Zeyu Liu


2023

pdf bib
Learning to translate by learning to communicate
C.m. Downey | Xuhui Zhou | Zeyu Liu | Shane Steinert-Threlkeld
Proceedings of the 3rd Workshop on Multi-lingual Representation Learning (MRL)

pdf bib
Towards A Unified View of Sparse Feed-Forward Network in Pretraining Large Language Model
Zeyu Liu | Tim Dettmers | Xi Lin | Veselin Stoyanov | Xian Li
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Large and sparse feed-forward layers (S-FFN) such as Mixture-of-Experts (MoE) have proven effective in scaling up Transformers model size for pretraining large language models. By only activating part of the FFN parameters conditioning on input, S-FFN improves generalization performance while keeping training and inference costs (in FLOPs) fixed. In this work, we analyzed two major design choices of S-FFN: the memory block (a.k.a. expert) size and the memory block selection method under a general conceptual framework of sparse neural memory. Using this unified framework, we compare several S-FFN architectures for language modeling and provide insights into their relative efficacy and efficiency. We found a simpler selection method — Avg-K that selects blocks through their mean aggregated hidden states, achieving lower perplexity in language model pretraining compared to existing MoE architectures including Switch Transformer (Fedus et al., 2021) and HashLayer (Roller et al., 2021).

2021

pdf bib
Probing Across Time: What Does RoBERTa Know and When?
Zeyu Liu | Yizhong Wang | Jungo Kasai | Hannaneh Hajishirzi | Noah A. Smith
Findings of the Association for Computational Linguistics: EMNLP 2021

Models of language trained on very large corpora have been demonstrated useful for natural language processing. As fixed artifacts, they have become the object of intense study, with many researchers “probing” the extent to which they acquire and readily demonstrate linguistic abstractions, factual and commonsense knowledge, and reasoning abilities. Recent work applied several probes to intermediate training stages to observe the developmental process of a large-scale model (Chiang et al., 2020). Following this effort, we systematically answer a question: for various types of knowledge a language model learns, when during (pre)training are they acquired? Using RoBERTa as a case study, we find: linguistic knowledge is acquired fast, stably, and robustly across domains. Facts and commonsense are slower and more domain-sensitive. Reasoning abilities are, in general, not stably acquired. As new datasets, pretraining protocols, and probes emerge, we believe that probing-across-time analyses can help researchers understand the complex, intermingled learning that these models undergo and guide us toward more efficient approaches that accomplish necessary learning faster.

2020

pdf bib
Linguistically-Informed Transformations (LIT): A Method for Automatically Generating Contrast Sets
Chuanrong Li | Lin Shengshuo | Zeyu Liu | Xinyi Wu | Xuhui Zhou | Shane Steinert-Threlkeld
Proceedings of the Third BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP

Although large-scale pretrained language models, such as BERT and RoBERTa, have achieved superhuman performance on in-distribution test sets, their performance suffers on out-of-distribution test sets (e.g., on contrast sets). Building contrast sets often requires human-expert annotation, which is expensive and hard to create on a large scale. In this work, we propose a Linguistically-Informed Transformation (LIT) method to automatically generate contrast sets, which enables practitioners to explore linguistic phenomena of interests as well as compose different phenomena. Experimenting with our method on SNLI and MNLI shows that current pretrained language models, although being claimed to contain sufficient linguistic knowledge, struggle on our automatically generated contrast sets. Furthermore, we improve models’ performance on the contrast sets by applying LIT to augment the training data, without affecting performance on the original data.