Common Sense or World Knowledge? Investigating Adapter-Based Knowledge Injection into Pretrained Transformers
Data and Web Science Group, University of Mannheim（曼海姆大学数据与网络科学组）；Wluper；Ubiquitous Knowledge Processing (UKP) Lab, TU Darmstadt（达姆施塔特工业大学普适知识处理（UKP）实验室）
Anne Lauscher, Olga Majewska, Leonardo F. R. Ribeiro, Iryna Gurevych, Nikolai Rozanov, Goran Glavaš
Following the major success of neural language models (LMs) such as BERT or GPT-2 on a variety of language understanding tasks, recent work focused on injecting (structured) knowledge from external resources into these models. While on the one hand, joint pretraining (i.e., training from scratch, adding objectives based on external knowledge to the primary LM objective) may be prohibitively computationally expensive, post-hoc fine-tuning on external knowledge, on the other hand, may lead to the catastrophic forgetting of distributional knowledge. In this work, we investigate models for complementing the distributional knowledge of BERT with conceptual knowledge from ConceptNet and its corresponding Open Mind Common Sense (OMCS) corpus, respectively, using adapter training. While overall results on the GLUE benchmark paint an inconclusive picture, a deeper analysis reveals that our adapter-based models substantially outperform BERT (up to 15-20 performance points) on inference tasks that require the type of conceptual knowledge explicitly present in ConceptNet and OMCS. All code and experiments are open sourced under: https://github.com/wluper/retrograph .
MerA: Merging Pretrained Adapters For Few-Shot Learning
University of Maryland, College Park（马里兰大学帕克分校）；The University of Sydney（悉尼大学）；University of Chinese Academy of Sciences（中国科学院大学）；JD Explore Academy（京东探索研究院）
Beijing Institute for General Artificial Intelligence（北京通用人工智能研究院）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
Transfer learning with large pretrained transformer-based language models like BERT has become a dominating approach for most NLP tasks. Simply fine-tuning those large language models on downstream tasks or combining it with task-specific pretraining is often not robust. In particular, the performance considerably varies as the random seed changes or the number of pretraining and/or fine-tuning iterations varies, and the fine-tuned model is vulnerable to adversarial attack. We propose a simple yet effective adapter-based approach to mitigate these issues. Specifically, we insert small bottlene…
Center for Information and Language Processing, LMU Munich（慕尼黑大学信息与语言处理中心）；Munich Center for Machine Learning（慕尼黑机器学习中心）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
Pretrained language models (PLMs) are trained on massive corpora, but often need to specialize to specific domains. A parameter-efficient adaptation method suggests training an adapter for each domain on the task of language modeling. This leads to good in-domain scores but can be impractical for domain- or resource-restricted settings. A solution is to use a related-domain adapter for the novel domain at test time. In this paper, we introduce AdapterSoup, an approach that performs weight-space averaging of adapters trained on different domains. Our approach is embarrassingly parallel: first, …
National University of Singapore（新加坡国立大学）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；Nanyang Technological University（南洋理工大学）；Singapore University of Technology and Design（新加坡科技设计大学）
Adapter-based tuning has recently arisen as an alternative to fine-tuning. It works by adding light-weight adapter modules to a pretrained language model (PrLM) and only updating the parameters of adapter modules when learning on a downstream task. As such, it adds only a few trainable parameters per new task, allowing a high degree of parameter sharing. Prior studies have shown that adapter-based tuning often achieves comparable results to fine-tuning. However, existing work only focuses on the parameter-efficient aspect of adapter-based tuning while lacking further investigation on its effec…
Westlake University（西湖大学）；Technical University of Darmstadt（达姆施塔特工业大学）
Pretrained language models (PLM) have recently advanced graph-to-text generation, where the input graph is linearized into a sequence and fed into the PLM to obtain its representation. However, efficiently encoding the graph structure in PLMs is challenging because such models were pretrained on natural language, and modeling structured data may lead to catastrophic forgetting of distributional knowledge. In this paper, we propose StructAdapt, an adapter method to encode graph structure into PLMs. Contrary to prior work, StructAdapt effectively models interactions among the nodes based on the …
University of Cambridge（剑桥大学）；University of Mannheim（曼海姆大学）
Adapter modules, additional trainable parameters that enable efficient fine-tuning of pretrained transformers, have recently been used for language specialization of multilingual transformers, improving downstream zero-shot cross-lingual transfer. In this work, we propose orthogonal language and task adapters (dubbed orthoadapters) for cross-lingual transfer. They are trained to encode language- and task-specific information that is complementary (i.e., orthogonal) to the knowledge already stored in the pretrained transformer's parameters. Our zero-shot cross-lingual transfer experiments, invo…
Orange Innovation（Orange创新研究院）；Aix-Marseille Univ.（艾克斯-马赛大学）；CNRS（法国国家科学研究中心）；LIS（计算机与系统实验室）；AMU（艾克斯-马赛大学）；Huawei Edinburgh Research Centre（华为爱丁堡研究中心）
Text generation from Abstract Meaning Representation (AMR) has substantially benefited from the popularized Pretrained Language Models (PLMs). Myriad approaches have linearized the input graph as a sequence of tokens to fit the PLM tokenization requirements. Nevertheless, this transformation jeopardizes the structural integrity of the graph and is therefore detrimental to its resulting representation. To overcome this issue, Ribeiro et al. have recently proposed StructAdapt, a structure-aware adapter which injects the input graph connectivity within PLMs using Graph Neural Networks (GNNs). In …
Technical University of Darmstadt（达姆施塔特工业大学）；Johannes Gutenberg-University Mainz（美因茨约翰内斯·古腾堡大学）
The open-access dissemination of pretrained language models through online repositories has led to a democratization of state-of-the-art natural language processing (NLP) research. This also allows people outside of NLP to use such models and adapt them to specific use-cases. However, a certain amount of technical proficiency is still required which is an entry barrier for users who want to apply these models to a certain task but lack the necessary knowledge or resources. In this work, we aim to overcome this gap by providing a tool which allows researchers to leverage pretrained models witho…
The University of Sheffield（谢菲尔德大学）；Hessian Center for AI (hessian.AI)（黑森人工智能中心）；Technical University of Darmstadt（达姆施塔特工业大学）
State-of-the-art pretrained NLP models contain a hundred million to trillion parameters. Adapters provide a parameter-efficient alternative for the full finetuning in which we can only finetune lightweight neural network layers on top of pretrained weights. Adapter layers are initialized randomly. However, existing work uses the same adapter architecture -- i.e., the same adapter layer on top of each layer of the pretrained model -- for every dataset, regardless of the properties of the dataset or the amount of available training data. In this work, we introduce adaptable adapters that contain…
Carnegie Mellon University（卡内基梅隆大学）；University of Washington（华盛顿大学）；DeepMind
Adapters are light-weight modules that allow parameter-efficient fine-tuning of pretrained models. Specialized language and task adapters have recently been proposed to facilitate cross-lingual transfer of multilingual pretrained models (Pfeiffer et al., 2020b). However, this approach requires training a separate language adapter for every language one wishes to support, which can be impractical for languages with limited data. An intuitive solution is to use a related language adapter for the new language variety, but we observe that this solution can lead to sub-optimal performance. In this …
Center for Information and Language Processing, LMU Munich（慕尼黑大学信息与语言处理中心）；Munich Center for Machine Learning（慕尼黑机器学习中心）；Microsoft（微软）
Large multilingual models trained with self-supervision achieve state-of-the-art results in a wide range of natural language processing tasks. Self-supervised pretrained models are often fine-tuned on parallel data from one or multiple language pairs for machine translation. Multilingual fine-tuning improves performance on low-resource languages but requires modifying the entire model and can be prohibitively expensive. Training a new adapter on each language pair or training a single adapter on all language pairs without updating the pretrained model has been proposed as a parameter-efficient…
EPFL University（洛桑联邦理工学院）；Idiap Research Institute（IDIAP研究所）；DeepMind
Adapting large-scale pretrained language models to downstream tasks via fine-tuning is the standard method for achieving state-of-the-art performance on NLP benchmarks. However, fine-tuning all weights of models with millions or billions of parameters is sample-inefficient, unstable in low-resource settings, and wasteful as it requires storing a separate copy of the model for each task. Recent work has developed parameter-efficient fine-tuning methods, but these approaches either still require a relatively large number of parameters or underperform standard fine-tuning. In this work, we propos…
Personal rare word recognition in end-to-end Automatic Speech Recognition (E2E ASR) models is a challenge due to the lack of training data. A standard way to address this issue is with shallow fusion methods at inference time. However, due to their dependence on external language models and the deterministic approach to weight boosting, their performance is limited. In this paper, we propose training neural contextual adapters for personalization in neural transducer based ASR models. Our approach can not only bias towards user-defined words, but also has the flexibility to work with pretraine…
Johns Hopkins University（约翰斯·霍普金斯大学）；University of Maryland（马里兰大学）
A popular approach to creating a zero-shot cross-language retrieval model is to substitute a monolingual pretrained language model in the retrieval model with a multilingual pretrained language model such as Multilingual BERT. This multilingual model is fined-tuned to the retrieval task with monolingual data such as English MS MARCO using the same training recipe as the monolingual retrieval model used. However, such transferred models suffer from mismatches in the languages of the input text during training and inference. In this work, we propose transferring monolingual retrieval models usin…
Center for Information and Language Processing (CIS), LMU Munich（慕尼黑大学信息与语言处理中心（CIS））；Research Training Group AIPHES（AIPHES研究培训小组）
Graph-to-text generation aims to generate fluent texts from graph-based data. In this paper, we investigate two recently proposed pretrained language models (PLMs) and analyze the impact of different task-adaptive pretraining strategies for PLMs in graph-to-text generation. We present a study across three graph domains: meaning representations, Wikipedia knowledge graphs (KGs) and scientific KGs. We show that the PLMs BART and T5 achieve new state-of-the-art results and that task-adaptive pretraining strategies improve their performance even further. In particular, we report new state-of-the-a…
Center for Information and Language Processing, LMU Munich（慕尼黑大学信息与语言处理中心）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）
The remarkable success of large language models has been driven by dense models trained on massive unlabeled, unstructured corpora. These corpora typically contain text from diverse, heterogeneous sources, but information about the source of the text is rarely used during training. Transferring their knowledge to a target domain is typically done by continuing training in-domain. In this paper, we introduce a method to permit domain adaptation to many diverse domains using a computationally efficient adapter approach. Our method is based on the observation that textual domains are partially ov…
Center for Information and Language Processing (CIS), LMU Munich（慕尼黑大学信息与语言处理中心（CIS））
Recently, it has been found that monolingual English language models can be used as knowledge bases. Instead of structural knowledge base queries, masked sentences such as "Paris is the capital of [MASK]" are used as probes. We translate the established benchmarks TREx and GoogleRE into 53 languages. Working with mBERT, we investigate three questions. (i) Can mBERT be used as a multilingual knowledge base? Most prior work only considers English. Extending research to multiple languages is important for diversity and accessibility. (ii) Is mBERT's performance as knowledge base language-independ…
University of Cambridge（剑桥大学）；Mila - Quebec AI Institute（米拉-魁北克人工智能研究所）；McGill University（麦吉尔大学）
Fine-tuning the entire set of parameters of a large pretrained model has become the mainstream approach for transfer learning. To increase its efficiency and prevent catastrophic forgetting and interference, techniques like adapters and sparse fine-tuning have been developed. Adapters are modular, as they can be combined to adapt a model towards different facets of knowledge (e.g., dedicated language and/or task adapters). Sparse fine-tuning is expressive, as it controls the behavior of all model components. In this work, we introduce a new fine-tuning method with both these desirable properti…
While large pretrained Transformer models have proven highly capable at tackling natural language tasks, handling long sequence inputs continues to be a significant challenge. One such task is long input summarization, where inputs are longer than the maximum input context of most pretrained models. Through an extensive set of experiments, we investigate what model architectural changes and pretraining paradigms can most efficiently adapt a pretrained Transformer for long input summarization. We find that a staggered, block-local Transformer with global encoder tokens strikes a good balance of…
Pluggable Neural Machine Translation Models via Memory-augmented Adapters
Tsinghua University（清华大学）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学智能产业研究院（AIR））；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Zhongguancun Laboratory（中关村实验室）
University of Cambridge（剑桥大学）；University of Mannheim（曼海姆大学）；Mila – Quebec AI Institute（米拉-魁北克人工智能研究所）
In parallel to their overwhelming success across NLP tasks, language ability of deep Transformer networks, pretrained via language modeling (LM) objectives has undergone extensive scrutiny. While probing revealed that these models encode a range of syntactic and semantic properties of a language, they are still prone to fall back on superficial cues and simple heuristics to solve downstream tasks, rather than leverage deeper linguistic knowledge. In this paper, we target one such area of their deficiency, verbal reasoning. We investigate whether injecting explicit information on verbs' semanti…
Lelapa AI（莱拉帕人工智能公司）；Luleå University of Technology（吕勒奥理工大学）；Lanfrica（兰弗里卡）；Instituto Politécnico Nacional（墨西哥国立理工学院）；USC Information Sciences Institute（南加州大学信息科学研究所）；University of California, Davis（加州大学戴维斯分校）；New Mexico State University（新墨西哥州立大学）；Technical University of Munich（慕尼黑工业大学）；University of Porto（波尔图大学）；ML Collective（机器学习集体）；University of Toronto（多伦多大学）；University of Dayton（代顿大学）；McGill University（麦吉尔大学）；Mila Quebec AI Institute（米拉魁北克人工智能研究所）
Many natural language processing (NLP) tasks make use of massively pre-trained language models, which are computationally expensive. However, access to high computational resources added to the issue of data scarcity of African languages constitutes a real barrier to research experiments on these languages. In this work, we explore the applicability of low-compute approaches such as language adapters in the context of this low-resource double-bind. We intend to answer the following question: do language adapters allow those who are doubly bound by data and compute to practically build useful m…
How does language model pretraining help transfer learning? We consider a simple ablation technique for determining the impact of each pretrained layer on transfer task performance. This method, partial reinitialization, involves replacing different layers of a pretrained model with random weights, then finetuning the entire model on the transfer task and observing the change in performance. This technique reveals that in BERT, layers with high probing performance on downstream GLUE tasks are neither necessary nor sufficient for high accuracy on those tasks. Furthermore, the benefit of using p…
School of Computing and Information Systems（计算与信息系统学院）；Singapore Management University（新加坡管理大学）
In this paper, we revisit math word problems~(MWPs) from the cross-lingual and multilingual perspective. We construct our MWP solvers over pretrained multilingual language models using sequence-to-sequence model with copy mechanism. We compare how the MWP solvers perform in cross-lingual and multilingual scenarios. To facilitate the comparison of cross-lingual performance, we first adapt the large-scale English dataset MathQA as a counterpart of the Chinese dataset Math23K. Then we extend several English datasets to bilingual datasets through machine translation plus human annotation. Our expe…
EPFL University（洛桑联邦理工学院）；Idiap Research Institute（伊迪亚普研究所）；DeepMind（深度思维）；Google Brain（谷歌大脑）
State-of-the-art parameter-efficient fine-tuning methods rely on introducing adapter modules between the layers of a pretrained language model. However, such modules are trained separately for each task and thus do not enable sharing information across tasks. In this paper, we show that we can learn adapter parameters for all layers and tasks by generating them using shared hypernetworks, which condition on task, adapter position, and layer id in a transformer model. This parameter-efficient multi-task learning framework allows us to achieve the best of both worlds by sharing knowledge across …
Can pretrained language models (PLMs) generate derivationally complex words? We present the first study investigating this question, taking BERT as the example PLM. We examine BERT's derivational capabilities in different settings, ranging from using the unmodified pretrained model to full finetuning. Our best model, DagoBERT (Derivationally and generatively optimized BERT), clearly outperforms the previous state of the art in derivation generation (DG). Furthermore, our experiments show that the input segmentation crucially impacts BERT's derivational knowledge, suggesting that the performanc…
University of Amsterdam（阿姆斯特丹大学）；Naver Labs Europe（Naver欧洲实验室）
Parameter-Efficient transfer learning with Adapters have been studied in Natural Language Processing (NLP) as an alternative to full fine-tuning. Adapters are memory-efficient and scale well with downstream tasks by training small bottle-neck layers added between transformer layers while keeping the large pretrained language model (PLMs) frozen. In spite of showing promising results in NLP, these methods are under-explored in Information Retrieval. While previous studies have only experimented with dense retriever or in a cross lingual retrieval scenario, in this paper we aim to complete the p…
University of Edinburgh（爱丁堡大学）；NAVER AI Lab（NAVER人工智能实验室）；NAVER Clova AI（NAVER Clova人工智能）
Metadata attributes (e.g., user and product IDs from reviews) can be incorporated as additional inputs to neural-based NLP models, by modifying the architecture of the models, in order to improve their performance. Recent models however rely on pretrained language models (PLMs), where previously used techniques for attribute injection are either nontrivial or ineffective. In this paper, we propose a lightweight and memory-efficient method to inject attributes to PLMs. We extend adapters, i.e. tiny plug-in feed-forward modules, to include attributes both independently of or jointly with the tex…
University of Chicago（芝加哥大学）；Toyota Technological Institute at Chicago（芝加哥丰田技术研究所）；University of Michigan（密歇根大学）；Johns Hopkins University（约翰斯·霍普金斯大学）
While transferring a pretrained language model, common approaches conventionally attach their task-specific classifiers to the top layer and adapt all the pretrained layers. We investigate whether one could make a task-specific selection on which subset of the layers to adapt and where to place the classifier. The goal is to reduce the computation cost of transfer learning methods (e.g. fine-tuning or adapter-tuning) without sacrificing its performance. We propose to select layers based on the variability of their hidden states given a task-specific corpus. We say a layer is already "well-spec…
University of Mannheim（曼海姆大学）；Bocconi University（博科尼大学）
Unfair stereotypical biases (e.g., gender, racial, or religious biases) encoded in modern pretrained language models (PLMs) have negative ethical implications for widespread adoption of state-of-the-art language technology. To remedy for this, a wide range of debiasing techniques have recently been introduced to remove such stereotypical biases from PLMs. Existing debiasing methods, however, directly modify all of the PLMs parameters, which -- besides being computationally expensive -- comes with the inherent risk of (catastrophic) forgetting of useful language knowledge acquired in pretrainin…
We introduce Trankit, a light-weight Transformer-based Toolkit for multilingual Natural Language Processing (NLP). It provides a trainable pipeline for fundamental NLP tasks over 100 languages, and 90 pretrained pipelines for 56 languages. Built on a state-of-the-art pretrained language model, Trankit significantly outperforms prior multilingual NLP pipelines over sentence segmentation, part-of-speech tagging, morphological feature tagging, and dependency parsing while maintaining competitive performance for tokenization, multi-word token expansion, and lemmatization over 90 Universal Dependen…
Tencent AI LAB（腾讯人工智能实验室）；UBTECH Sydney AI Center（优必选悉尼人工智能中心）；The University of Sydney（悉尼大学）；Tencent Robotics X（腾讯机器人X实验室）
Large-scale pretrained language models have achieved outstanding performance on natural language understanding tasks. However, it is still under investigating how to apply them to dialogue generation tasks, especially those with responses conditioned on multiple sources. Previous work simply concatenates all input sources or averages information from different input sources. In this work, we study dialogue models with multiple input sources adapted from the pretrained language model GPT2. We explore various methods to fuse multiple separate attention information corresponding to different sour…
GIFT: Guided Fine-Tuning and Transfer for Enhancing Instruction-Tuned Language Models
Southern University of Science and Technology（南方科技大学）；Alibaba Group（阿里巴巴集团）；Shanghai University of Finance and Economics（上海财经大学）；Tsinghua University（清华大学）；Xiamen University（厦门大学）
Natural language modeling with limited training data is a challenging problem, and many algorithms make use of large-scale pretrained language models (PLMs) for this due to its great generalization ability. Among them, additive learning that incorporates a task-specific adapter on top of the fixed large-scale PLM has been popularly used in the few-shot setting. However, this added adapter is still easy to disregard the knowledge of the PLM especially for few-shot natural language generation (NLG) since an entire sequence is usually generated by only the newly trained adapter. Therefore, in thi…
National Technical University of Athens（雅典国立技术大学）；Athena Research Center（雅典娜研究中心）
Multimodal learning pipelines have benefited from the success of pretrained language models. However, this comes at the cost of increased model parameters. In this work, we propose Adapted Multimodal BERT (AMB), a BERT-based architecture for multimodal tasks that uses a combination of adapter modules and intermediate fusion layers. The adapter adjusts the pretrained language model for the task at hand, while the fusion layers perform task-specific, layer-wise fusion of audio-visual information with textual BERT representations. During the adaptation process the pre-trained language model param…
University of California, Santa Barbara（加州大学圣巴巴拉分校）
The adoption of natural language generation (NLG) models can leave individuals vulnerable to the generation of harmful information memorized by the models, such as conspiracy theories. While previous studies examine conspiracy theories in the context of social media, they have not evaluated their presence in the new space of generative language models. In this work, we investigate the capability of language models to generate conspiracy theory text. Specifically, we aim to answer: can we test pretrained generative language models for the memorization and elicitation of conspiracy theories with…
Active learning has been shown to be an effective way to alleviate some of the effort required in utilising large collections of unlabelled data for machine learning tasks without needing to fully label them. The representation mechanism used to represent text documents when performing active learning, however, has a significant influence on how effective the process will be. While simple vector representations such as bag-of-words and embedding-based representations based on techniques such as word2vec have been shown to be an effective way to represent documents during active learning, the e…
University of Mannheim（曼海姆大学）；University of Cambridge（剑桥大学）；University of Würzburg（维尔茨堡大学）
State-of-the-art neural (re)rankers are notoriously data-hungry which -- given the lack of large-scale training data in languages other than English -- makes them rarely used in multilingual and cross-lingual retrieval settings. Current approaches therefore commonly transfer rankers trained on English data to other languages and cross-lingual setups by means of multilingual encoders: they fine-tune all parameters of pretrained massively multilingual Transformers (MMTs, e.g., multilingual BERT) on English relevance judgments, and then deploy them in the target language(s). In this work, we show…
Pretrained Transformers achieve state-of-the-art performance in various code-processing tasks but may be too large to be deployed. As software development tools often incorporate modules for various purposes which may potentially use a single instance of the pretrained model, it appears relevant to utilize parameter-efficient fine-tuning for the pretrained models of code. In this work, we test two widely used approaches, adapters and LoRA, which were initially tested on NLP tasks, on four code-processing tasks. We find that though the efficient fine-tuning approaches may achieve comparable or …
