach’s Verbal Tense Structure
Introduction           Reichenbach’s Model of Tense             RTMML   Using the markup             Conclusion




Example markup


       <rtmml>
       Yesterday, John ate well.
       <seg type="token" />
       <doc time="now" />
       <timerefx xml:id="t1" target="#token0" />
       <verb xml:id="v1" target="#token3"
       view="simple" tense="past"
       sr=">" er="=" se=">"
       r="t1" s="doc" />
       </rtmml>



Leon Derczynski and Robert Gaizauskas                                                      University of Sheffield
An Annotation Scheme for Reichenbach’s Verbal Tense Structure
Introduction           Reichenbach’s Model of Tense             RTMML   Using the markup             Conclusion




RTMML links


               Although we can relate primitives with the current syntax,
               three common types of link are catered for with <rtmlink>:
               positions, describing positional use of the reference point;
               same timeframe, where events share a commonly situated
               reference point;
               reports, for reported speech.
       <rtmlink xml:id="l1" type="POSITIONS">
       <link source="#t1" />
       <link target="#v1" />
       </rtmlink>


Leon Derczynski and Robert Gaizauskas                                                      University of Sheffield
An Annotation Scheme for Reichenbach’s Verbal Tense Structure
Introduction           Reichenbach’s Model of Tense             RTMML   Using the markup             Conclusion




Outline


       1 Introduction

       2 Reichenbach’s Model of Tense

       3 RTMML

       4 Using the markup

       5 Conclusion




Leon Derczynski and Robert Gaizauskas                                                      University of Sheffield
An Annotation Scheme for Reichenbach’s Verbal Tense Structure
Introduction           Reichenbach’s Model of Tense             RTMML   Using the markup             Conclusion




Example - Relations between events
       Saddam appeared to accept a border demarcation treaty he had
       rejected in peace talks.
            Verb 1 - appeared - is simple past. Ev 1 < Sv 1 , Ev 1 = Rv 1
            <verb xml:id="v1" view="simple" tense="past" />
            Verb 2 - had rejected - is anterior past. Ev 2 < Rv 2 , Rv 2 < Sv 2
            <verb xml:id="v2" view="anterior" tense="past" />
            These occur in the same timeframe, sharing a reference point.
            Rv 1 = Rv 2
            <rtmlink type="SAME TIMEFRAME">
            <link target="v1" />
            <link target="v2" />
            </rtmlink>
            We can infer from this that Ev 2 < Ev 1 .
Leon Derczynski and Robert Gaizauskas                                                      University of Sheffield
An Annotation Scheme for Reichenbach’s Verbal Tense Structure
Introduction           Reichenbach’s Model of Tense             RTMML   Using the markup             Conclusion




Context


               Speech and reference points tend to persist in discourse - until
               changed by a shift in context.
               Emmanuel had said “This will explode!”, but later changed
               his mind.
               Positions of S and R persist throughout each context.
               Changing the S − R relationship inside a context leads to
               awkward text;
               “By the time I ran, John will have arrived”.




Leon Derczynski and Robert Gaizauskas                                                      University of Sheffield
An Annotation Scheme for Reichenbach’s Verbal Tense Structure
Introduction           Reichenbach’s Model of Tense             RTMML   Using the markup             Conclusion




Outline


       1 Introduction

       2 Reichenbach’s Model of Tense

       3 RTMML

       4 Using the markup

       5 Conclusion




Leon Derczynski and Robert Gaizauskas                                                      University of Sheffield
An Annotation Scheme for Reichenbach’s Verbal Tense Structure
Introduction           Reichenbach’s Model of Tense             RTMML   Using the markup             Conclusion




Conclusion




            We have presented Reichenbach’s tense model, a markup for
           representing its time points, and shown how it can be applied.




Leon Derczynski and Robert Gaizauskas                                                      University of Sheffield
An Annotation Scheme for Reichenbach’s Verbal Tense Structure
Introduction           Reichenbach’s Model of Tense             RTMML   Using the markup             Conclusion




Improvements




               Guidelines for languages other than English.
               Does not cater for event intervals or progressive aspect.
               No mechanism for integrating nominal events, which may be
               used positionally as a timerefx.




Leon Derczynski and Robert Gaizauskas                                                      University of Sheffield
An Annotation Scheme for Reichenbach’s Verbal Tense Structure
Introduction           Reichenbach’s Model of Tense             RTMML   Using the markup             Conclusion




RTMBank




               Current work in progress.
               Goal is to create a corpus of fifty to sixty RTMML-annotated
               documents.
               Documents chosen for annotation are already in TimeBank.




Leon Derczynski and Robert Gaizauskas                                                      University of Sheffield
An Annotation Scheme for Reichenbach’s Verbal Tense Structure
Introduction           Reichenbach’s Model of Tense             RTMML   Using the markup             Conclusion




Questions




                   Thank you for your time. Are there any questions?




Leon Derczynski and Robert Gaizauskas                                                      University of Sheffield
An Annotation Scheme for Reichenbach’s Verbal Tense Structure

More Related Content

PDF
RTMBank: Capturing Verbs with Reichenbach's Tense Model
ODP
Efficient named entity annotation through pre-empting
PPT
Verbal tenses
PDF
Leveraging the Power of Social Media
PDF
Handling and Mining Linguistic Variation in UGC
PDF
Broad Twitter Corpus: A Diverse Named Entity Recognition Resource
PPT
Tenses and its uses
PDF
Empirical Validation of Reichenbach’s Tense Framework
RTMBank: Capturing Verbs with Reichenbach's Tense Model
Efficient named entity annotation through pre-empting
Verbal tenses
Leveraging the Power of Social Media
Handling and Mining Linguistic Variation in UGC
Broad Twitter Corpus: A Diverse Named Entity Recognition Resource
Tenses and its uses
Empirical Validation of Reichenbach’s Tense Framework

More from Leon Derczynski (20)

PDF
Joint Rumour Stance and Veracity
PDF
State of Tools for NLP in Danish: 2018
ODP
RumourEval
PDF
Corpus Annotation through Crowdsourcing: Towards Best Practice Guidelines
ODP
Passive-Aggressive Sequence Labeling with Discriminative Post-Editing for Rec...
PDF
Starting to Process Social Media
ODP
Christmas Presentation at Aarhus: What I do
PDF
Recognising and Interpreting Named Temporal Expressions
PPT
TwitIE: An Open-Source Information Extraction Pipeline for Microblog Text
PDF
Twitter Part-of-Speech Tagging for All: Overcoming Sparse and Noisy Data
PDF
Mining Social Media with Linked Open Data, Entity Recognition, and Event Extr...
PDF
Determining the Types of Temporal Relations in Discourse
PDF
Microblog-genre noise and its impact on semantic annotation accuracy
PDF
Towards Context-Aware Search and Analysis on Social Media Data
PDF
Determining the Types of Temporal Relations in Discourse
PDF
TIMEN: An Open Temporal Expression Normalisation Resource
PPT
Review of: Challenges of migrating to agile methodologies
PPT
A data driven approach to query expansion in question answering
PDF
A Corpus-based Study of Temporal Signals
PDF
Word Sense Disambiguation and Induction
Joint Rumour Stance and Veracity
State of Tools for NLP in Danish: 2018
RumourEval
Corpus Annotation through Crowdsourcing: Towards Best Practice Guidelines
Passive-Aggressive Sequence Labeling with Discriminative Post-Editing for Rec...
Starting to Process Social Media
Christmas Presentation at Aarhus: What I do
Recognising and Interpreting Named Temporal Expressions
TwitIE: An Open-Source Information Extraction Pipeline for Microblog Text
Twitter Part-of-Speech Tagging for All: Overcoming Sparse and Noisy Data
Mining Social Media with Linked Open Data, Entity Recognition, and Event Extr...
Determining the Types of Temporal Relations in Discourse
Microblog-genre noise and its impact on semantic annotation accuracy
Towards Context-Aware Search and Analysis on Social Media Data
Determining the Types of Temporal Relations in Discourse
TIMEN: An Open Temporal Expression Normalisation Resource
Review of: Challenges of migrating to agile methodologies
A data driven approach to query expansion in question answering
A Corpus-based Study of Temporal Signals
Word Sense Disambiguation and Induction
Ad

Recently uploaded (20)

PDF
From MVP to Full-Scale Product A Startup’s Software Journey.pdf
PPTX
Group 1 Presentation -Planning and Decision Making .pptx
PPTX
TechTalks-8-2019-Service-Management-ITIL-Refresh-ITIL-4-Framework-Supports-Ou...
PDF
Agricultural_Statistics_at_a_Glance_2022_0.pdf
PDF
DASA ADMISSION 2024_FirstRound_FirstRank_LastRank.pdf
PPTX
1. Introduction to Computer Programming.pptx
PPTX
Digital-Transformation-Roadmap-for-Companies.pptx
PPTX
Tartificialntelligence_presentation.pptx
PDF
Accuracy of neural networks in brain wave diagnosis of schizophrenia
PDF
Profit Center Accounting in SAP S/4HANA, S4F28 Col11
PDF
project resource management chapter-09.pdf
PDF
gpt5_lecture_notes_comprehensive_20250812015547.pdf
PDF
Heart disease approach using modified random forest and particle swarm optimi...
PDF
A novel scalable deep ensemble learning framework for big data classification...
PDF
Video forgery: An extensive analysis of inter-and intra-frame manipulation al...
PDF
Approach and Philosophy of On baking technology
PDF
DP Operators-handbook-extract for the Mautical Institute
PDF
Enhancing emotion recognition model for a student engagement use case through...
PDF
Encapsulation theory and applications.pdf
PDF
WOOl fibre morphology and structure.pdf for textiles
From MVP to Full-Scale Product A Startup’s Software Journey.pdf
Group 1 Presentation -Planning and Decision Making .pptx
TechTalks-8-2019-Service-Management-ITIL-Refresh-ITIL-4-Framework-Supports-Ou...
Agricultural_Statistics_at_a_Glance_2022_0.pdf
DASA ADMISSION 2024_FirstRound_FirstRank_LastRank.pdf
1. Introduction to Computer Programming.pptx
Digital-Transformation-Roadmap-for-Companies.pptx
Tartificialntelligence_presentation.pptx
Accuracy of neural networks in brain wave diagnosis of schizophrenia
Profit Center Accounting in SAP S/4HANA, S4F28 Col11
project resource management chapter-09.pdf
gpt5_lecture_notes_comprehensive_20250812015547.pdf
Heart disease approach using modified random forest and particle swarm optimi...
A novel scalable deep ensemble learning framework for big data classification...
Video forgery: An extensive analysis of inter-and intra-frame manipulation al...
Approach and Philosophy of On baking technology
DP Operators-handbook-extract for the Mautical Institute
Enhancing emotion recognition model for a student engagement use case through...
Encapsulation theory and applications.pdf
WOOl fibre morphology and structure.pdf for textiles
Ad

An Annotation Scheme for Reichenbach's Verbal Tense Structure

  • 1. Introduction Reichenbach’s Model of Tense RTMML Using the markup Conclusion An Annotation Scheme for Reichenbach’s Verbal Tense Structure Leon Derczynski and Robert Gaizauskas University of Sheffield 11 January 2011 Leon Derczynski and Robert Gaizauskas University of Sheffield An Annotation Scheme for Reichenbach’s Verbal Tense Structure
  • 2. Introduction Reichenbach’s Model of Tense RTMML Using the markup Conclusion Outline 1 Introduction 2 Reichenbach’s Model of Tense 3 RTMML 4 Using the markup 5 Conclusion Leon Derczynski and Robert Gaizauskas University of Sheffield An Annotation Scheme for Reichenbach’s Verbal Tense Structure
  • 3. Introduction Reichenbach’s Model of Tense RTMML Using the markup Conclusion Introduction to RTMML We present RTMML - a markup schema for a model of tense in language - that helps us better automatically process temporal information in text. Leon Derczynski and Robert Gaizauskas University of Sheffield An Annotation Scheme for Reichenbach’s Verbal Tense Structure
  • 4. Introduction Reichenbach’s Model of Tense RTMML Using the markup Conclusion Temporal Annotation Relating time is an essential part of discourse. To automatically process time information in documents, we can record data with a temporal annotation. Data annotated might include: times, events, the relations between them. Existing standards - TIMEX, TimeML Existing corpora - TimeBank, AQUAINT TimeML corpus, WikiWars We focus on two sub-tasks: relating events, and processing temporal expressions. Leon Derczynski and Robert Gaizauskas University of Sheffield An Annotation Scheme for Reichenbach’s Verbal Tense Structure
  • 5. Introduction Reichenbach’s Model of Tense RTMML Using the markup Conclusion Relating events Temporal expressions and events may be seen as intervals. Defining relations between two intervals permits temporal ordering. Human readers can usually temporally relate events in a discourse using cues. Automatic labelling of temporal links is a difficult research problem. Leon Derczynski and Robert Gaizauskas University of Sheffield An Annotation Scheme for Reichenbach’s Verbal Tense Structure
  • 6. Introduction Reichenbach’s Model of Tense RTMML Using the markup Conclusion Temporal expressions Wednesday; December 4, 1997; for two weeks A temporal expression is text that describes a time or period. The process of mapping temporal expressions to an absolute calendar is normalisation. Wednesday ⇒ 2011/01/12 T 00:00:00 - 2011/01/12 T 23:59:59 Leon Derczynski and Robert Gaizauskas University of Sheffield An Annotation Scheme for Reichenbach’s Verbal Tense Structure
  • 7. Introduction Reichenbach’s Model of Tense RTMML Using the markup Conclusion Outline 1 Introduction 2 Reichenbach’s Model of Tense 3 RTMML 4 Using the markup 5 Conclusion Leon Derczynski and Robert Gaizauskas University of Sheffield An Annotation Scheme for Reichenbach’s Verbal Tense Structure
  • 8. Introduction Reichenbach’s Model of Tense RTMML Using the markup Conclusion The Model When describing an event, we can call the time of the event E . The event is described at speech time S. “I will walk the dog.” ⇒ S < E Reichenbach introduces a reference point, an abstract time from which events are viewed. “I ran home” ⇒ E < S “I had run home” ⇒ E < R < S Leon Derczynski and Robert Gaizauskas University of Sheffield An Annotation Scheme for Reichenbach’s Verbal Tense Structure
  • 9. Introduction Reichenbach’s Model of Tense RTMML Using the markup Conclusion Special properties of the reference point permanence: when sentences or clauses are combined, grammatical rules constrain the set of available tenses. These rules work such that R has the same position in all cases. “I had run home when I heard the noise” positional use: when a time is found in the same clause as a verbal event, R is bound to the time. “It was six o’clock and John had prepared” – the preparation, E , occurs before six o’clock, R. Leon Derczynski and Robert Gaizauskas University of Sheffield An Annotation Scheme for Reichenbach’s Verbal Tense Structure
  • 10. Introduction Reichenbach’s Model of Tense RTMML Using the markup Conclusion Motivation At least 10% of normalisation errors are due to incorrect R 1 . There is a “need to develop sophisticated methods for temporal focus tracking if we are to extend current time-stamping technologies”2 . If can relate the S and R of multiple event verbs, we can reason about and label the relation between event times. Tracking S, E and R according to Reichenbach’s model helps generate correct tense and aspect for NLG3 . 1 Mani & Wilson, 2000 2 Mazur & Dale, 2010 3 Elson & McKeown, 2010 Leon Derczynski and Robert Gaizauskas University of Sheffield An Annotation Scheme for Reichenbach’s Verbal Tense Structure
  • 11. Introduction Reichenbach’s Model of Tense RTMML Using the markup Conclusion Outline 1 Introduction 2 Reichenbach’s Model of Tense 3 RTMML 4 Using the markup 5 Conclusion Leon Derczynski and Robert Gaizauskas University of Sheffield An Annotation Scheme for Reichenbach’s Verbal Tense Structure
  • 12. Introduction Reichenbach’s Model of Tense RTMML Using the markup Conclusion What to annotate? RTMML is intended to describe Reichenbach’s verbal event structure. First primitive: verb groups describing an event (had snowed, is running, will have given). Second primitive: text describing a time (next two weeks, last April). We are more concerned with the relations between times than the absolute position of the times. Leon Derczynski and Robert Gaizauskas University of Sheffield An Annotation Scheme for Reichenbach’s Verbal Tense Structure
  • 13. Introduction Reichenbach’s Model of Tense RTMML Using the markup Conclusion Annotation Schema RTMML is an XML-based standoff annotation standard that may be standalone or integrated with TimeML. <doc> defines document creation/utterance time, which is also the default speech time. <verb> denotes verb groups, including tense, and relations between S, E and R. These points may be expressed in terms of other times in the annotation or new labels. <timerefx> denotes a time-referring expression, which can be optionally specified in TIMEX3 format. Leon Derczynski and Robert Gaizauskas University of Sheffield An Annotation Scheme for Reichenbach’s Verbal Tense Structure
  • 14. Introduction Reichenbach’s Model of Tense RTMML Using the markup Conclusion Example markup <rtmml> Yesterday, John ate well. <seg type="token" /> <doc time="now" /> <timerefx xml:id="t1" target="#token0" /> <verb xml:id="v1" target="#token3" view="simple" tense="past" sr=">" er="=" se=">" r="t1" s="doc" /> </rtmml> Leon Derczynski and Robert Gaizauskas University of Sheffield An Annotation Scheme for Reichenbach’s Verbal Tense Structure
  • 15. Introduction Reichenbach’s Model of Tense RTMML Using the markup Conclusion RTMML links Although we can relate primitives with the current syntax, three common types of link are catered for with <rtmlink>: positions, describing positional use of the reference point; same timeframe, where events share a commonly situated reference point; reports, for reported speech. <rtmlink xml:id="l1" type="POSITIONS"> <link source="#t1" /> <link target="#v1" /> </rtmlink> Leon Derczynski and Robert Gaizauskas University of Sheffield An Annotation Scheme for Reichenbach’s Verbal Tense Structure
  • 16. Introduction Reichenbach’s Model of Tense RTMML Using the markup Conclusion Outline 1 Introduction 2 Reichenbach’s Model of Tense 3 RTMML 4 Using the markup 5 Conclusion Leon Derczynski and Robert Gaizauskas University of Sheffield An Annotation Scheme for Reichenbach’s Verbal Tense Structure
  • 17. Introduction Reichenbach’s Model of Tense RTMML Using the markup Conclusion Example - Relations between events Saddam appeared to accept a border demarcation treaty he had rejected in peace talks. Verb 1 - appeared - is simple past. Ev 1 < Sv 1 , Ev 1 = Rv 1 <verb xml:id="v1" view="simple" tense="past" /> Verb 2 - had rejected - is anterior past. Ev 2 < Rv 2 , Rv 2 < Sv 2 <verb xml:id="v2" view="anterior" tense="past" /> These occur in the same timeframe, sharing a reference point. Rv 1 = Rv 2 <rtmlink type="SAME TIMEFRAME"> <link target="v1" /> <link target="v2" /> </rtmlink> We can infer from this that Ev 2 < Ev 1 . Leon Derczynski and Robert Gaizauskas University of Sheffield An Annotation Scheme for Reichenbach’s Verbal Tense Structure
  • 18. Introduction Reichenbach’s Model of Tense RTMML Using the markup Conclusion Context Speech and reference points tend to persist in discourse - until changed by a shift in context. Emmanuel had said “This will explode!”, but later changed his mind. Positions of S and R persist throughout each context. Changing the S − R relationship inside a context leads to awkward text; “By the time I ran, John will have arrived”. Leon Derczynski and Robert Gaizauskas University of Sheffield An Annotation Scheme for Reichenbach’s Verbal Tense Structure
  • 19. Introduction Reichenbach’s Model of Tense RTMML Using the markup Conclusion Outline 1 Introduction 2 Reichenbach’s Model of Tense 3 RTMML 4 Using the markup 5 Conclusion Leon Derczynski and Robert Gaizauskas University of Sheffield An Annotation Scheme for Reichenbach’s Verbal Tense Structure
  • 20. Introduction Reichenbach’s Model of Tense RTMML Using the markup Conclusion Conclusion We have presented Reichenbach’s tense model, a markup for representing its time points, and shown how it can be applied. Leon Derczynski and Robert Gaizauskas University of Sheffield An Annotation Scheme for Reichenbach’s Verbal Tense Structure
  • 21. Introduction Reichenbach’s Model of Tense RTMML Using the markup Conclusion Improvements Guidelines for languages other than English. Does not cater for event intervals or progressive aspect. No mechanism for integrating nominal events, which may be used positionally as a timerefx. Leon Derczynski and Robert Gaizauskas University of Sheffield An Annotation Scheme for Reichenbach’s Verbal Tense Structure
  • 22. Introduction Reichenbach’s Model of Tense RTMML Using the markup Conclusion RTMBank Current work in progress. Goal is to create a corpus of fifty to sixty RTMML-annotated documents. Documents chosen for annotation are already in TimeBank. Leon Derczynski and Robert Gaizauskas University of Sheffield An Annotation Scheme for Reichenbach’s Verbal Tense Structure
  • 23. Introduction Reichenbach’s Model of Tense RTMML Using the markup Conclusion Questions Thank you for your time. Are there any questions? Leon Derczynski and Robert Gaizauskas University of Sheffield An Annotation Scheme for Reichenbach’s Verbal Tense Structure