Grupo 0
| Retention Period
|
Group 0
(No treatment)
|
Groups 1 and 2
|
| 1-day average return rate:
|
35.4%
|
34.9%
|
| 3-day average return rate:
|
29.5%
|
30.3%
|
| 7-day average return rate:
|
22.6%
|
24.1%
|
| 14-day average return rate:
|
14.7%
|
15.8%
|
- Nota: Usuarios expuestos a descripciones breves automáticas asistidas tuvieron una tasa mayor de retorno, en comparación a usuarios que no estuvieron expuestos a la función
Próximos Pasos:
El experimento fue hecho en servicios de la Nube, la cual no es una solucion sostenible. Hubo suficientes indicadores positivos para hacer que la función se habilite para las comunidades que lo deseen. El equipo de aplicaciones trabajará en conjunto con nuestro Aprendizaje Automatizado para migrar el modelo a Liftwing. Una vez migrada, y habiéndose testeado lo suficiente su funcionamiento, regresaremos a interactuar con las comunidades de idiomas para determinar dónde habilitar la función y qué mejoras adicionales se pueden sumar al modelo. Las modificaciones que se consideran actualmente son:
- Prohibir Biografías de personas vivas: Durante el experimento permitimos que usuarios con mas de 50 ediciones añadieran descripciones breves a Biografías de personas vivas con asistencia automatizada. Reconocemos las inquietudes que pesan sobre sugerencias de descripciones breves permanentes en estos artículos. No evidenciamos problemas relacionados a Biografías de Personas Vivas, pero estamos conformes sin mostrar sugerencias en este tipo de biografías.
- Utilizar solo la Ruta 1: La Ruta 1 superó continuamente a la Ruts 2 en sugerencias. Como resultado, solo mostraremos una recomendación, la cual pertenece a la Ruta 1.
- Modificar la incorporación y la guía: Durante el experimento, existió una pantalla de bienvenida a las sugerencias automatizadas. Nos gustaría incorporar estas cuando se estrene la función. Sería de gran ayuda recibir los comentarios de la comunidad sobre adiciones que les gustaría que realicemos para que escribir descripciones breves sea más eficiente, y asi poder mejorar su inclusión.
De existir errores evidentes, por favor deje un mensaje en la página de discusión del proyecto, para así poder corregirlos. Un ejemplo de error evidente son las fechas erróneas, que notamos durante las pruebas de la aplicacion, y se añadió un filtro que previene descripciones breves con fechas que no son mencionadas en el texto del artículo. También notamos que se recomendaba páginas de desambiguación en el modelo original, por lo que las retiramos en la interfaz de cliente, un cambio que prentendemos mantener permanentemente. Otros cambios, como el uso de mayúsculas en la primera letra, son cambios generales que podríamos hacer, ya que hay una clara trayectoria para usar en su implementación.
Para idiomas en los que el modelo no esta funcionando suficientemente bien para ser desplegado completamente, lo mas útil es añadir más descripciones breves de artículos en el idioma, asi el despliegue del modelo tendrá mas informacion con la que podrá continuar. No existe una fecha o una frecuencia fija en este punto; sin embargo, para ello se volverá a entrenar el modelo. Podemos trabajar con el equipo de Investigación y Aprendizaje Automático para que esto se priorice a medida que las comunidades lo soliciten.
July 2023: Early Insights from 32 Days of Data Analysis: Grading Scores and Editing Patterns
We can not complete our data analysis until all entries have been graded so that we have an accurate grading score. However we do have early insights we can share. These insights are based on 32 days of data:
- 3968 Articles with Machine Edits were exposed to 375 editors.
- Note: Exposed does not mean selected.
- 2125 Machine edits were published by 256 editors
- Editors with 50+ edits completed three times the amount of edits per unique compared to editors with less than 50 edits
May 2023: Experiment Deactivated & Volunteers Evaluate Article Short Descriptions
The experiment has officially been deactivated and we are now in a period of edits being graded.
Volunteers across several language Wikis have begun to evaluate both human generated and machine assisted article short descriptions.
We express our sincere gratitude and appreciation to all the volunteers, and have added a dedicated section to honor their efforts on the project page. Thank you for your support!
We are still welcoming support from the following language Wikipedias for grading: Arabic, English, French, German, Italian, Japanese, Russian, Spanish, and Turkish languages.
If you are interested in joining us for this incredible project, please reach out to Amal Ramadan. We look forward to collaborating with passionate individuals like you!
April 2023: FAQ Page and Model Card
We released our experiment in the 25 mBART languages this month and it will run until mid-May. Prior to release we added a model card to our FAQ page to provide transparency into how the model works.
This is the onboarding process:
January 2023: Updated Designs
After determining that the suggestions could be embedded in the existing article short descriptions task the Android team made updates to our design.
-
Tooltip to as onboarding of feature
-
Once the tooltip is dismissed the keyboard becomes active
-
Dialog appears with suggestions when users tap "show suggested descriptions"
-
Tapping a suggestion populates text field and publish button becomes active
If a user reports a suggestion, they will see the same dialog as we proposed in our August 2022 update as the what will be seen if someone clicks Not Sure.
This new design does mean we will allow users to publish their edits, as they would be able to without the machine generated suggestions. However, our team will patrol the edits that are made through this experiment to ensure we do not overwhelm volunteer patrollers. Additionally, new users will not receive suggestions for Biographies of Living Persons.
November 2022: API Development
The Research team put the model on toolforge and tested the performance of the API.
Initial insights found that it took 5-10 seconds to generate suggestions, which also varied depending on how many suggestions were being shown. Performance improved as the number of suggestions generated decreased. Ways of addressing this problem was by preloading some suggestions, restricting the number of suggestions shown when integrated into article short descriptions, and altering user flows to ensure suggestions can be generated in the background.
August 2022: Initial Design Concepts and Guardrails for Bias
When I am using the Wikipedia Android app, am logged in, and discover a tooltip about a new edit feature, I want to be educated about the task, so I can consider trying it out.
Open Question: When should this tooltip be seen in relation to other tooltips?
When I want to try out the article short descriptions feature, I want to be educated about the task, so my expectations are set correctly.
User story for adding descriptions
When I use the article short descriptions feature, I want to see articles without a description, I want to be presented with two suitable descriptions and an option to add a description of my own, so I can select or add a description for multiple articles in a row.
-
Concept for selecting a suggested article description
-
Design concept for a user deciding the description should be an alternative to what is listed
-
Design concept for a user editing a suggestion before hitting publish
-
Design concept for what users see when pressing other
-
Screen displaying options for if a user says they are not sure what the correct article description should be
Guardrails for bias and harm
The team generated possible guardrails for bias and harm:
- Harm: problematic text recommendations
- Guardrail: blocklist of words never to use
- Guardrail: check for stereotypes – e.g., gendered language + occupations
- Harm: poor quality of recommendations
- Guardrail: minimum amount of information in article
- Guardrail: verify performance by knowledge gap
- Harm: recommendations only for some types of articles
- Guardrail: monitor edit distribution by topic
|
