Generation of Textual Description: Difference between revisions

From FDHwiki
Jump to navigation Jump to search
 
(One intermediate revision by the same user not shown)
Line 82: Line 82:
Tried different SOTA models for translation --> Unsatisfactory results due to the nature of the language being in old time and specific to Venetian dialect. Preliminary results with 10 examples:
Tried different SOTA models for translation --> Unsatisfactory results due to the nature of the language being in old time and specific to Venetian dialect. Preliminary results with 10 examples:


{| class="wikitable"
{| class="wikitable" style="background-color:#ffffff; color:#383838;"
|-
|-
! Original text
! Original text
Line 89: Line 89:
! GPT-4
! GPT-4
|- style="vertical-align:middle;"
|- style="vertical-align:middle;"
| casa e bottega da barbier
| style="background-color:#dae8fc;" | casa e bottega da barbier
| and a barber pole
| and a barber pole
| House and Bottega da Barbier
| House and Bottega da Barbier
| House and barber shop
| House and barber shop
|-
|-
| casa
| style="background-color:#dae8fc;" | casa
| style="vertical-align:middle;" | home
| style="vertical-align:middle;" | home
| house
| house
| style="vertical-align:middle;" | House
| style="vertical-align:middle;" | House
|-
|-
| bottega da strazariol
| style="background-color:#dae8fc;" | bottega da strazariol
| style="vertical-align:middle;" | a strawberry bottle
| style="vertical-align:middle;" | a strawberry bottle
| Bottega da Strazariol
| Bottega da Strazariol
| style="vertical-align:middle;" | Rag dealer's shop
| style="vertical-align:middle;" | Rag dealer's shop
|-
|-
| casa e bottega da tentor
| style="background-color:#dae8fc;" | casa e bottega da tentor
| style="vertical-align:middle;" | home and pushbutton
| style="vertical-align:middle;" | home and pushbutton
| House and Bottega da Tentor
| House and Bottega da Tentor
| style="vertical-align:middle;" | House and dyer’s shop
| style="vertical-align:middle;" | House and dyer’s shop
|-
|-
| magazen
| style="background-color:#dae8fc;" | magazen
| style="vertical-align:middle;" | warehouse
| style="vertical-align:middle;" | warehouse
| magazen
| magazen
| style="vertical-align:middle;" | Warehouse
| style="vertical-align:middle;" | Warehouse
|-
|-
| mezà
| style="background-color:#dae8fc;" | mezà
| style="vertical-align:middle;" | Eight
| style="vertical-align:middle;" | Eight
| mezà
| mezà
| style="vertical-align:middle;" | Halfway house or mezzanine level
| style="vertical-align:middle;" | Halfway house or mezzanine level
|-
|-
| cas vuota
| style="background-color:#dae8fc;" | cas vuota
| style="vertical-align:middle;" | empty house
| style="vertical-align:middle;" | empty house
| Cas empty
| Cas empty
| style="vertical-align:middle;" | Empty house
| style="vertical-align:middle;" | Empty house
|-
|-
| casa a pepian
| style="background-color:#dae8fc;" | casa a pepian
| style="vertical-align:middle;" | the pepian house
| style="vertical-align:middle;" | the pepian house
| House in Pepian
| House in Pepian
| style="vertical-align:middle;" | House on the ground floor
| style="vertical-align:middle;" | House on the ground floor
|-
|-
| bottega da confetti
| style="background-color:#dae8fc;" | bottega da confetti
| style="vertical-align:middle;" | Packaging bottle
| style="vertical-align:middle;" | Packaging bottle
| Bottega da sugaredi
| Bottega da sugaredi
| style="vertical-align:middle;" | Confectioner’s shop
| style="vertical-align:middle;" | Confectioner’s shop
|-
|-
| casa e bottega
| style="background-color:#dae8fc;" | casa e bottega
| style="vertical-align:middle;" | home and doorbell
| style="vertical-align:middle;" | home and doorbell
| House and Bottega
| House and Bottega
| style="vertical-align:middle;" | House and shop
| style="vertical-align:middle;" | House and shop
|}
|}
-> gonna choose GPT-4


=Results=
=Results=

Latest revision as of 15:46, 2 November 2024

Introduction

Motivation

Deliverables

Project Timeline & Milestones

Timeframe Task Completion
Week 4
  • Exploring the dataset
  • Exploring in-context learning models for text summarization
Week 5
  • Identify patterns and edge cases from the dataset (e.g missing fields, "odd" values)
  • Define different summarization formats accordingly to be used for in-context learning
  • Explore the connection between the Catastici and Sommarioni dataset
Week 6
  • Refine summarization formats
  • Construct a pipeline connecting translation generation, summarization and validation
Week 7
  • Evaluate summarization results
Week 8
  • TBD
Week 9
  • TBD
Week 10
  • TBD
Week 11
  • TBD
Week 12
  • TBD
Week 13
  • TBD
Week 14
  • TBD

Methodology

Generating Summarization Formats for In-context Learning

Choosing NLP Model for Translation

Tried different SOTA models for translation --> Unsatisfactory results due to the nature of the language being in old time and specific to Venetian dialect. Preliminary results with 10 examples:

Original text mBART Google Translate GPT-4
casa e bottega da barbier and a barber pole House and Bottega da Barbier House and barber shop
casa home house House
bottega da strazariol a strawberry bottle Bottega da Strazariol Rag dealer's shop
casa e bottega da tentor home and pushbutton House and Bottega da Tentor House and dyer’s shop
magazen warehouse magazen Warehouse
mezà Eight mezà Halfway house or mezzanine level
cas vuota empty house Cas empty Empty house
casa a pepian the pepian house House in Pepian House on the ground floor
bottega da confetti Packaging bottle Bottega da sugaredi Confectioner’s shop
casa e bottega home and doorbell House and Bottega House and shop

-> gonna choose GPT-4

Results

Limitations and further work

Conclusion

Credits