NLP/Computational Linguistics PhD @lecslab.bsky.social and @bouldernlp.bsky.social typologically robust multilingual NLP technology for language documentation https://covetedfish.github.io/https://bsky.app/profile/covetedfish.bsky.socialhttps://bsky.app/profile/covetedfish.bsky.social/post/3lofd2hm3wk2bMe and @wxie.bsky.social05 May 2025 02:28 +0000at://did:plc:f6si734pcbm5yt3y3obx4w4e/app.bsky.feed.post/3lofd2hm3wk2bhttps://bsky.app/profile/covetedfish.bsky.social/post/3locj3iniys2bme at the NAACL workshops today03 May 2025 23:38 +0000at://did:plc:f6si734pcbm5yt3y3obx4w4e/app.bsky.feed.post/3locj3iniys2bhttps://bsky.app/profile/covetedfish.bsky.social/post/3lnxh5jw5mk2rI’ll be presenting this work at #NAACL at the LM4UC workshop on Sunday. Come say hi! https://bsky.app/profile/arxiv-cs-cl.bsky.social/post/3lldp5syuvs2t [contains quote post or other embedded content]29 Apr 2025 14:04 +0000at://did:plc:f6si734pcbm5yt3y3obx4w4e/app.bsky.feed.post/3lnxh5jw5mk2rhttps://bsky.app/profile/covetedfish.bsky.social/post/3lnt2hlexjs2tShout out CU boulder for pulling up the little native plant garden outside our apartment for no reason27 Apr 2025 20:06 +0000at://did:plc:f6si734pcbm5yt3y3obx4w4e/app.bsky.feed.post/3lnt2hlexjs2thttps://bsky.app/profile/covetedfish.bsky.social/post/3lnin2b5d622eI don't want to be taken seriously. I want to be taken sillily.23 Apr 2025 16:39 +0000at://did:plc:f6si734pcbm5yt3y3obx4w4e/app.bsky.feed.post/3lnin2b5d622ehttps://bsky.app/profile/covetedfish.bsky.social/post/3lng26w5ya22oEvery time I see this crane I wonder if someone will take it as a sign to breakup with their girlfriend22 Apr 2025 15:57 +0000at://did:plc:f6si734pcbm5yt3y3obx4w4e/app.bsky.feed.post/3lng26w5ya22ohttps://bsky.app/profile/covetedfish.bsky.social/post/3lndyatbpmc27I'm looking for work on how NLP tools can be misaligned with the real and present needs of documentary linguists. Specifically, cases where the tools *seem* useful but aren't practical or miss the mark in some other way. Any ideas?21 Apr 2025 20:17 +0000at://did:plc:f6si734pcbm5yt3y3obx4w4e/app.bsky.feed.post/3lndyatbpmc27https://bsky.app/profile/covetedfish.bsky.social/post/3lmwxvy33ec26I'm giving a lecture on language model debiasing to my undergrad NLP course on Friday but I'm not super up to date on the research. Does anyone have any suggestions for papers/topics to cover?16 Apr 2025 16:06 +0000at://did:plc:f6si734pcbm5yt3y3obx4w4e/app.bsky.feed.post/3lmwxvy33ec26https://bsky.app/profile/covetedfish.bsky.social/post/3lhehvtqta22gThe AmericasNLP 2025 Shared Task on Machine Translation Metrics for Indigenous languages is live! Standard metrics like BLEU and ChrF are not ideal for evaluating Indigenous American languages. How can we do better? Due March 5th, 2025. https://turing.iimas.unam.mx/americasnlp/2025_st_3.html04 Feb 2025 16:26 +0000at://did:plc:f6si734pcbm5yt3y3obx4w4e/app.bsky.feed.post/3lhehvtqta22ghttps://bsky.app/profile/covetedfish.bsky.social/post/3lcg3qjn7x223Our paper was accepted to #COLING! If you work on low-resource MT and have ever found yourself limited to bible data, you might find this interesting. [contains quote post or other embedded content]03 Dec 2024 16:47 +0000at://did:plc:f6si734pcbm5yt3y3obx4w4e/app.bsky.feed.post/3lcg3qjn7x223https://bsky.app/profile/covetedfish.bsky.social/post/3lcddvz7wcc2rpeople will take any excuse to use the word nascent (I'm people)02 Dec 2024 14:36 +0000at://did:plc:f6si734pcbm5yt3y3obx4w4e/app.bsky.feed.post/3lcddvz7wcc2rhttps://bsky.app/profile/covetedfish.bsky.social/post/3lbpvukrkec2qI feel like reviewers often expect short papers to be long papers condensed into 4 pages. They should really be a venue to showcase focused and incremental work.24 Nov 2024 21:04 +0000at://did:plc:f6si734pcbm5yt3y3obx4w4e/app.bsky.feed.post/3lbpvukrkec2qhttps://bsky.app/profile/covetedfish.bsky.social/post/3lb43faifzs2bWhy do people still use iso 639-1 codes instead of iso 639-3? Honest question16 Nov 2024 23:49 +0000at://did:plc:f6si734pcbm5yt3y3obx4w4e/app.bsky.feed.post/3lb43faifzs2b