MRQA Workshop

Missed the MRQA workshop at #emnlp2021? Recordings of invited talks and panels (multilingual QA and interpretable QA) are now available on our website! Link: #program" target="_blank" rel="nofollow noopener">mrqa.github.io/#program

Join us on Zoom for the interpretability panel in 25 minutes! With Hanna Hajishirzi, Dieuwke Hupkes, Marco Tulio Ribeiro, Michael Collins, and Dan Roth.

@HannaHajishirzi talking now about "Knowledge-Rich and Robust Neural Text Comprehension and Reasoning." How do we build robust models for textual comprehension and reasoning, and how should we systematically evaluate them?

Speaking now: @marcotcr talks about "Explanations and counterfactuals." Great perspective through the lens of counterfactuals - which counterfc are used to create explanation, how these counterfc are summarized, and what counterfc preds the explanation allows the user to make.

Starting up again: join for @JonathanBerant's talk on "Is my QA model reasoning? Meaning representations and multi-task training for understanding QA models".

Also honorable mention to Kell et. al. on "What Would it Take to get Biomedical QA Systems into Practice?" and to Fajcik et. al. on "Rethinking the Objectives of Extractive Question Answering"

Best paper talks happening now! Congrats to the best paper authors, @maxime_de_bruyn et. al., on "MFAQ: a Multilingual FAQ Dataset" (mrqa.github.io/assets/papers/…)

Happening now: multilingual QA panel with Reut Tsarfaty, Yiming Cui, Eunsol Choi, Luke Zettlemoyer, Jon Clark, and Jordan Boyd-Graber!

Catch @KCrosner's talk on Chinese Machine Reading Comprehension and Beyond! Covers 3 main topics in dealing with non-English MRC scenarios, including new models, benchmarks and paradigms.

Talking now: @JonClarkSeattle on "Question Answering for All." How can we make QA more user-centric? This perspective influences what research questions we pursue, what datasets we built, and ultimately how useful systems built with our methodologies will be to real people.

Talking now: @rtsarfaty on Comprehensive and Inclusive Text Understanding. SOTA models beat "human" benchmarks. Does their performance on current QA tasks indeed resemble human-like understanding? And, are these reports attainable in languages that are different from English?

If you are attending MRQA 2021, ask us questions in our slido: sli.do/mrqa2021

After some delays due to onsite logistics, we are finally underway! Join us. Schedule at mrqa.github.io (expect some deviation due to the late start).

For the full schedule, and our accepted papers, check out mrqa.github.io We're looking forward to seeing you virtually, and in person.

Alongside our speakers, we'll also welcome @boydgraber and @LukeZettlemoyer for a Multilingual QA panel, and @_dieuwke_ @DanRothNLP and Michael Collins for panel on Interpretability

MRQA 2021 is *tomorrow*! Join us Weds 9am AST, Workshop W12 #EMNLP2021 This year there's a special focus on Multilingual and interpretable QA, with talks from @rtsarfaty @JonClarkSeattle @KCrosner @JonathanBerant @marcotcr @HannaHajishirzi, 2 panels, best paper talks, & posters!

Congrats to all authors on acceptance to #EMNLP2021! If you have accepted papers in Machine Reading / Question Answering, consider submitting to the non-archival track of #MRQA workshop. Simply submit it through google form: tinyurl.com/mrqa-nonarc Deadline: September 3

‼️ MRQA (at #emnlp2021) deadline extended to **Thursday, August 12** ‼️ (September 3 w/ ARR reviews) More info: mrqa.github.io/cfp We welcome submissions in interpretability track, multilinguality track & regular research track. Please consider submitting your work!

Our Call for Papers is out: mrqa.github.io/cfp We seek submissions in interpretability track, multilinguality track & regular research track. Please consider submitting your work! Submission deadline: **August 5** (August 27 if you have reviews from @ReviewAcl)

cc'ing our speakers: @HannaHajishirzi @JonathanBerant Marco Tulio Ribeiro @JonClarkSeattle @rtsarfaty @KCrosner + organizers @adamjfisch @AlonTalmor @danqi_chen @eunsolc @seo_minjoon @PSH_Lewis @robinomial @sewon__min

Please vote for #MRQA workshop if you are interested in cutting-edge research in machine reading and QA. In particular, this year we focus on two special themes: multilinguality & interpretability, and feature a great line-up of speakers. More info at mrqa.github.io