TaBERT: A new model for understanding queries over tabular data
1–10 of 26 posts
Re: TaBERT: A new model for understanding queries over tabular data
#2Git repo or it doesn't exist ;-)
Seriously, if this is not available, what are the alternatives?
I've seen in the past some NLP + Storage project but I don't recall them. (even remotely connected, there was something to convert PDFs into machine readable data).
Is this AwesomeNLP https://github.com/keon/awesome-nlp a good starting point there?
Re: TaBERT: A new model for understanding queries over tabular data
#3Git repo or it doesn't exist ;-) Seriously, if this is not available, what are the alternatives? I've seen in the past some NLP + Storage project but I don't recall them. (even remotely connected, there was something to convert PDFs into machine readable data). Is this AwesomeNLP https://github.com/keon/awesome-nlp a good starting point there?
it's in the paper
Re: TaBERT: A new model for understanding queries over tabular data
#4Does anyone know how it relates/compares to Google's TaPaS? [1]
I notice this paper doesn't refer to it.
[1] https://ai.googleblog.com/2020/04/using-neural-networks-to-f...
Re: TaBERT: A new model for understanding queries over tabular data
#5Seems similar to this work out of Salesforce a few years ago: https://www.salesforce.com/blog/2017/08/salesforce-research-...
Re: TaBERT: A new model for understanding queries over tabular data
#6I'd like to see something that could do this, handling the awfulness of real world tabular data. "What country has the highest GDP? Okay, which table has GDP? Is it the country_gdp table? No, that's an old one that hasn't been written to in 3 years. Ah here it is, but you need to join against `geopolitics`, but first dedup the crimea data, since it's showing up in two places, we're can't remember why it got written to twice there. Also, you need to exclude June 21 because we had an outage on the brazil data that day. What do you mean some of the country_id rows are NULL?" And so on. I dream that someday there's a solution for that. That's a looooong ways away, I'd bet.
Re: TaBERT: A new model for understanding queries over tabular data
#7I'd like to see something that could do this, handling the awfulness of real world tabular data. "What country has the highest GDP? Okay, which table has GDP? Is it the country_gdp table? No, that's an old one that hasn't been written to in 3 years. Ah here it is, but you need to join against `geopolitics`, but first dedup the crimea data, since it's showing up in two places, we're can't remember why it got written t…
The tough thing is that a common failure mode of many of the modern AI solutions is some output that looks superficially correct, but doesn't actually map correctly to the real world. When you want a table of data, it seems like the danger will be high that the table looks correct but isn't actually accurate. The problem here is about keeping sloppy data out of your table, which is tough for a statistical AI.
So yeah, I would expect this to be a long ways away.
Re: TaBERT: A new model for understanding queries over tabular data
#8I thought Google already did something similar?
Are we entering deep copycat culture?
Re: TaBERT: A new model for understanding queries over tabular data
#9I'd like to see something that could do this, handling the awfulness of real world tabular data. "What country has the highest GDP? Okay, which table has GDP? Is it the country_gdp table? No, that's an old one that hasn't been written to in 3 years. Ah here it is, but you need to join against `geopolitics`, but first dedup the crimea data, since it's showing up in two places, we're can't remember why it got written t…
The tough thing is that a common failure mode of many of the modern AI solutions is some output that looks superficially correct, but doesn't actually map correctly to the real world. When you want a table of data, it seems like the danger will be high that the table looks correct but isn't actually accurate. The problem here is about keeping sloppy data out of your table, which is tough for a statistical AI. So yeah…
For more interesting problems than "which country has the highest GDP?", it's about more than just sloppy data. If you want to include any covariates, how do you know which ones to include? You could try to include everything predictive, but then you'll use the client margin column to predict client revenue or something. Or you'll control for a column causally downstream, biasing your estimates, like estimating revenue differences and controlling for page views in an experiment that affects page views. There's so much that we just don't include in our databases that's crucial to using them, and it's not just about sloppiness.
Re: TaBERT: A new model for understanding queries over tabular data
#10I'd like to see something that could do this, handling the awfulness of real world tabular data. "What country has the highest GDP? Okay, which table has GDP? Is it the country_gdp table? No, that's an old one that hasn't been written to in 3 years. Ah here it is, but you need to join against `geopolitics`, but first dedup the crimea data, since it's showing up in two places, we're can't remember why it got written t…
The tough thing is that a common failure mode of many of the modern AI solutions is some output that looks superficially correct, but doesn't actually map correctly to the real world. When you want a table of data, it seems like the danger will be high that the table looks correct but isn't actually accurate. The problem here is about keeping sloppy data out of your table, which is tough for a statistical AI. So yeah…
tbf that problem is also quite tough for data scientists, the model doesnt need to be flawless just better