We present LEMMING, a modular log-linear model that jointly models lemmatization and tagging and supports the integration of arbitrary global features. It is trainable on corpora annotated with gold standard tags and lemmata and does not rely on morphological dictionaries or analyzers. LEMMING sets the new state of the art in token-based statistical lemmatization on six languages; e.g., for Czech lemmatization, we reduce the error by 60%, from 4.05 to 1.58. We also give empirical evidence that jointly modeling morphological tags and lemmata is mutually beneficial.

When you try to describe the much-loved video game Lemmings, it sounds like a wind-up. It looked, if not bad, then wilfully basic even for 1991. But, released years before mobile phone games were a thing, it was nonetheless a fiendishly addictive game that feels like the spiritual precursor to the likes of Angry Birds. And it was manna to many, many kids like me, whose sole household computing device was a rubbish PC with a horrible four-colour CGA screen that basically couldn't play any video game of the time … except Lemmings! To mark 30 years since its release, Exient – current holders of the franchise – has made a YouTube documentary about it.

Monday September 4, join us for a panel with chatbot experts Thomas Schranz, Barbara Ondrisek & Anna Berger at sektor5. Find out about the most interesting use cases for chatbots and what the biggest take-aways are, developing conversations between ANI (Artificial Narrow Intelligence) and humans. Thomas Schranz is the Founder and CEO of Blossom, project tracking for distributed companies, and organizer of Lemmings I/O, a program for everyone who wants to get into AI and building bots. Lemmings started its 3rd batch this Summer. Dr. Barbara Ondrisek, aka "Bot Mother", is a software developer with 15 years of experience.