activity
20182023
most citedOPT-IML: Scaling Language Model Instruction Meta Learning through the Lens of Generalization

85 citations · 499 across the 23 of their papers we have counts for

collaborators
Showing 2021Show all

6 papers · 1 filter

cs.HC2021

Pretty Princess vs. Successful Leader: Gender Roles in Greeting Card Messages

Jiao Sun, Tongshuang Wu, Yue Jiang +3

People write personalized greeting cards on various occasions. While prior work has studied gender roles in greeting card messages, systematic analysis at scale and tools for raisi…

cs.CL2021★ 14 cited

Efficient Large Scale Language Modeling with Mixtures of Experts

Mikel Artetxe, Shruti Bhosale, Naman Goyal +21

Mixture of Experts layers (MoEs) enable efficient scaling of language models through conditional computation. This paper presents a detailed empirical study of how autoregressive M…

cs.CL2021★ 77 cited

Few-shot Learning with Multilingual Language Models

Xi Victoria Lin, Todor Mihaylov, Mikel Artetxe +18

Large-scale generative language models such as GPT-3 are competitive few-shot learners. While these models are known to be able to jointly represent many different languages, their…

cs.CL2021★ 1 cited

Learning to Synthesize Data for Semantic Parsing

Bailin Wang, Wenpeng Yin, Xi Victoria Lin +1

Synthesizing data for semantic parsing has gained increasing attention recently. However, most methods require handcrafted (high-precision) rules in their generative process, hinde…

cs.CL2021★ 4 cited

FeTaQA: Free-form Table Question Answering

Linyong Nan, Chiachun Hsieh, Ziming Mao +14

Existing table question answering datasets contain abundant factual questions that primarily evaluate the query and schema comprehension capability of a system, but they fail to in…

cs.CL2021★ 1 cited

NeurIPS 2020 NLC2CMD Competition: Translating Natural Language to Bash Commands

Mayank Agarwal, Tathagata Chakraborti, Quchen Fu +6

The NLC2CMD Competition hosted at NeurIPS 2020 aimed to bring the power of natural language processing to the command line. Participants were tasked with building models that can t…