Agent Spotlight: Ashley Holmquist, Cat Rescuing Superhero
January 19, 2023
Amanda Simioni
Multi-Talented And Adventurous Entrepreneur From Brazil
March 15, 2023
2
min to Read
Invisible Spotlight
"I'm very proud of my entrepreneurship and my independence."
Meet Amanda, an agent who became part of the Invisible family a year and 5 months ago.
We reached out to learn more about her!
Rio de Janeiro, Brazil.
I am a very logical, curious, and adventurous person. I'm constantly questioning how many unexplored possibilities there are for both simple and complex problems. I grew up to be a very transdisciplinary thinker; I cannot help but piece out different knowledge fields to reflect on the things in my life. I love a good debate, and to surround myself with art and flowers. Finally, I'm a chronic overthinker!
I love creating flower arrangements. In general, mixing and matching colors and scents gives me the sensation that I'm doing an alchemist's work, which is magical. I like painting and visiting public places to patiently observe how people act and move. Some other hobbies include: reading, going to the theater, watching movies, and dancing.
I was doing my Master's in International Political Economy at the Federal University of Rio de Janeiro. I was a fully funded researcher and dedicated my time integrally to conducting research, teaching, reviewing articles, organizing events, and all things related to the Academics. I also worked in politics and marketing advising.
It's been quite a while since I joined Invisible. I was attracted by a very interesting role immersed in a global and diverse culture. I always loved food, and at the apex of pandemics I felt an immense will to contribute to the thriving community of restaurants I would be digitalizing data for, bringing the visibility they deserved. The role taught me a ton, and I loved my team. It was truly remarkable how much I got to learn and the steps I took in growing.
In the collection of memories from invisible, one of my fondest is my last day as Squad Lead at the Brown Team. To give a brief introduction, we worked the last semester together and bonded. We were curious about each other's culture and struggles, and liked to hear about each other's day, and stayed until late off-hours keeping each other company. I got to lead the team for approximately two months, and I learned plenty from my leader at the time. She took the team from the beginning and really raised the bar as she did a marvelous job connecting us as the beautiful group we turned into. After she left, I felt the pressure - it was not the first time I managed a team, but I still got butterflies. It took time and effort as I cared a lot about my colleagues and friends and wanted us to maintain top-notch quality. Of all the teams at the time, Brown was one of the shyest. We only turned our cameras after several months (yet, there are people I have yet to see). When, after two months, the moment to say goodbye arrived, I was surprised with a very affectionate farewell. To my surprise, almost everyone turned their cameras on, and I felt grateful and happy to see their effort to be there and show they valued me as their manager and friend.
01|
02|
03|
I'm very proud of my entrepreneurship and my independence. I felt the strong urge to leave home at 18 to pursue my bachelor's degree at a distinguished university. Years later, I received a scholarship to conduct field research in Venezuela, which was published as my final thesis. Again, years later, I would decide to move to Rio de Janeiro after being awarded a scholarship to continue my research career at one of Latin America's most prestigious universities.
It is geared towards autonomy and owning your work; it's an ever-evolving and ever-changing environment for people who embrace change as a constructive force. There is room for logical and stability enthusiasts, but not the environment if you're stubborn. It's about knowing your expertise and ensuring you're communicating that to best contribute and learn. Also, brace yourself for the accelerated learning curve you'll find here.
Improve with each coming day, I'm never stagnant. I'm grateful for the work I get to do every day and the unique people I share it with. I like how open and horizontal the communication is and the available possibilities. My main concern is delivering the best work possible, and I'm happy to invest my time in improving and learning all things that will make me accomplish that.
It's about knowing your expertise and ensuring you're communicating that to best contribute and learn.
We value your critical thinking at Invisible, Amanda!!
Want to join an elite team of global professionals?
.svg)
Meet Amanda, an agent who became part of the Invisible family a year and 5 months ago.
We reached out to learn more about her!
Rio de Janeiro, Brazil.
I am a very logical, curious, and adventurous person. I'm constantly questioning how many unexplored possibilities there are for both simple and complex problems. I grew up to be a very transdisciplinary thinker; I cannot help but piece out different knowledge fields to reflect on the things in my life. I love a good debate, and to surround myself with art and flowers. Finally, I'm a chronic overthinker!
I love creating flower arrangements. In general, mixing and matching colors and scents gives me the sensation that I'm doing an alchemist's work, which is magical. I like painting and visiting public places to patiently observe how people act and move. Some other hobbies include: reading, going to the theater, watching movies, and dancing.
I was doing my Master's in International Political Economy at the Federal University of Rio de Janeiro. I was a fully funded researcher and dedicated my time integrally to conducting research, teaching, reviewing articles, organizing events, and all things related to the Academics. I also worked in politics and marketing advising.
It's been quite a while since I joined Invisible. I was attracted by a very interesting role immersed in a global and diverse culture. I always loved food, and at the apex of pandemics I felt an immense will to contribute to the thriving community of restaurants I would be digitalizing data for, bringing the visibility they deserved. The role taught me a ton, and I loved my team. It was truly remarkable how much I got to learn and the steps I took in growing.
In the collection of memories from invisible, one of my fondest is my last day as Squad Lead at the Brown Team. To give a brief introduction, we worked the last semester together and bonded. We were curious about each other's culture and struggles, and liked to hear about each other's day, and stayed until late off-hours keeping each other company. I got to lead the team for approximately two months, and I learned plenty from my leader at the time. She took the team from the beginning and really raised the bar as she did a marvelous job connecting us as the beautiful group we turned into. After she left, I felt the pressure - it was not the first time I managed a team, but I still got butterflies. It took time and effort as I cared a lot about my colleagues and friends and wanted us to maintain top-notch quality. Of all the teams at the time, Brown was one of the shyest. We only turned our cameras after several months (yet, there are people I have yet to see). When, after two months, the moment to say goodbye arrived, I was surprised with a very affectionate farewell. To my surprise, almost everyone turned their cameras on, and I felt grateful and happy to see their effort to be there and show they valued me as their manager and friend.
LLM Task
Benchmark Dataset/Corpus
Common Metric
Dataset available at
Sentiment Analysis
SST-1/SST-2
Accuracy
https://huggingface
.co/datasets/sst2
Natural Language Inference / Recognizing Textual Entailment
Stanford Natural Language Inference Corpus (SNLI)
Accuracy
https://nlp.stanford.edu
projects/snli/
Named Entity Recognition
conll-2003
F1 Score
https://huggingface.co/
datasets/conll2003
Question Answering
SQuAD
F1 Score, Exact Match, ROUGE
https://rajpurkar.github.i
o/SQuAD-explorer/
Machine Translation
WMT
BLEU, METEOR
https://machinetranslate
.org/wmt
Text Summarization
CNN/Daily Mail Dataset
ROUGE
https://www.tensorflow
.org/datasets/catalog/
cnn_dailymail
Text Generation
WikiText
BLEU, ROUGE
Paraphrasing
MRPC
ROUGE, BLEU
https://www.microsoft.
com/en-us/download/details.a
spx?id=52398
Language Modelling
Penn Tree Bank
Perplexity
https://zenodo.org/recor
d/3910021#.ZB3qdHbP
23A
Bias Detection
StereoSet
Bias Score, Differential Performance
Table 1 - Example of some LLM tasks with common benchmark datasets and their respective metrics. Please note for many of these tasks, there are multiple benchmark datasets, some of which have not been mentioned here.
Metric
Usage
Pros
Cons
Accuracy
Measures the proportion of correct predictions made by the model compared to the total number of predictions.
Simple interpretability. Provides an overall measure of model performance.
Sensitive to dataset imbalances, which can make it not informative. Does not take into account false positives and false negatives.
Precision
Measures the proportion of true positives out of all positive predictions.
Useful when the cost of false positives is high. Measures the accuracy of positive predictions.
Does not take into account false negatives.Depends on other metrics to be informative (cannot be used alone).Sensitive to dataset imbalances.
Recall
Measures the proportion of true positives out of all actual positive instances.
Useful when the cost of false negatives is high.
Does not take into account false negatives.Depends on other metrics to be informative (cannot be used alone)and Sensitive to dataset imbalances.
F1 Score
Measures the harmonic mean of precision and recall.
Robust to imbalanced datasets.
Assumes equal importance of precision and recall.May not be suitable for multi-class classification problems with different class distributions.
Perplexity
Measures the model's uncertainty in predicting the next token (common in text generation tasks).
Interpretable as it provides a single value for model performance.
May not directly correlate with human judgment.
BLEU
Measures the similarity between machine-generated text and reference text.
Correlates well with human judgment.Easily interpretable for measuring translation quality.
Does not directly explain the performance on certain tasks (but correlates with human judgment).Lacks sensitivity to word order and semantic meaning.
ROUGE
Measures the similarity between machine-generated and human-generated text.
Has multiple variants to capture different aspects of similarity.
May not capture semantic similarity beyond n-grams or LCS.Limited to measuring surface-level overlap.
METEOR
Measures the similarity between machine-generated translations and reference translations.
Addresses some limitations of BLEU, such as recall and synonyms.
May have higher computational complexity compared to BLEU or ROUGE.Requires linguistic resources for matching, which may not be available for all languages.
Table 2 - Common LLM metrics, their usage as a measurement tool, and their pros and cons. Note that for some of these metrics there exist different versions. For example, some of the versions of ROUGE include ROUGE-N, ROUGE-L, and ROUGE-W. For context, ROUGE-N measures the overlap of sequences of n-length-words between the text reference and the model-generated text. ROUGE-L measures the overlap between the longest common subsequence of tokens in the reference text and generated text, regardless of order. ROUGE-W on the other hand, assigns weights (relative importances) to longer common sub-sequences of common tokens (similar to ROUGE-L but with added weights). A combination of the most relevant variants of a metric, like ROUGE is selected for comprehensive evaluation.
.png)
