AI and Ancestry Hints

While AI and OCR recognition have been used for quite some time, it's only been in recent months I've seen an increase in inaccurate hints on Ancestry. It seems to correspond with the widespread increase in the use of AI across the board. While I absolutely appreciate more possible records for my relatives and ancestors, you never know when an "ah ha!" hint will appear, I can't help but notice how many new hints are not relevant. AI considerably reduces the necessity for human intervention and indexing. Combined with the magical algorithms, one would certainly expect many new results as this technology takes hold. But it's far from perfect. 

In the past, I'd estimate 95% of the hinting was pretty accurate for my tree (not including user uploaded media potentially appearing more than once). There were always a few scattered incorrect records suggested, but by in large, I was quite happy with results I received. I suspect many of those incorrect hints were the result of the algorithm picking up on records attached in other trees. Now, I'm finding more inaccurate records than ever before, especially in the hints pulled from newspapers and yearbooks. It seems like the combination of AI and algorithms may not be filtering as well as I've been used to. Now, I have a "reject rate" of closer to 15%.

I've found numerous newspaper hints where the person in my tree would have been a youngster, far tooo young to be the subject of a newspaper article. And many appear to be picking up on a spouse (showing a Mrs. [fill in the blank]) when the person being researched is not female (and most often has no tie to the article referenced). I've also noticed the algorithm seems to combine names (example: Mr. Bill Jones went to the home of Mr. Wayne Smith might produce a hint for Bill Smith in my tree). When it comes to yearbooks, the algorithms are often pulling women's married surname instead of their maiden surname (and while it's possible these women might have been married while still in school, it's unlikely.)

I'm a big fan of AI overall and I use it daily as my "assistant", helping me format, translate/transcribe and extract data. I absolutely believe it has a very valid use when it comes to scanning large data sets to provide us with new hints. I just wish they'd tighten up some of the parameters, or perhaps run a second scan of the potential records to weed out some of the inaccuracies. I fear click-happy new researchers (I was one of them back when I started!) will attach anything and everything without proper vetting, causing inaccuracies to populate even faster.

Of course, it is (and always has been ) the responsibility of each researcher to determine if records apply or not. This is not new! Only you can determine if you believe a hint is accurate or not. Over time, I suspect we'll see the inaccurate results decrease as people reject irrelevant hints, and algoritms are tweaked, I believe we'll ultimately see overall improvements in hinting. But for the short term, we may need to be a little more careful evaluating new hints. 

One final thought...it's important to note, correlation is not necessarily an indication of causation. I could be totally wrong in my observations. Perhaps it's simply the addition of new newspapers and yearbooks. Perhaps I've been underestimating my previous "reject rate". Have you seen any trends in Ancestry hinting since AI has become more widespread? I'd love to hear your comments and thoughts.

Image by Gerd Altmann from Pixabay

Latin Names in Church Records

 

When I'm working on my ex-husband's family line, I routinely encounter Catholic parish/church records. I took two years of Latin in middle school, but sadly, there's not much left in my aging memory bank. It can be a challenge to figure out if the person in the record is the same person as in my tree. 

To be fair, most of the Latin records I encounter, I don't need to translate word for word. Knowing a record is for a baptism or death, I can usually suss out the dates and locations well enough to enter data in my tree. If I were to stumble across a record I think I might need to translate, I'd more than likely use AI to assist me. Only if I had no other choice, or the record seemed so tantalizing it was worth the effort, would I try to decipher word by word. 

The challenge for me is names in Latin. From Wikipedia, "Latinisation (or Latinization) of names, also known as onomastic Latinisation, is the practice of rendering a non-Latin name in a modern Latin style. It is commonly found with historical proper names, including personal names..." In this branch of the family, I'm often starting with a foreign name and then I'm encountering this foreign name in Latin. It can leave me scratching my head!

A good example is Hermann Franz Berendes (1825-1910). Born in Germany (also shown as Prussia in some records) to parents Wilhelm and Anna Berendes, I have a good inking he probably wouldn't have gone by his original given name once he arrived here in the United States. In an effort to sound more American, he likely would have gone by Herman Frank Berendes or Herman Francis Berendes. As it turns out, he appears to have gone simply by Frank Berendes in most records. His parents are most likely going to be shown as William and Anna, or Anne.

To illustrate the challenge of records in Latin, I'd probably be looking for Franciscus filius (son of) Guglielmus, Gulielmus, Guilhelmus, Gulielmo, or Gulielmum (yup, all those indicate William in Latin) and Anna.  It can get even more confusing when Latinate suffixes have been used to create the genitive tense (used to show relationships) for the person(s) in the record. For instance, Guglielmus would become Guglielmi to signify the father. and Anna becomes Annae for the mother. So now, instead of looking for Frank son of William and Anne, I'm looking for Franciscus filius Guglielmi (or any one of the many other possible forms of William) and Annae. It's not rocket science, but it can take a bit of dilligence.

After struggling repeatedly with these types of records, I found a listing of Latin names on Family Tree Forum. It's certainly not all inclusive, but it is simply organized and searching (using Ctrl+F) within the page works quite well. Rules for the different genitive forms based on father, mother, bride of, etc are included. There are plenty of sites out there to assist with Latin translations, but this list of names is simple and straightforward. Thus far, it's been sufficient to meet my research needs. 

Next time you run into onomastic Latinisation, you'll eiher have a handy reference...or you'll be able to win at Trivial Pursuit (if there's a quesiton about a dead language used to convolute common names beyond all recognition in church records). Either way, I've added a section for Names in my Genealogy Toolbox (and moved a few existing links to this section to make them easier to find). Enjoy!