Generation of Textual Description: Difference between revisions

From FDHwiki
Jump to navigation Jump to search
Line 416: Line 416:


=Results=
=Results=
==Metrics 1: [???]===
==Metrics 1: [???]==
Report the results here: accuracy, some examples, notes etc
Report the results here: accuracy, some examples, notes etc



Revision as of 11:29, 18 December 2024

Introduction

Leveraging two invaluable historical datasets - the 1740 Catastici and the 1808 Sommarioni - our project aim to generate detailed textual descriptions of parcels in Venice. These datasets, rich in historical, spatial, and social information, provide a comprehensive view of land ownership, urban development, and social structure in Venice across two distinct periods. The 1740 Catastici offers early insights into parcel functions, rent payments, and tenant names, while the 1808 Sommarioni provides a more detailed and standardized survey, including owner data, and normalized ownership types and qualities. By integrating these datasets, we can create informative descriptions of each parcel, including their location, function, ownership details, and historical context, thereby enhancing our understanding of Venice's evolution and cultural significance.

A visualization of the datapoints and an example of their parcel information on the Catastici 1740 Dataset.

Motivation

Our motivation for utilizing the 1740 Catastici and 1808 Sommarioni datasets stems from the rich historical insights they offer, despite the challenges in comprehending and connecting the data. These datasets, like many other historical records, face significant challenges in terms of data consistency and coherence. The data, often unstructured and manually constructed, presents inconsistencies due to its varied and sometimes incomplete nature. Fields may be missing, mistranscribed, or contain varying levels of detail, making it difficult to connect the different pieces of information into a coherent narrative. Additionally, the use of old Italian and Venetian dialects can further complicate the interpretation and context of the data.

Given these challenges, especially for non-historians, our goal is to simplify and contextualize this complex information. By cleaning, organizing, and integrating the data from these datasets, we aim to create coherent and informative textual descriptions. Leveraging in-context learning and prompting with GPT-4, we seek to depict a clear description of the story behind each datapoint, making the historical narratives more accessible and understandable for a broader audience. This approach will not only facilitate a deeper understanding of Venice's history but also make the datasets more user-friendly and interpretable.

Deliverables

  • Pre-processed, standardized dataset from the original source
  • A manually-crafted dictionary of old Venice house functions, matching terms used in the dataset with translations and detailed historical description
  • A text generation pipeline using in-context learning methods
  • A set of evaluation metrics to assess the text generation pipeline across different perspectives

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
  • Prepare for mid-term presentation
Week 9
  • Explore father-son relationship among Catastici and Sommarioni dataset
Week 10
  • Standardization of monthly rent column
Week 11
  • Verified and refined standardized rent values
Week 12
  • Added district mean rent column and integrated additional information into the data
  • Refine text prompts to incorporate new information
  • Implement evaluation methods for the final generated text
Week 13
  • Refine evaluation methods
  • Split evaluation tasks among members
Week 14
  • Verify and combine evaluation tasks
  • Finalize Wikipage and prepare for presentation

Methodology

Data Exploration

Data clusterings and patterns

After a general review of the Catastici data, it was observed that each data point contains a series of empty fields. Many of these fields appeared to follow the same pattern of missing values. Since the generated text needs to handle various entries with different available data, the first step involved categorizing the data points based on their missing values and then addressing each category.

In the initial step, all possible patterns of missing values were extracted, and their frequency within the dataset was analyzed. Among the 36K data points, 28K samples were found to align with 8 major patterns. In the table below, the 8 frequent patterns are present in order of popularity with an 'X' indicating that the data is present in the given template.

Frequent Patterns in the Dataset
pattern id owner entity owner entity group owner first name owner family name owner family group owner title an rendi ten name
2 X X X X X
0 X X X X X X
12 X X X X
19 X X X X X
8 X X X X X X
1 X X X X X
23 X X X
5 X X X X X

The main text generation task was then divided into two subtasks. The first subtask addressed the most frequent patterns, where a suitable example was crafted for each pattern to be used as context for the large language model. The second subtask focused on optimizing the context and prompt to ensure high-quality descriptions could also be generated for the less frequent patterns in the dataset.

Frequent Patterns Categorization

In tackling the first subtask, the 8 major patterns were categorized based on the following features:

  • Whether the property is owned by a person or a different entity
  • Whether the owner's title is present or not
  • Whether the tenant’s name is present or not

For each combination of these features, a sample paragraph was crafted for a corresponding sample data point, providing a precise explanation of the parcel. Below are two examples crafted for pattern id 0 and 1 respectively:

Pattern #0 Sample:

The property with ID 1 is located in Campo vicino alla Chiesa and serves as a casa e bottega da barbier (house and workshop for a barber). Owned by Liberal Campi, who holds the title of Secondo Prete (Second Priest), the property is tenanted by Francesco Zeni. In 1700s-1800s Venice, such properties were often dual-purpose, combining living spaces with workplaces. Barbers at the time may have also performed minor medical tasks in addition to their grooming services.

Pattern #1 Sample:

The property with ID 3 is located in Campo vicino alla Chiesa and serves as a bottega da strazariol (a workshop for a dealer or repairer of old clothes). The owner is listed as Pievan di San Cancian (the parish priest of San Cancian), with the title of Pievano. The tenant is Bortolamio Piazza. In the 1700s and 1800s, such workshops were associated with tradespeople engaged in repairing or selling second-hand clothing.

When a given data point matched one of the frequent patterns, the pre-crafted sample data and text were added to the prompt, enabling the language model to generate descriptions for new data points. The outcomes consistently resulted in well-written and reliable descriptions. To provide the sample data point to the language model, the following structure is used in the prompt:

... As an example of descriptive text I generated: {incontext_learning_text}; for sample data: {incontext_learning_data}.

Addressing Less Frequent Patterns

Addressing the second subtask, which involved the less frequent patterns, the dataset revealed over 160 different patterns, each representing fewer than 100 samples. Many of these patterns were present in fewer than five samples. Due to the variety, it was impractical to craft a tailored text for each individual pattern. Instead, an approach was devised where examples of two frequent patterns, along with their desired manually crafted paragraphs, were provided to the language model. The prompt was enhanced to acknowledge the possibility of missing values and instructed the model to adjust the paragraph slightly if necessary. Additionally, the prompt included a request for the model to highlight missing values, as this information could be useful to the end-user.

Data Enrichment

Functionality of Parcels

[Nas's part of processing the functionality and creating dictionary]

Standardization of Monthly Rent

Exploring Value Formats

Inferring accurate values from rent data can offer valuable insights into a parcel's history, such as its price in relation to its neighborhood, which may reflect its relative status at that time. Among 35,946 data rows, we identified that only 28,610 (~80%) contained numeric values, with the remaining entries consisting of null values or text data.

Upon exploration, we encountered examples of text data such as:

'10 ducati, 19 grossi' '40 ducati e 14 grossi' 'casa in soler'
'libertà di traghetto' '20 lire' '26 lire' '15 lire'...

These examples illustrate the diversity of information present in the text entries, including multiple currencies, descriptive text about the parcel’s function, and potential typographical errors.

To standardize the non-numeric rent values, we developed an iterative approach. Using regular expressions (regex), we captured patterns within the data. After each iteration, we matched the patterns against the dataset, identified any emerging new patterns, and incorporated them into our existing pattern set. This process was repeated until no new patterns could be found.

In the final iteration, we identified six main patterns as follows:

Pattern Name Example Notes
Single currency 30 lire with optional "de piccoli" or "di piccoli"
Dual currency 7 ducati, 18 grossi with optional "de piccoli" or "di piccoli"
Three-part currency 10 ducati, 2 lire, 8 soldi
Fractional or "e mezzo" units 8 ducati e mezzo
Time-related mentions al mese, ogni tre mesi, per metà
Function or Ownership casa, bottega
Others 1[5], 1' Unmatched with any of the above

Format Selection and Hypothesis

From the identified text formats, we decided to exclude entries related to function, ownership, or other non-monetary details due to uncertainty about their origins. These deviations may stem from transcription errors or the inclusion of special characters.

For analysis, we focused on the remaining matched patterns, which revealed a mix of currencies within the entries. We identified five currency types used:

  • Ducati/ducato [basis currency]
  • Lire/lira/libre
  • Grossi/grosso
  • Soldi

To standardize the dataset, we made the following assumptions:

  1. Currency synonyms: Terms like ducati and ducato refer to the same currency, as do lire, lira, libre, and grossi/grosso.
  2. Default currency: If no currency is mentioned, it defaults to ducati.
  3. Irrelevant qualifiers: Phrases like de piccoli or di piccoli are ignored in numeric contexts. For example, 50 lire is treated the same as 50 lire di piccoli. Historically, "lire di piccoli" referred to a monetary unit based on the piccolo, a base coin in Venice, but not a distinct currency itself.
  4. Exchange rate: Based on Wikipedia, we use the following conversion:
    1. 1 ducati = 6.2 lire = 24 grossi = 124 solid
    2. While exchange rates were historically dynamic and context-dependent, we adopted this commonly cited, publicly available rate.
  5. Unmatched formats: Entries that do not align with the identified currency patterns are excluded from analysis and marked as -1 due to uncertainty (e.g., transcription errors or unclear historical context).

Standardization Strategy

We standardized all values by converting them to the smallest unit (soldi):

  • Numeric values: Convert from ducati to soldi
  • Non-numeric values:
    • Matched format: Standardize as below
    • Unmatched format: Ignore (no analysis)

Value Standardization Method

  1. Single currency: For entries like 30 lire, convert directly using the chosen exchange rate.
  2. Dual currency: For entries like 7 ducati, 18 grossi, separate the components, convert each, and combine the results.
  3. Three-part currency: For entries like 10 ducati, 2 lire, 8 soldi, follow the same process as dual currency but account for the third component.
  4. Fractional units: For entries like 8 ducati e mezzo or 8 e mezzo, treat e mezzo (and similar terms) as +0.5, then convert.
  5. Time-related mentions:
    1. al mese = "monthly" (standard conversion).
    2. ogni tre mesi = "every three months" (divide by 3).
    3. per metà = "for half" (divide by 2; likely indicates partial or shared payment responsibility). For example, 36 lire per metà translates to 18 lire each for two parties or simply half of 36 lire.
    4. per 3 mesi = "for 3 months" (remain as is; indicates a fixed three-month payment).

This process results in a new dataset column, std_rent, which contains standardized monthly rent values in soldi. A few samples of the result is shown as below:

an_rendi std_rent
30 3720.0
30.5 lire di picolli 189.1
7 ducati, 18 grossi di piccolo 1300.0
10.0 ducati, 2 lire, 8 soldi 1260.4
30 lire per mezzo 189.1
40 lire al mese 248.0

Adding Mean District Rent Value for Parcels

With the standardized rent values for each parcel, we extended our analysis to compare individual parcels against the mean rent value of their respective districts (sestiere).

During this process, we identified additional anomalies, such as values with more than four digits. Upon verification, these entries were recognized as transcription errors, likely due to confusion with the ID field. Such values were excluded from further analysis.

To compute the mean rent price for each district, we excluded both the invalid entries and the standardized -1 values, as defined earlier. The results are visualized in the following graph:

The mean monthly rent price of each district (sestiere)

We further visualized the mean district rent values on a map, utilizing geographic coordinates to explore spatial patterns and gain insights into neighborhood characteristics and rent distributions.

Distribution of mean monthly rent price by district (sestiere), visualized on exact coordinates

From this visualization, we can derive interesting insights about neighborhoods. For example, San Marco (SM) has the highest mean rent, likely due to its central location within the city. This information enables further enrichment for text generation, not only within individual districts but also for comparisons across districts, offering a richer understanding of the socio-economic dynamics of the city.

Prompt Engineering

Use of translations

When dealing with the historical context and asking the GPT-4o model to provide explanations based on historical facts and information, it was observed that the GPT-4o model lacks an understanding of certain words in 18th-century Italian. Some words and phrases related to the functionality of parcels are not accurately translated by the model, resulting in generated text that is sometimes inaccurate or, in certain cases, misleading.

Take the following sample data entry as an example:

  • General Information
    • ID: 238
    • Place: Campiel del remer
  • Ownership Details
    • Owner First Name: Gerolamo
    • Owner Family Name: GRADENIGO
    • Owner Title: NOBIL HOMO
  • Functionality
    • Catastici Function: bastion inviamento (bastion with trade designation)
    • Standardized Functions: bastione, inviamento
    • Sommarioni Functions: BOTTEGA, CASA

Using the finalized prompt and without manually providing the translations, the model generated the following text regarding the context of the parcel's functionality:

In the 1700s-1800s Venice, the term "bastion inviamento" suggests a space used for fortification activities and dispatch operations.

However, based on the available sources, it is known that bastione refers to a large tavern or commercial space, often used for selling wine, which is significantly different from what the language model might infer from modern Italian. To address this issue, a dictionary titled Dizionario del dialetto veneziano was used as the primary source, along with two additional resources: a website called History Walks Venice and an index of Venetian toponymy titled Toponomastica Veneziana. Using these sources, an accurate translation of standardized functionalities was created, and a small dictionary was compiled.

This dictionary is provided to the GPT-4 model to ensure it generates factually and historically accurate explanations about the functionality of parcels. In the system prompt, only the necessary definitions are included to avoid redundant context and minimize resource usage.

With the updated translation provided to the language model, a description for the above example was generated as follows:

In the context of the 1700s-1800s Venice, a "bastion inviamento" may imply a versatile commercial space potentially used for selling wine by the glass and/or was designated for a specific trade, granted a particular right or possibly a license related to lucrative professions like baking or wine selling.

Using the compiled dictionary, the model accurately describes the functionality of the parcel within the historical context of 1700–1800s Venice.

Use of Sommarioni data

To further enrich the generated text, Sommarioni data has also been incorporated. The primary information extracted from the Sommarioni data is functionality. By including functionality from the Sommarioni data, it becomes possible to compare the functionality of a given parcel between 1740 and 1808, enabling the generated description to highlight changes or consistencies over time.

A specific request has been added to the GPT-4o model prompt to provide insights into the change in functionality between the Sommarioni data and the Catastici. Since the GPT-4o model does not inherently understand the difference between these two datasets, the prompt clarifies that one functionality corresponds to the year 1740 and the other to 1808. It is also specified that insights about changes in functionality should only be included if Sommarioni data is available, in order to avoid unnecessary or irrelevant text.

The part of the prompt related to the change of functionality is written as follows:

The field "som_function" (always refer to it as function in Sommarioni Data), if available, indicates the function in 1808 based on Sommarioni Data rather than field "function" which indicates the function in 1740. If the "som_function" is available, compare it to "function" and explain the difference.

As an example, the following data point has been provided to the API (not all available information about the parcel is mentioned below):

  • General Information
    • ID: 1315
    • Place: Anconetta
  • Ownership Details
    • Owner First Name: Bortolamio
    • Owner Family Name: FERARI
  • Functionality
    • Catastici Function: Bottega
    • Standardized Functions: bottega
    • Sommarioni Functions: CASA
  • Tenant Details
    • Name: Bastian Picolin Bombaser

The GPT-4o model, in return, generated a description containing the following sentence related to the comparison between the functionality in 1740 and 1808:

... According to the Sommarioni Data of 1808, the function transitioned to a "CASA" (house), highlighting a change from a commercial to a residential purpose over time.

Ensuring Historical Accuracy Over Narrative Storytelling

Evaluating the descriptions generated by the GPT-4o model, it was discovered that the language model occasionally shifts toward storytelling rather than adhering strictly to historical facts. While the story provided by the model might be correct, we prefer not to include redundant information without concrete factual evidence. For instance, consider the following data point as an example (not all available information about the parcel is mentioned below):

  • General Information
    • ID: 3
    • Place: Campo vicino alla Chiesa
  • Ownership Details
    • Owner Title: PIEVANO
  • Functionality
    • Catastici Function: bottega da strazariol

Feeding this example to the GPT-4 model resulted in a description that included the following part about the historical context of the parcel's functionality:

... Workshops like this were typically associated with tradespeople specializing in the repair or resale of second-hand clothing, which was a common trade in Venice during the 1700s-1800s.

The last part of the sentence appears to come from either common sense or potentially from information included in the language model's training data. However, verifying the accuracy of such sentences can be both challenging and time-consuming, and is considered beyond the scope of this project. Therefore, it has been decided to instruct the model not to provide insights that are not historically and explicitly evident or presented in the data.

Below is another data point given to the model and part of the generated description which is not desired:

  • General Information
    • ID: 5
    • Place: Campo vicino alla Chiesa
  • Ownership Details
    • Owner First Name: Agostin
    • Owner Family Name: FILIPPI
  • Functionality
    • Catastici Function: casa e bottega da tentor
... Dyers were integral to Venice's renowned textile industry, contributing to the city's economic and cultural prominence.

Again, while the sentence might be correct, it provides vague information, such as references to being integral to an industry or phrases like "cultural prominence," which make the description sound more like a (possibly fictional) narrative rather than a factual account of the available data.

On the other hand, when obvious translations or context can be applied, the model should be free to discuss them. However, the model tends to use overly definitive language, which may come across as overconfident given the limited data available. For instance, in the sample above, the description of the function initially included:

During the 1700s-1800s in Venice, "casa e bottega da tentor" was a common dual-purpose structure where artisans, such as dyers, lived and operated their trade.

To address these issues, the prompt should explicitly state that storytelling is prohibited and must be avoided. Additionally, the model should be instructed to use less confident language to avoid implying that sufficient data exists to make assumptions, such as suggesting that casa e bottega da tentor was a "common" dual-purpose structure.

The following text is part of the prompt, requesting historical context while ensuring the description remains concise, factual, and less definitive:

3. Historical Context: Offer a brief explanation of the property's function, referencing its role in 1700s-1800s Venice, phrased with appropriate caution (e.g., "may suggest," "indicates," "was often associated with") rather than definitive language. 

Avoid speculative storytelling or unnecessary elaboration or phrases like "reflecting a common arrangement".

Avoid Extrapolating beyond the data provided unless well-established historical knowledge applies directly.

Avoid describing the Venetian society when providing Historical Context about the functionality. Focus on the function.

Using the above-mentioned prompt, the generated description by the model contains the following regarding the historical context about the parcel's functionality; sounding concise and factual:

In the context of 1700s-1800s Venice, a "casa e bottega da tentor" may suggest a common structure where artisans like dyers both resided and conducted their trade.

Evaluation Metrics

[Explain the 3 different approaches we took for evaluating the results here - Fawzia?]

Results

Metrics 1: [???]

Report the results here: accuracy, some examples, notes etc

Metrics 2: [???]=

Report the results here: accuracy, some examples, notes etc ...

Limitations and Future Work

While this project has established a comprehensive pipeline for enriching data and generating textual descriptions, there are several areas where future work can enhance the quality and depth of the results:

  • Further data standardization: Currently, we have only standardized the rent column due to its identified frequent patterns. However, there are additional unstandardized text fields that could provide valuable information, such as the quantity or quality of income. Further standardization of these fields could infer more detailed insights into owners' or tenants' social and economic status.
  • Handling uncertain data: At present, we ignore data attributes that do not satisfy certain predetermined formats. Future work could involve taking extra steps to handle these uncertain cases, such as manual checks to verify accuracy, or developing additional strategies for interpretation through hypotheses or further processing (for instance, we ignore very high rent values (5 or 6-digit) for them being the outliers of our data - but was that true or there were these exceptional parcels that are highly expensive due to certain economical situation?)
  • Deepening the connection between Catastici and Sommarioni: We have demonstrated the changes in parcel functions between the Catastici and Sommarioni datasets, which offer historical and economic insights. However, the Sommarioni dataset contains more potential information that requires deeper exploration. For instance, the detailed owner information, including family relationships, titles, and parcel ownership, can be used to detect interesting inheritance patterns (e.g., whether a parcel was inherited from father to son or grandson). This could significantly enhance the summarization text by providing a more nuanced understanding of historical and economic shifts.
  • Extensive model testing and comparative analysis: Due to monetary constraints, we only tested GPT-4 on a subset of samples. Future work should involve refining the pipeline and running the final version over the entire dataset. Additionally, testing with different models and conducting a comparative analysis using existing or new evaluation metrics would provide a more critical and comprehensive assessment of the results. This approach would help in identifying the most effective model and fine-tuning the pipeline for optimal performance.

By addressing these limitations, future work can further enrich the data, improve the accuracy of the generated texts, and provide a more comprehensive understanding of the historical and economic context of Venice during these periods.

Conclusion

Github Repository

GitHub Link

Credits

Course: Foundation of Digital Humanities (DH-405), EPFL
Professor: Frédéric Kaplan
Supervisors: Alexander Rusnak, Tristan Karch, Tommy Bruzzese
Authors: Nastaran Hashemisanjani, Fawzia Zeitoun, Bich Ngoc (Rubi) Doan