Parameter-efficient tuning (PET) methods can effectively drive extremely large pre-trained language models (PLMs) by training only minimal parameters. Different PET methods utilize different manually designed tunable modules. In small PLMs, there are usually noticeable performance differences among PET methods. Nevertheless, as the model scale increases, the performance differences become marginal. Hence, we hypothesize that model scaling mitigates the impact of design differences on PET methods. To investigate this hypothesis, we introduce a more flexible PET method called Arbitrary PET (APET) method. The APET method is compatible with a tunable module, which consists of any number of parameters distributed in arbitrary positions. Then, we utilize it and conduct experiments on 11 NLP tasks across 3 representative PLMs. Our investigations reveal that model scaling (1) mitigates the effects of the positions of tunable parameters on performance, and (2) enables tuning methods to achieve performance comparable to full-parameter fine-tuning by optimizing fewer tunable parameters. Intriguingly, we also observe that tuning methods optimize the similar number of tunable parameters to exceed random guess performance on different tasks. We collectively discuss this phenomenon and the two aforementioned findings from an optimization perspective to understand the underlying mechanisms. These conclusions enhance our understanding of the impact of model scaling on PET and assist in designing more effective and efficient PET methods for PLMs of different scales. The source code can be obtained from this GitHub repository: https://github.com/yushengsu-thu/PET_Scaling.

In-context learning is a new learning paradigm where a language model conditions on a few input-output pairs (demonstrations) and a test input, and directly outputs the prediction. It has been shown sensitive to the provided demonstrations and thus promotes the research of demonstration retrieval: given a test input, relevant examples are retrieved from the training set to serve as informative demonstrations for in-context learning. While previous works train task-specific retrievers for several tasks separately, these methods are hard to transfer and scale on various tasks, and separately trained retrievers will cause a lot of parameter storage and deployment cost. In this paper, we propose Unified Demonstration Retriever (UDR), a single model to retrieve demonstrations for a wide range of tasks. To train UDR, we cast various tasks’ training signals into a unified list-wise ranking formulation by language model’s feedback. Then we propose a multi-task list-wise ranking training framework with an iterative mining strategy to find high-quality candidates, which can help UDR fully incorporate various tasks’ signals. Experiments on 30+ tasks across 13 task families and multiple data domains show that UDR significantly outperforms baselines. Further analyses show the effectiveness of each proposed component and UDR’s strong ability in various scenarios including different LMs (1.3B 175B), unseen datasets, varying demonstration quantities, etc. We will release the code and model checkpoint after review.

Early exiting can reduce the average latency of pre-trained language models (PLMs) via its adaptive inference mechanism and work with other inference speed-up methods like model pruning, thus drawing much attention from the industry. In this work, we propose a novel framework, BADGE, which consists of two off-the-shelf methods for improving PLMs’ early exiting. We first address the issues of training a multi-exit PLM, the backbone model for early exiting. We propose the novel architecture of block-wise bypasses, which can alleviate the conflicts in jointly training multiple intermediate classifiers and thus improve the overall performances of multi-exit PLM while introducing negligible additional flops to the model. Second, we propose a novel divergence-based early exiting (DGE) mechanism, which obtains early exiting signals by comparing the predicted distributions of two adjacent layers’ exits. Extensive experiments on three proprietary datasets and three GLUE benchmark tasks demonstrate that our method can obtain a better speedup-performance trade-off than the existing baseline methods.\footnote{Code will be made publicly available to the research community upon acceptance.}

Large scale pre-training models have been widely used in named entity recognition (NER) tasks. However, model ensemble through parameter averaging or voting can not give full play to the differentiation advantages of different models, especially in the open domain. This paper describes our NER system in the SemEval 2022 task11: MultiCoNER. We proposed an effective system to adaptively ensemble pre-trained language models by a Transformer layer. By assigning different weights to each model for different inputs, we adopted the Transformer layer to integrate the advantages of diverse models effectively. Experimental results show that our method achieves superior performances in Farsi and Dutch.

Artificial Intelligence (AI), along with the recent progress in biomedical language understanding, is gradually offering great promise for medical practice. With the development of biomedical language understanding benchmarks, AI applications are widely used in the medical field. However, most benchmarks are limited to English, which makes it challenging to replicate many of the successes in English for other languages. To facilitate research in this direction, we collect real-world biomedical data and present the first Chinese Biomedical Language Understanding Evaluation (CBLUE) benchmark: a collection of natural language understanding tasks including named entity recognition, information extraction, clinical diagnosis normalization, single-sentence/sentence-pair classification, and an associated online platform for model evaluation, comparison, and analysis. To establish evaluation on these tasks, we report empirical results with the current 11 pre-trained Chinese models, and experimental results show that state-of-the-art neural models perform by far worse than the human ceiling.

Early exiting allows instances to exit at different layers according to the estimation of difficulty. Previous works usually adopt heuristic metrics such as the entropy of internal outputs to measure instance difficulty, which suffers from generalization and threshold-tuning. In contrast, learning to exit, or learning to predict instance difficulty is a more appealing way. Though some effort has been devoted to employing such “learn-to-exit” modules, it is still unknown whether and how well the instance difficulty can be learned. As a response, we first conduct experiments on the learnability of instance difficulty, which demonstrates that modern neural models perform poorly on predicting instance difficulty. Based on this observation, we propose a simple-yet-effective Hash-based Early Exiting approach HashEE) that replaces the learn-to-exit modules with hash functions to assign each token to a fixed exiting layer. Different from previous methods, HashEE requires no internal classifiers nor extra parameters, and therefore is more efficient. HashEE can be used in various tasks (including language understanding and generation) and model architectures such as seq2seq models. Experimental results on classification, regression, and generation tasks demonstrate that HashEE can achieve higher performance with fewer FLOPs and inference time compared with previous state-of-the-art early exiting methods.

In developing an online question-answering system for the medical domains, natural language inference (NLI) models play a central role in question matching and intention detection. However, which models are best for our datasets? Manually selecting or tuning a model is time-consuming. Thus we experiment with automatically optimizing the model architectures on the task at hand via neural architecture search (NAS). First, we formulate a novel architecture search space based on the previous NAS literature, supporting cross-sentence attention (cross-attn) modeling. Second, we propose to modify the ENAS method to accelerate and stabilize the search results. We conduct extensive experiments on our two medical NLI tasks. Results show that our system can easily outperform the classical baseline models. We compare different NAS methods and demonstrate our approach provides the best results.

In this article, we describe our systems for the MEDIQA 2021 Shared Tasks. First, we will describe our method for the second task, Multi-Answer Summarization (MAS). For extractive summarization, two series of methods are applied. The first one follows (CITATION). First a RoBERTa model is first applied to give a local ranking of the candidate sentences. Then a Markov Chain model is applied to evaluate the sentences globally. The second method applies cross-sentence contextualization to improve the local ranking and discard the global ranking step. Our methods achieve the 1st Place in the MAS task. For the question summarization (QS) and radiology report summarization (RRS) tasks, we explore how end-to-end pre-trained seq2seq model perform. A series of tricks for improving the fine-tuning performances are validated.

In this work, we propose a novel framework, Gradient Aligned Mutual Learning BERT (GAML-BERT), for improving the early exiting of BERT. GAML-BERT’s contributions are two-fold. We conduct a set of pilot experiments, which shows that mutual knowledge distillation between a shallow exit and a deep exit leads to better performances for both. From this observation, we use mutual learning to improve BERT’s early exiting performances, that is, we ask each exit of a multi-exit BERT to distill knowledge from each other. Second, we propose GA, a novel training method that aligns the gradients from knowledge distillation to cross-entropy losses. Extensive experiments are conducted on the GLUE benchmark, which shows that our GAML-BERT can significantly outperform the state-of-the-art (SOTA) BERT early exiting methods.

In this paper, we integrate span-related information into pre-trained encoder for entity relation extraction task. Instead of using general-purpose sentence encoder (e.g., existing universal pre-trained models), we introduce a span encoder and a span pair encoder to the pre-training network, which makes it easier to import intra-span and inter-span information into the pre-trained model. To learn the encoders, we devise three customized pre-training objectives from different perspectives, which target on tokens, spans, and span pairs. In particular, a span encoder is trained to recover a random shuffling of tokens in a span, and a span pair encoder is trained to predict positive pairs that are from the same sentences and negative pairs that are from different sentences using contrastive loss. Experimental results show that the proposed pre-training method outperforms distantly supervised pre-training, and achieves promising performance on two entity relation extraction benchmark datasets (ACE05, SciERC).

This paper describes the models designated for the MEDIQA 2019 shared tasks by the team PANLP. We take advantages of the recent advances in pre-trained bidirectional transformer language models such as BERT (Devlin et al., 2018) and MT-DNN (Liu et al., 2019b). We find that pre-trained language models can significantly outperform traditional deep learning models. Transfer learning from the NLI task to the RQE task is also experimented, which proves to be useful in improving the results of fine-tuning MT-DNN large. A knowledge distillation process is implemented, to distill the knowledge contained in a set of models and transfer it into an single model, whose performance turns out to be comparable with that obtained by the ensemble of that set of models. Finally, for test submissions, model ensemble and a re-ranking process are implemented to boost the performances. Our models participated in all three tasks and ranked the 1st place for the RQE task, and the 2nd place for the NLI task, and also the 2nd place for the QA task.

To solve the shared tasks of COIN: COmmonsense INference in Natural Language Processing) Workshop in , we need explore the impact of knowledge representation in modeling commonsense knowledge to boost performance of machine reading comprehension beyond simple text matching. There are two approaches to represent knowledge in the low-dimensional space. The first is to leverage large-scale unsupervised text corpus to train fixed or contextual language representations. The second approach is to explicitly express knowledge into a knowledge graph (KG), and then fit a model to represent the facts in the KG. We have experimented both (a) improving the fine-tuning of pre-trained language models on a task with a small dataset size, by leveraging datasets of similar tasks; and (b) incorporating the distributional representations of a KG onto the representations of pre-trained language models, via simply concatenation or multi-head attention. We find out that: (a) for task 1, first fine-tuning on larger datasets like RACE (Lai et al., 2017) and SWAG (Zellersetal.,2018), and then fine-tuning on the target task improve the performance significantly; (b) for task 2, we find out the incorporating a KG of commonsense knowledge, WordNet (Miller, 1995) into the Bert model (Devlin et al., 2018) is helpful, however, it will hurts the performace of XLNET (Yangetal.,2019), a more powerful pre-trained model. Our approaches achieve the state-of-the-art results on both shared task’s official test data, outperforming all the other submissions.