Wouldn’t it solve so many problems in the world if everyone just spoke the same language? Not so fast! 

Lingthusiasm is a brand-new podcast that’s enthusiastic about linguistics, hosted by Lauren Gawne of Superlinguo​ and Gretchen McCulloch of All Things Linguistic.

In this first episode of Lingthusiasm, ​Gretchen and Lauren discuss the “one language equals peace” fallacy, and whether speaking the same words means that people will necessarily agree with each other (spoiler: no). But the history of how people have tried is still really interesting, from constructed and symbolic communication like Blissymbols and emoji to the way astronauts communicate in the high stakes environment of the International Space Station.

For links to things mentioned during this episode visit http://lingthusiasm.com/post/154520059101/lingthusiasm-episode-1-speaking-a-single-language

Listen to bonus episodes, suggest future topics, and help keep the show ad-free by supporting us on Patreon: http://patreon.com/lingthusiasm

01: Speaking a single language won’t bring about world peace

There are some pretty funny quotes of historical people complaining about kids back then doing linguistic things that now seem totally unremarkable. So let’s cut to the chase and celebrate linguistic innovation while it’s happening. 

In episode 7 of Lingthusiasm, your hosts Lauren Gawne and Gretchen McCulloch explore how far back we can trace complaints about the language of Kids These Days, why linguistic discrimination is harmful, and why “be like”, hyperbolic “literally”, and other modern innovations are actually signs of something awesome. 

We also announce a Patreon to keep the podcast sustainable! You can support us there to listen to a bonus episode about swearing and future monthly bonus content, and help decide the topics of future episodes. Even if you’re not sure about pledging, do check out the Patreon goals to see some of our future plans and our video to see a totally realistic and not at all staged cameo from our producer. Check out http://patreon.com/lingthusiasm 

For more information visit the show page: http://lingthusiasm.com/post/159796192161/lingthusiasm-episode-7-kids-these-days-arent

07: Kids these days aren’t ruining language

An interview with Chris Dyer.

https://www.semanticscholar.org/paper/Recurrent-Neural-Network-Grammars-Dyer-Kuncoro/1594d954abc650bce2db445c52a76e49655efb0c

04 - Recurrent Neural Network Grammars, with Chris Dyer

https://www.semanticscholar.org/paper/Capturing-Semantic-Similarity-for-Entity-Linking-w-Francis-Landau-Durrett/1c9aca60f7ac5edcceb73d612806704a7d662643

07 - Capturing Semantic Similarity for Entity Linking with Convolutional Neural Networks

How do we get from knowing words to making brand-new sentences out of them? In episode 9 of Lingthusiasm, your hosts Gretchen McCulloch and Lauren Gawne talk about how words form groups with other words: constituency. 

Once you start looking for it, constituency is everywhere: in ambiguous sentences like “time flies like an arrow; fruit flies like a banana”, in remixed films like “Of Oz The Wizard”, and even internet dog memes.

This month’s Patreon bonus was the backstory about the linguistics of the doggo meme and its connection to Australian slang, which grew out of this NPR article about doggo. You can get access to it and previous bonuses about swearing, teaching yourself linguistics, and explaining linguistics to employers by supporting Lingthusiasm on Patreon.

For more information, and links to things mentioned in this episode, visit the show page: http://lingthusiasm.com/post/161859273886/lingthusiasm-episode-9-the-bridge-between-words

09: The bridge between words and sentences - Constituency

Some linguists work with multiple languages, while others focus on just one. But for many people, learning a language after early childhood is the thing that first gets them curious about how language works in general and all the things in their native language(s) that they take for granted. 

In episode 10 of Lingthusiasm, your hosts Gretchen McCulloch and Lauren Gawne talk about how learning languages can feed into linguistics and vice versa. We also explore the power dynamics that affect learning languages, and the importance of learning about the rules of interaction as well as the rules of grammar.

This month’s Patreon bonus was about hypercorrection, where you try so hard to follow a linguistic rule that you end up overshooting. You can get access to it and previous bonuses about the doggo meme, swearing, teaching yourself linguistics, and explaining linguistics to employers by supporting Lingthusiasm on Patreon. http://patreon.com/lingthusiasm

Gretchen’s new recorder in this episode is thanks to the support of our patrons! 

For more information, and links to things mentioned in this episode, visit the show page: http://lingthusiasm.com/post/163226798571/lingthusiasm-episode-10-learning-languages

10: Learning languages linguistically

AAAI 2017 paper, by Dan Roth.

In this episode we have a conversation with Dan about what he means by "incidental supervision", and how it's related to ideas in reinforcement learning and representation learning.  For many tasks, there are signals you can get from seemingly unrelated data that will help you in making predictions.  Leveraging the international news cycle to learn transliteration models for named entities is one example of this, as is the current trend in NLP of using language models or other multi-task signals to do better representation learning for your end task.  Dan argues that we need to be thinking about this more explicitly in our research, instead of learning everything "end-to-end", as we will never have enough data to learn complex tasks directly from annotations alone.

https://www.semanticscholar.org/paper/Incidental-Supervision-Moving-beyond-Supervised-Le-Roth/2997dcfc6d5ffc262d57d0a26f74d091de096573

48 - Incidental Supervision: Moving Beyond Supervised Learning, with Dan Roth

TACL 2018 paper by Jacob Buckman and Graham Neubig. 

Jacob tells us about marginalizing over latent structure in a sentence by doing a clever parameterization of a lattice with a model kind of like a tree LSTM.  This lets you treat collocations as multi-word units, or allow words to have multiple senses, without having to commit to a particular segmentation or word sense disambiguation up front.  We talk about how this works and what comes out.  One interesting result that comes out of the sense lattice: learning word senses from a language modeling objective tends to give you senses that capture the mode of the "next word" distribution, like uses of "bank" that are always followed by "of".  Helpful for local perplexity, but not really what you want if you're looking for semantic senses, probably.

https://www.semanticscholar.org/paper/Neural-Lattice-Language-Models-Buckman-Neubig/f36b961ea5106c19c341763bd9942c1f09038e5d

Jacob Buckman

63 - Neural Lattice Language Models, with Jacob Buckman

When we think about language, we generally think about things that are visible or audible: letters, sounds, signs, words, symbols, sentences. We don’t often think about the lack of anything. But little bits of silence or invisibility are found surprisingly often throughout our linguistic system, from the micro level of an individual sound or bit of meaning to the macro level of sentences and conversations.  

In this episode of the podcast that’s enthusiastic about linguistics, your hosts Lauren Gawne and Gretchen McCulloch get enthusiastic about four different kinds of linguistic nothings: silence in between turns, silence in between sounds, invisible units of meaning, and invisible words. (Officially known as turntaking, glottal stops, zero morphemes, and traces.) 

We also announced some details about our upcoming liveshow! Our last liveshow was in Montreal where Gretchen lives, so it’s only fair that our next official show is in Lauren’s hometown of Melbourne! It’ll be sometime in November. Stay tuned for the exact date and venue - you can sign up for Lingthusiasm email updates if you want to be sent it directly: bit.ly/LingthusiasmEmailList  

Gretchen will also be around for the Centre of Excellence for the Dynamics of Language Summer School in Canberra and the annual Australian Linguistics Society conference in Adelaide. If anyone else in Australia wants to invite her to anything in November or early December 2018, now’s your chance! 

This month’s bonus episode was an inside view into the linguistics conference circuit which Lauren and Gretchen are recently returned from, featuring emoji, gesture, and the International Congress of Linguists! Support the show on Patreon to get access to this and all 18 bonus episodes. patreon.com/lingthusiasm 

For the full shownotes with links to everything mentioned in this episode, go to https://lingthusiasm.com/post/177070997956/lingthusiasm-episode-23-when-nothing-means

23: When nothing means something

Paper by Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R. Bowman.

Sam comes on to tell us about GLUE.  We talk about the motivation behind setting up a benchmark framework for natural language understanding, how the authors defined "NLU" and chose the tasks for this benchmark, a very nice diagnostic dataset that was constructed for GLUE, and what insight they gained from the experiments they've run so far.  We also have some musings about the utility of general-purpose sentence vectors, and about leaderboards.

https://www.semanticscholar.org/paper/GLUE%3A-A-Multi-Task-Benchmark-and-Analysis-Platform-Wang-Singh/a2054eff8b4efe0f1f53d88c08446f9492ae07c1

67 - GLUE: A Multi-Task Benchmark and Analysis Platform, with Sam Bowman

NAACL 2018 paper, by Rachel Rudinger, Aaron Steven White, and Benjamin Van Durme

Rachel comes on to the podcast, telling us about what factuality is (did an event happen?), what datasets exist for doing this task (a few; they made a new, bigger one), and how to build models to predict factuality (turns out a vanilla biLSTM does quite well).  Along the way, we have interesting discussions about how you decide what an "event" is, how you label factuality (whether something happened) on inherently uncertain text (like "I probably failed the test"), and how you might use a system that predicts factuality in some end task.

https://www.semanticscholar.org/paper/Neural-models-of-factuality-Rudinger-White/4d62a1e7819f9e3f8c837832c66659db5a6d9b37

68 - Neural models of factuality, with Rachel Rudinger

squishable, blobfish, aaarggghh, gubernatorial, apple lovers, ain’t, tronc, wug, toast, toast, toast, toast, toast.

All of these are words that someone, somewhere has asserted aren’t real words – or maybe aren’t even words at all. But we don’t point at a chair or a tree and assert that it’s not a word. Of course it’s not! That would be absurd. So why, then, do people feel called to question the wordhood of actual words?  

In this episode of the funnest* podcast about linguistics, your hosts Lauren Gawne and Gretchen McCulloch take you on a tour through what’s really going on when people say that a word isn’t a word. (*Funnest is definitely a real word, and so are all the others.)

We’re heading into our second anniversary! That’s two whole years of linguistics enthusiasm delivered right to your ears every month (twice a month for patrons). To celebrate, we want to share the show with more people! Most people find podcasts through word of mouth, and there are people out there who would be totally into a lively deep-dive into how language works, they just don’t know it exists yet. They need you to save them from their dreary, un-lingthusiastic lives! 

At our anniversary last year, we thanked over 100 people for their recs, and this year we want to thank even more! Here’s what to do: post about why you like Lingthusiasm on social media (or link to your rec elsewhere, such as a blog or podcast), make sure to tag us in your rec so we can find it, and your name will live on in perpetuity on our special second anniversary thank you post! 

This month’s bonus episode was about bringing up bilingual babies! We get enthusiastic about various ways to raise children who speak more than one language when you’re stuck in a mostly-monolingual society: the one-parent, one language method, immersion schools, and speaking different languages at home and in the public sphere. Support Lingthusiasm on Patreon to gain access to this and 19 previous bonus episodes: https://www.patreon.com/lingthusiasm

In November, we’re doing two liveshows! We’ll be in Sydney at GiantDwarf on Monday the 12th of November, and State Library of Victoria in Melbourne on Friday the 16th of November. Both events will be Auslan interpreted. For more details and how to book tickets check out our liveshow page: http://www.lingthusiasm.com/show 

We also have new merch! Alongside the Space Babies, new children’s clothing and new colours for the IPA scarves, we also have IPA ties! Check out our Merch page for more details: http://lingthusiasm.com/merch

For links to things mentioned in the episode and more details about all of the above, head to the shownotes page: https://lingthusiasm.com/post/179193327461/lingthusiasm-episode-25-every-word-is-a-real-word

25: Every word is a real word

Blog post by Alex Irpan titled "Deep Reinforcement Learning Doesn't Work Yet"
https://www.alexirpan.com/2018/02/14/rl-hard.html

In this episode, Alex Irpan talks about limitations of current deep reinforcement learning methods and why we have a long way to go before they go mainstream. We discuss sample inefficiency, instability, the difficulty to design reward functions and overfitting to the environment. Alex concludes with a list of recommendations he found useful when training models with deep reinforcement learning.

74 - Deep Reinforcement Learning Doesn't Work Yet, with Alex Irpan

In this episode, we invite Hal Daumé to continue the discussion on reinforcement learning, focusing on how it has been used in NLP. We discuss how to reduce NLP problems into the reinforcement learning framework, and circumstances where it may or may not be useful. We discuss imitation learning, roll-in and roll-out, and how to approximate an expert with a reference policy. 

DAgger: https://www.semanticscholar.org/paper/A-Reduction-of-Imitation-Learning-and-Structured-to-Ross-Gordon/17eddf33b513ae1134abadab728bdbf6abab2a05?navId=citing-papers
RESLOPE: http://legacydirs.umiacs.umd.edu/~hal/docs/daume18reslope.pdf

nlp

dam