Students in Ulukhaktok, N.W.T., building app to preserve Inuinnaqtun language
Students at a school in Ulukhaktok, N.W.T., have teamed up with the British Columbia Institute of Technology to develop an app to help preserve the Inuinnaqtun language.
An official language of both the N.W.T. and Nunavut, Inuinnaqtun is the primary Indigenous language spoken in Ulukhaktok and is also spoken in western Kitikmeot communities of Cambridge Bay, Kugluktuk and Gjoa Haven, Nunavut.
But the small number of residents who speak it are growing older in both territories. In the N.W.T. alone, the territory said back in 2019 there were just 259 speakers.
That's part of the reason it became a topic of conversation at a parent-teacher night at Helen Kalvak School. David Leitch, a teacher there, said parents and students wanted to do more with the language and together they came up with the idea last year to create a simple translation app.
"As soon as we got into it, the kids had some pretty fantastic ideas about what they wanted to do, and one of the biggest ones was they wanted to capture the voices of their elders."
Leitch said students started working on the project this year, and it quickly exceeded his capacity for programming – but there was a big breakthrough when they reached out to the British Columbia Institute of Technology (BCIT) for help. A group of students in a computer technology program there agreed to take the project on, said Leitch, and they're creating a large language model – a type of artificial intelligence – that's learning Inuinnaqtun now.
The app is being called Echo of the North and once it's done, Leitch said it'll translate full sentences and will also feature recordings of elders speaking. When someone asks the app for a translation, it'll use that large language model to respond.
Joanne Ogina, an elder in Ulukhaktok who has done some translations for the app, said she likes that it's preserving her language. She said Inuinnaqtun is rarely spoken, unless conversing with someone who is older.
"I'm hoping that it revitalizes it, the speaking of it in our younger generation, because a lot of them rarely speak the language or even have a chance to hear it," she said.
A lot more work to do
Leitch said now that BCIT is helping out, students in Ulukhaktok are focusing their time on interviewing elders, recording their voices, and also uploading "every bit" of Inuinnaqtun to the internet so the AI program can learn it.
"There's actually different dialects of Inuinnaqtun…. Depending on where you are or where you're from, where your family is from."
To reflect those differences, Leitch said users will be able to flag a word in the app and add more information about how it's spelled or pronounced in another dialect – and those details will appear to users as well.
Although students have been working hard on the project, Leitch said there's a long way yet to go. The artificial intelligence has learned the entire Inuinnaqtun dictionary but that means it can only translate word-for-word.
"To really function, it's going to take months and years of our students and our community and elders putting the language, the sentences, the sentence structure, into the database [so] that the AI can learn the language well enough to translate it," said Leitch.
Hashtags
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
8 hours ago
Shark tales: What locals saw, or didn't see, during Passamaquoddy Bay White Shark Week
Saturday was a normal day for Joshua Clinch of St. George, N.B. He, his fiancée and friends decided to go mackerel fishing, a common summertime activity for them. I saw a big flock of birds and some other sea life, said Clinch, describing his view of the area around Campobello Island. "I was sort of watching that way, thinking, 'Oh, maybe we'll see a whale. I'm sure the ladies would like to see a whale.' And all of a sudden I saw the shark fin roll over. That fin moved closer and closer before disappearing. A few minutes later, though, it came up again and began swimming under and around the 17-foot boat. Enlarge image (new window) Clinch didn't know the Passamaquoddy Bay White Shark Week was happening until he posted a clip of his shark encounter online. Photo: CBC / Michael Heenan Originally, we wouldn't have thought it was a white shark at all, said Clinch, a New Brunswick Community College student. "I mean, I was sort of thinking that it was going to be a basking shark or something just because of the sheer size it looked like at a distance. And then obviously, when it got in alongside the boat, we were able to tell, no, it is definitely a white shark. And Clinch isn't the only one in Charlotte County with an up-close shark story. His experience just happened to fall at the tail-end of what was dubbed Passamaquoddy Bay White Shark Week — a different take on the Discovery Channel sensation that has been delivering a week of shark-themed programming every year for 37 years. WATCH | 'That is a big shark' But Clinch had no idea Passamaquoddy shark week was happening until he shared phone footage of the encounter and was told to talk to the professor visiting from the University of Guelph. Stephen Crawford of the department of integrative biology has been coming to Passamaquoddy Bay for three years and recently finished up more interviews on Campobello, Deer and Grand Manan islands with local and Indigenous knowledge keepers about their shark encounters. Crawford believes there is a high possibility that white sharks — popularly known as great whites — are mating in Passamaquoddy Bay, an inlet of the Bay of Fundy between Maine and New Brunswick. I've been all the way through Atlantic Canada, all the way up to Gaspé so far, and I have not found any place where the big 18, 19, 20-foot white sharks are in the numbers and displaying the kinds of behaviour that are consistent with courtship and mating, Crawford said. Enlarge image (new window) During Passamaquoddy Bay White Shark Week, volunteers logged 183 hours of shark-search time over seven days. Photo: CBC / Michael Heenan It may be happening on the other side of Nova Scotia, I would also put a high probability for Cape Breton or off P.E.I., but there is something about Passamaquoddy that is special for the white sharks and their courtship and mating. In Atlantic Canada, white sharks are seasonal migrants in the late summer and early fall. They are classified as endangered in Canada, according to a status report from 2021. (new window) but the population appears to have remained stable since the 1990s and is projected to stay that way or even increase slightly. The sharks are widely distributed but most frequently observed over the continental shelves of the western north Atlantic Ocean, Mediterranean Sea, the north Pacific Ocean, and off the coasts of southern Africa, southern Australia and New Zealand. Crawford said white shark mating has only been documented in New Zealand (new window) , in Otago Harbour. We're looking for that type of an experience here in Passamaquoddy Bay, because when you get that many reports of big animals, it increases the probability. And with shark stories galore, Crawford said, the community decided to form its own shark week, where people would take their vessels out and report their observations. Enlarge image (new window) Stephen Crawford, a University of Guelph professor, has doing research on white sharks and was part of the inaugural Passamaquoddy Bay White Shark Week. Photo: CBC / Michael Heenan According to Crawford's summary, volunteers logged 183 hours of search time over seven days. Kingsley Pendleton of Deer Island, who took his boat out, said it's great to have an online community to share his findings with now. He also thinks it would be good to know if there is white shark mating happening in the bay. Pendleton has lived in the area his entire life. He loves fishing and his wife loves whale watching. One day in 2020, as he and his family left Hardwood Island in Passamaquoddy Bay, Pendleton saw something. As he got closer, he thought it might be a plankton-eating basking shark — the second largest fish in the world. I've only actually seen two in my life, he said. "And I said, 'I'll get 100 yards in front of it and let it swim by us.' And when I did, it turned at me. Enlarge image (new window) Kingsley Pendleton of Deer Island volunteered his time and boat to go looking for white sharks. In 2020, he had his own run-in with one. Photo: CBC / Michael Heenan Pendleton said the shark, which he still thought was a basking shark, started picking up speed, and its fin went underwater. Then, he said, the shark looked at him. I've seen sharks lots of times, he said. I used to drag with my brother, and we caught the odd shark, you know, but they were eight feet, 10 feet, makos or porbeagles. This one was a big, big, great white. The shark resurfaced four times and Pendleton estimates it was between 18 and 20 feet long. After he posted about the experience on Facebook, a shark researcher from Massachusetts contacted him (new window) and said it would have been one of the biggest sharks documented on the East Coast. Pendleton suspects there are more white shark sightings now than there used to be, but one thing he knows has changed — the ability to document an encounter on a cellphone. Volunteers during shark week saw plenty of other creatures while out on the water, including seals, a food source for white sharks. Photo: CBC / Hannah Rudderham Ron Fournier, a helicopter pilot based in St. Stephen who does tours of Saint Andrews, Passamaquoddy Bay, the St. Croix River and Campobello Island areas, said he saw a call for volunteers on the news and decided to help — from above. After all, he had a sighting of his own in May. We weren't looking for anything because … I'm from Alberta, and we don't really look for fish, Fournier said. We were flying by, and we went by Campobello Island, and we saw what looked like two black shadows that looked just like sharks that you see on TV. Fournier said he thinks it's important to document experiences like this. Alexa Meyer, the conservation manager with the Passamaquoddy Recognition Group, the non-profit that represents the Peskotomuhkati Nation, agreed. Alexa Meyer, the conservation manager with the Passamaquoddy Recognition Group, says it's important to understand the current state of the bay as part of efforts to revitalize it. Photo: CBC She said it's important to understand the current state of the bay because it's a piece of the puzzle when it comes to revitalizing it. It's one of the reasons her team wanted to get involved with shark week. Knowing what the sharks are doing can shed light on what other species might be present. Meyer said the volunteer effort is special in another way, too. It reconnects not only people to the lands and the waters again, but also brings out awareness of how beautiful this place is, she said. Crawford now has about 130 interviews for his research program and thinks he has at least a year and a half to go. I can't see me not coming back here, Crawford said. Based on everything that I've heard so far from the Indigenous and local knowledge holders, if anybody's going to find white sharks courtship and mating, I put the highest probability right here in Passamaquoddy Bay. And while no white shark activity was spotted the first six days of the inaugural shark week, which Joshua Clinch didn't even know existed at first, it ended on a high. "You might hear the Jaws music playing in your head, Clinch said. But, I mean, ultimately, I spent a lot of summers out here on the water, and to see something like that up close is a once-in-a-lifetime experience." Hannah Rudderham (new window) · CBC News · Journalist Hannah Rudderham is a reporter with CBC New Brunswick. She grew up in Cape Breton, N.S., and moved to Fredericton in 2018. You can send story tips to With files from Michael Heenan
National Observer
20 hours ago
- National Observer
AI observers hit the high seas
This story was originally published by bioGraphic and appears here as part of the Climate Desk collaboration Accurately monitoring a fishery — knowing how many and which fish species are being caught, and what misfortunate creatures are being dragged in as bycatch along the way — has never been easy. Around the world, the job of keeping tabs on fishers has typically fallen to people called fisheries observers who temporarily join a fishing crew to watch and record. There to take scientific observations and report any rule breaking, these independent monitors often have a difficult and dangerous job. Harassment and unsafe working conditions are common, and violence can be rife. Every year since 2009, at least one fisheries observer has gone missing at sea. In other words, relying on onboard human observers is a notoriously imperfect way to regulate fishing activity. Slightly easier and cheaper, and decidedly much safer, is fitting fishing vessels with cameras that record their catches. But even video review is costly and time-consuming. A single fishing trip can generate hundreds of hours of video footage that someone still has to comb through to identify and count the animals flying past the camera. For small-scale fishers, like those involving Indigenous communities on the west coast of Canada, video monitoring and review can be even more of a burden. Though monitoring is essential for managing fish stocks, the Canadian government's fisheries monitoring system was designed with large, commercial, single-species fishers in mind, says Lauren Dean, a communications specialist for the Ha'oom Fisheries Society, an Indigenous organization representing five First Nations near Tofino, British Columbia. Unlike regular commercial fishers, however, Ha'oom's fishers often embark on relatively modest expeditions targeting several species at once. In the Canadian government's view, each species targeted counts as a different commercial with its own legal monitoring requirements. 'Dealing with five or six different systems for monitoring is simply not viable economically,' Dean says. In recent years, though, a solution has emerged to make fisheries monitoring more accessible, more efficient and safer: artificial intelligence. As machine learning, image recognition and other forms of artificial intelligence grow ever more potent, a startup based in Vancouver and called OnDeck AI is developing a computerized fisheries monitoring system that could radically change the video review process for Ha'oom's fishers and others. Though the system is still in the design and testing stages, OnDeck AI hopes to one day be able to automatically detect and count fish in video footage, streamlining the monitoring process. It has big implications for everything from fisheries management and conservation to Indigenous nations' access to data about their waters and resources. Relying on onboard human observers is a notoriously imperfect way to regulate fishing activity, which is why some are trying to develop artificial intelligence that can aid in the completion of the task — or do it without the need for humans. OnDeck AI is the brainchild of Alexander Dungate, who grew up recreationally catching prawns, crab and sole with his family on the BC coast. In 2021, while studying computer science and biology at the University of British Columbia (UBC), he learned about the world of fisheries monitoring — including the hazardous, sometimes lethal situations faced by independent monitors. He also learned that the archive of fisheries catch footage that has already been amassed is so massive that fully analyzing all of it is nearly impossible. Across the border in the United States, for instance, the Pacific States Marine Fisheries Commission, which helps regulate fisheries in California, Oregon, Washington, Idaho and Alaska, has a year-and-a-half worth of video piled up awaiting review. Dungate reached out to friend and fellow UBC student Sepand Dyanatkar, who was studying machine learning, a branch of AI that focuses on developing algorithms that can learn to analyze data without explicit programming. Building on an AI concept called 'master object tracking,' the pair developed a computer program capable of visually identifying an object — in this case a fish — as it moves through a video. Previous efforts to use AI to audit fisheries catch footage have typically run into the same two types of challenges. One is the generalizability problem. Whether it's turbulent weather, bad lighting, waves and spray splashing the camera or the boat itself getting tossed around in a storm, the qualities of videos captured at sea are highly variable, making analysis difficult. Problem two is the data problem. It takes a significant amount of time and effort to annotate the images and videos needed to train an AI model to pick an individual fish out of an endless barrage of footage, let alone recognize the species. What's more, training a typical AI system to recognize all the rare species — which are often the most important given their ecological significance — is simply not possible, says Dungate, since there just isn't enough footage to work from. For instance, if a killer whale accidentally gets caught in a fisher's net, 'we really need to be able to recognize that. But there's maybe three photos on Earth of that happening,' Dungate says. OnDeck AI sidesteps those issues by designing their system to bypass the need for labeled training data by giving the model the ability to recognize what it's seeing across any setting, including with footage of varying quality captured by different types of cameras in changing weather. Dungate likens the difference between traditional AI models and OnDeck AI's to the difference between memorizing the answers to a test and using more complex reasoning to figure out the answers. In other words, it's being able to identify a fish based on its coloring, shape, and fin structure — even if the system has never seen it before. That's the long-term objective, at least. But for now, OnDeck AI's model needs more priming. So last summer, the company trained its AI system on Ha'oom's video footage. To do that, Jessica Edwards, a Ha'oom biologist, analyzed catch footage alongside the AI. If the model failed to recognize a particular fish in the video feed, Edwards would draw a box around the overlooked animal to teach the algorithm. The goal, Edwards says, is to get the AI system to do as good a job as a human — or better — but in less time. Even before getting to that point, the AI can help an auditor do their job faster by identifying when a fish appears in the footage, allowing them to skip forward to relevant segments of the video rather than having to go through the whole feed. While OnDeck's AI system still needs more tuning, scientists and engineers elsewhere are also trying to crack the AI fisheries observer problem. Some, like a team in Australia, are developing an AI system capable of distinguishing between 12 different species in video footage. Working with the Australian longline tuna and billfish fishers, their system picks the right species roughly 90 per cent of the time. Bubba Cook, the policy director for Sharks Pacific, a New Zealand-based NGO, believes AI-driven monitoring could dramatically increase how much of the world's oceans are under some sort of surveillance. Only a small fraction of the world's fisheries — roughly two per cent — are currently monitored by observers, meaning the vast majority of fishing activity, including the bycatch of protected species, happens without oversight. Though human observers will still be necessary for things like tissue sampling, 'the reality is,' says Cook, that 'electronic monitoring coupled with AI review is the only way we're going to get the level of observer coverage we need.'
Toronto Star
4 days ago
- Toronto Star
Ottawa, B.C. provide $77M to bring high-speed internet to nearly 7,000 households
ARMSTRONG, B.C. - The federal and B.C. governments are providing more than $77 million in combined funding to bring high-speed internet to more than 6,900 homes in the province. A statement from Innovation, Science and Economic Development Canada says the funding is part of an agreement struck in 2022 that committed up to $830 million to bridge the high-speed gap in rural, remote and Indigenous communities.
