Continue Reading

Experiments With Google's PaLM 2 LLM's For Embedding, Summarization, Event & Relation Extraction, NER & Q&A: Bison & Gecko

What does it look like to summarize a television evening news broadcast using Google's PaLM 2 large language model (LLM)?…

Continue Reading

Using Embeddings To Rank Clinical, "Creative" & "Inspired Fiction" Summaries Of An Evening News Broadcast

Earlier this month we demonstrated the use of embeddings to combat hallucination in LLM summarization and as a form of…

Continue Reading

Brookings: Television As Data: Opening The Internet Archive’s Two Decade Archive Of Global Television News Spanning 50 Countries To Journalists & Scholars Through AI, Analytics, Search & Visualization

Kalev spoke at the Brookings Institution this afternoon, surveying GDELT's various datasets and especially its new collaborations with the Internet…

Continue Reading

Cataloging The Core Visual Narratives Of A Year Of Russia 1's "60 Minutes" Using YOLOv8's Pretrained Image Classifier

Last year, in collaboration with the Internet Archive, we demonstrated using the open source YOLO object detection package to analyze…

Continue Reading

ChatGPT Experiments: Autoregressive Large Language Models (AR-LLMs) And The Limits Of Reasoning As Structured Summarization

As we continue to expand our rapidly growing archive of ChatGPT experiments, we can see that, like Whisper, the panacea…

Continue Reading

AI's Pivot To Fluency & Existential Non-Determinism Vs FBIS/BBCM, OSINT & The Centrality Of Fidelity In Translation

One of the most striking aspects of the IC's OSINT efforts over the years from a languages standpoint is the…

Continue Reading

A Look Back On How 2022's AI Developments Brought Home The Perils Of AI's Focus On Fluency Over Fidelity

The past year has marked a watershed moment in the AI landscape, in which a range of applications have burst…

Continue Reading

November Roundup Of Television News Tools & Datasets

In collaboration with the Internet Archive's Television News Archive, we've been rolling out a flood of new tools and datasets…

Continue Reading

Cataloging Two Weeks Of Russia 1 Using Visual Explorer + YOLOv5 Object Detection

Yesterday we demonstrated applying the YOLOv5x pretrained COCO model to a single Russian television news broadcast. Today we are going…

Continue Reading

Visual Explorer + YOLOv5 To Catalog Objects In A Russian TV News Broadcast

YOLO (You Only Look Once) is a popular and widely-used open object detection toolkit that is both extremely fast and…

Continue Reading

Comparing Human Vs Machine Transcription And Translation Of A Russian Television News Broadcast

Yesterday the Russian Media Monitor tweeted out a clip from a Russian television news broadcast with human-translated English language subtitles….

Continue Reading

Automated Transcript & Translation Of Yesterday's 2PM MSK NTV Broadcast

How might automated transcription and translation help make Russian television news more accessible to scholars and journalists? Take yesterday's 2PM…