Bill Byrne

speech and language processing researcher, also machine learning, professor, emigrant, bicyclist

[Bill Byrne @unattributed]

@mmbronstein @desirivanova @PetarV_93 @chaitjo @fhuszar @inxoy_ @bose_joey @pl219_Cambridge I've given lectures and practical exercises on transformers as part of the Cambridge MLMI MPhil since at least 2021. The module focused on machine translation, dialogue, and other NLP.

[Bill Byrne @unattributed]

@ianwu97 https://t.co/RpnBWMeMOF

[Bill Byrne @unattributed]

@ianwu97 Nice to see this approach applied to tasks other than NMT. https://t.co/mwOQonVFb6

[Bill Byrne @unattributed]

https://t.co/Kyk284RYl9

[Bill Byrne @unattributed]

Time to dust off all the old Boltzmann Machine papers...

[Bill Byrne @unattributed]

@kchonyc ok, that's funny .

[Bill Byrne @unattributed]

@natolambert Very nice work. Following your notes in the discussion, it'll be really interesting to see if the `reference free` reward for DPO also works. Having the reward depend on the regularisation mechanism used in training doesn't seem quite right.

[SIGdial @sigdial]

@JChiyahGarcia @ale_suglia @arash_eshghi @hfhastie And well done @alexcoca23, Bo-Hsiang Tseng, Jinghong Chen, Weizhe Lin, Weixuan Zhang, Tisha Anders, Bill Byrne for winning best long paper!!

(Let me know if we have failed to find your handle and you want to be tagged)

[GITT @GITT2024]

When you register for @EAMT_2023 , don't forget to sign up for our workshop (it's free!) so you can hear our 2nd 🔑🎵 Danielle Saunders talk about the challenges and needs in #Gender #inclusive #MachineTranslation, such as applying methods at scale (data size & language variety)

[Svitlana Vakulenko 🇺🇦 @svakulenk0]

Check out our survey on dense retrieval & QA for low-resource scenarios that was accepted at #EACL2023
@GianniBarlacchi @marcodeltredici @unattributed

@AmazonScience #AmazonScience

https://t.co/MhKvXXmK49

[Bill Byrne @unattributed]

@bnjmn_marie although there may have been earlier internal work at IBM. But here's a cite for MBR system combination https://t.co/pYmh1IyWJs

[Bill Byrne @unattributed]

@bnjmn_marie Nice writeup! Its great to see early work by Vaibhava Goel cited, but that 2000 paper was about A* search over lattices. Andreas Stolcke and colleagues had a'97 paper (MBR over n-best lists), which we cite, and which is probably the earliest citation in ASR...

[Bill Byrne @unattributed]

@zngu i see - thanks!

[Bill Byrne @unattributed]

@zngu Agree entirely about UK visa process. Do you have details on the Huawei scheme? How does it avoid the 'working away' problem?

[Bill Byrne @unattributed]

@margs_li Looking forward to reading. For some prior work on Bayesian domain weighting in NMT, check out https://t.co/gCnfADKaGg

[Svitlana Vakulenko 🇺🇦 @svakulenk0]

Interested in doing a 4-6 month research internship on topics relevant to #convsearch or QA? Our team at Amazon Alexa AI is looking for interns at Barcelona & Berlin locations! Reach out directly and apply via https://t.co/VX11Hbu3sU @chengweiwei @GianniBarlacchi @marcodeltredici

[Bill Byrne @unattributed]

Adapting machine translation models to new genres https://t.co/0VsLgqwn3X

[Giving Voice to Digital Democracies @voice_digital]

Tomorrow we will be hosting our free event on "Understanding and Automating #Counterspeech". We are very excited to discuss this important topic with experts on philosophy of language, law, computer science, media & political communication, counter terrorism and online activism.

[Bill Byrne @unattributed]

@random_walker and another paper on coaxing map to avoid bias - https://t.co/AVLLJFnSym

[Bill Byrne @unattributed]

@random_walker Here's a nice recent paper on avoiding map to avoid bias - https://t.co/Q1yaUbvd7H