no code implementations • 15 Mar 2024 • Tomasz Limisiewicz, Terra Blevins, Hila Gonen, Orevaoghene Ahia, Luke Zettlemoyer
A major consideration in multilingual language modeling is how to best represent languages with diverse vocabularies and scripts.
no code implementations • 16 Feb 2024 • Haoqiang Kang, Terra Blevins, Luke Zettlemoyer
While many automatic hallucination detection techniques have been proposed for English texts, their effectiveness in multilingual contexts remains unexplored.
no code implementations • 19 Jan 2024 • Terra Blevins, Tomasz Limisiewicz, Suchin Gururangan, Margaret Li, Hila Gonen, Noah A. Smith, Luke Zettlemoyer
Despite their popularity in non-English NLP, multilingual language models often underperform monolingual ones due to inter-language competition for model parameters.
1 code implementation • arXiv 2023 • Stephen Mayhew, Terra Blevins, Shuheng Liu, Marek Šuppa, Hila Gonen, Joseph Marvin Imperial, Börje F. Karlsson, Peiqin Lin, Nikola Ljubešić, LJ Miranda, Barbara Plank, Arij Riabi, Yuval Pinter
We introduce Universal NER (UNER), an open, community-driven project to develop gold-standard NER benchmarks in many languages.
Ranked #1 on Named Entity Recognition (NER) on UNER v1 (Danish)
no code implementations • 25 Oct 2023 • Weijia Shi, Anirudh Ajith, Mengzhou Xia, Yangsibo Huang, Daogao Liu, Terra Blevins, Danqi Chen, Luke Zettlemoyer
Min-K% Prob can be applied without any knowledge about the pretraining corpus or any additional training, departing from previous detection methods that require training a reference model on data that is similar to the pretraining data.
1 code implementation • 9 Sep 2023 • C. M. Downey, Terra Blevins, Nora Goldfine, Shane Steinert-Threlkeld
Pre-trained multilingual language models underpin a large portion of modern NLP tools outside of English.
no code implementations • 24 May 2023 • Akari Asai, Sneha Kudugunta, Xinyan Velocity Yu, Terra Blevins, Hila Gonen, Machel Reid, Yulia Tsvetkov, Sebastian Ruder, Hannaneh Hajishirzi
Despite remarkable advancements in few-shot generalization in natural language processing, most models are developed and evaluated primarily in English.
no code implementations • 26 Apr 2023 • Haoqiang Kang, Terra Blevins, Luke Zettlemoyer
To better understand this contrast, we present a new study investigating how well PLMs capture cross-lingual word sense with Contextual Word-Level Translation (C-WLT), an extension of word-level translation that prompts the model to translate a given word in context.
no code implementations • 8 Dec 2022 • Hila Gonen, Srini Iyer, Terra Blevins, Noah A. Smith, Luke Zettlemoyer
Language models can be prompted to perform a wide variety of zero- and few-shot learning problems.
no code implementations • 15 Nov 2022 • Terra Blevins, Hila Gonen, Luke Zettlemoyer
Although pretrained language models (PLMs) can be prompted to perform a wide range of language tasks, it remains an open question how much this ability comes from generalizable linguistic understanding versus surface-level lexical patterns.
no code implementations • 24 May 2022 • Terra Blevins, Hila Gonen, Luke Zettlemoyer
The emergent cross-lingual transfer seen in multilingual pretrained models has sparked significant interest in studying their behavior.
no code implementations • 9 May 2022 • Mandar Joshi, Terra Blevins, Mike Lewis, Daniel S. Weld, Luke Zettlemoyer
Creating labeled natural language training data is expensive and requires significant human effort.
no code implementations • 17 Apr 2022 • Terra Blevins, Luke Zettlemoyer
English pretrained language models, which make up the backbone of many modern NLP systems, require huge amounts of unlabeled training data.
no code implementations • EACL 2021 • Terra Blevins, Mandar Joshi, Luke Zettlemoyer
Current models for Word Sense Disambiguation (WSD) struggle to disambiguate rare senses, despite reaching human performance on global WSD metrics.
no code implementations • ACL 2020 • Terra Blevins, Luke Zettlemoyer
A major obstacle in Word Sense Disambiguation (WSD) is that word senses are not uniformly distributed, causing existing models to generally perform poorly on senses that are either rare or unseen during training.
Ranked #9 on Word Sense Disambiguation on Supervised:
1 code implementation • 6 May 2020 • Terra Blevins, Luke Zettlemoyer
A major obstacle in Word Sense Disambiguation (WSD) is that word senses are not uniformly distributed, causing existing models to generally perform poorly on senses that are either rare or unseen during training.
no code implementations • ACL 2019 • Terra Blevins, Luke Zettlemoyer
We incorporate morphological supervision into character language models (CLMs) via multitasking and show that this addition improves bits-per-character (BPC) performance across 24 languages, even when the morphology data and language modeling data are disjoint.
no code implementations • ACL 2018 • Terra Blevins, Omer Levy, Luke Zettlemoyer
We present a set of experiments to demonstrate that deep recurrent neural networks (RNNs) learn internal representations that capture soft hierarchical notions of syntax from highly varied supervision.
no code implementations • COLING 2016 • Terra Blevins, Robert Kwiatkowski, Jamie MacBeth, Kathleen McKeown, Desmond Patton, Owen Rambow
Violence is a serious problems for cities like Chicago and has been exacerbated by the use of social media by gang-involved youths for taunting rival gangs.