Studying word order through iterative shuffling

1 code implementation • EMNLP 2021 • Nikolay Malkin, Sameera Lanka, Pranav Goel, Nebojsa Jojic

As neural language models approach human performance on NLP benchmark tasks, their advances are widely seen as evidence of an increasingly complex understanding of syntax.

Language Modelling Sentence

GPT Perdetry Test: Generating new meanings for new words

no code implementations • NAACL 2021 • Nikolay Malkin, Sameera Lanka, Pranav Goel, Sudha Rao, Nebojsa Jojic

Human innovation in language, such as inventing new words, is a challenge for pretrained language models.

ARCHER: Aggressive Rewards to Counter bias in Hindsight Experience Replay

1 code implementation • 6 Sep 2018 • Sameera Lanka, Tianfu Wu

Experience replay is an important technique for addressing sample-inefficiency in deep reinforcement learning (RL), but faces difficulty in learning from binary and sparse rewards due to disproportionately few successful experiences in the replay buffer.

Continuous Control Reinforcement Learning (RL)