Transfer learning methods, and in particular domain adaptation, help exploit labeled data in one domain to improve the performance of a certain task in another domain. However, it is still not clear what factors affect the success of domain adaptation. This paper models adaptation success and selection of the most suitable source domains among several candidates in text similarity. We use descriptive domain information and cross-domain similarity metrics as predictive features. While mostly positive, the results also point to some domains where adaptation success was difficult to predict.
Center for Information & Language Processing, LMU Munich（慕尼黑大学信息与语言处理中心）；Institute for Finance & Banking, LMU Munich（慕尼黑大学金融与银行研究所）
In this paper, we automatically create sentiment dictionaries for predicting financial outcomes. We compare three approaches: (I) manual adaptation of the domain-general dictionary H4N, (ii) automatic adaptation of H4N and (iii) a combination consisting of first manual, then automatic adaptation. In our experiments, we demonstrate that the automatically adapted sentiment dictionary outperforms the previous state of the art in predicting the financial outcomes excess return and volatility. In particular, automatic adaptation performs better than manual adaptation. In our analysis, we find that …
Predicting Machine Translation Performance on Low-Resource Languages: The Role of Domain Similarity
University of Michigan（密歇根大学）；University of Toronto（多伦多大学）；Centro de Investigación en Matemáticas（数学研究中心）；Amherst College（阿默斯特学院）；Universiteit Gent（根特大学）；Ontario Tech University（安大略理工大学）
University of Canterbury（坎特伯雷大学）；New Zealand Institute for Language, Brain and Behaviour（新西兰语言、大脑与行为研究所）
This paper simulates a low-resource setting across 17 languages in order to evaluate embedding similarity, stability, and reliability under different conditions. The goal is to use corpus similarity measures before training to predict properties of embeddings after training. The main contribution of the paper is to show that it is possible to predict downstream embedding similarity using upstream corpus similarity measures. This finding is then applied to low-resource settings by modelling the reliability of embeddings created from very limited training data. Results show that it is possible t…
Measuring the similarity between two different sentential arguments is an important task in argument mining. However, one of the challenges in this field is that the dataset must be annotated using expertise in a variety of topics, making supervised learning with labeled data expensive. In this paper, we investigated whether this problem could be alleviated through transfer learning. We first adapted a pretrained language model to a domain of interest using self-supervised learning. Then, we fine-tuned the model to a task of measuring the similarity between sentences taken from different domai…
Seebyte Ltd（Seebyte有限公司）；University of Edinburgh（爱丁堡大学）
Due to the expensive nature of field data gathering, the lack of training data often limits the performance of Automatic Target Recognition (ATR) systems. This problem is often addressed with domain adaptation techniques, however the currently existing methods fail to satisfy the constraints of resource and time-limited underwater systems. We propose to address this issue via an online fine-tuning of the ATR algorithm using a novel data-selection method. Our proposed data-mining approach relies on visual similarity and outperforms the traditionally employed hard-mining methods. We present a co…
Bosch Center for Artificial Intelligence（博世人工智能中心）；Saarland University（萨尔大学）
In low-resource settings, model transfer can help to overcome a lack of labeled data for many tasks and domains. However, predicting useful transfer sources is a challenging problem, as even the most similar sources might lead to unexpected negative transfer results. Thus, ranking methods based on task and text similarity -- as suggested in prior work -- may not be sufficient to identify promising sources. To tackle this problem, we propose a new approach to automatically determine which and how many sources should be exploited. For this, we study the effects of model transfer on sequence labe…
In this technical report, we present our solution to the Traffic4Cast 2021 Core Challenge, in which participants were asked to develop algorithms for predicting a traffic state 60 minutes ahead, based on the information from the previous hour, in 4 different cities. In contrast to the previously held competitions, this year's challenge focuses on the temporal domain shift in traffic due to the COVID-19 pandemic. Following the past success of U-Net, we utilize it for predicting future traffic maps. Additionally, we explore the usage of pre-trained encoders such as DenseNet and EfficientNet and …
This thesis contributes to the mathematical foundation of domain adaptation as emerging field in machine learning. In contrast to classical statistical learning, the framework of domain adaptation takes into account deviations between probability distributions in the training and application setting. Domain adaptation applies for a wider range of applications as future samples often follow a distribution that differs from the ones of the training samples. A decisive point is the generality of the assumptions about the similarity of the distributions. Therefore, in this thesis we study domain a…
Unsupervised domain adaptation (UDA) transfers knowledge from a label-rich source domain to a different but related fully-unlabeled target domain. To address the problem of domain shift, more and more UDA methods adopt pseudo labels of the target samples to improve the generalization ability on the target domain. However, inaccurate pseudo labels of the target samples may yield suboptimal performance with error accumulation during the optimization process. Moreover, once the pseudo labels are generated, how to remedy the generated pseudo labels is far from explored. In this paper, we propose a…
Semi-Supervised Deep Domain Adaptation for Predicting Solar Power Across Different Locations
University of California, Riverside, California, USA（加州大学河滨分校）；North South University, Dhaka, Bangladesh（北南大学）；Louisiana State University, Louisiana, USA（路易斯安那州立大学）
Georgia Institute of Technology（佐治亚理工学院）；Georgia Tech Research Institute（佐治亚理工学院研究院）
This paper introduces a novel method to perform transfer learning across domains and tasks, formulating it as a problem of learning to cluster. The key insight is that, in addition to features, we can transfer similarity information and this is sufficient to learn a similarity function and clustering network to perform both domain adaptation and cross-task transfer learning. We begin by reducing categorical information to pairwise constraints, which only considers whether two instances belong to the same class or not. This similarity is category-agnostic and can be learned from data in the sou…
Predicting Onflow Parameters Using Transfer Learning for Domain and Task Adaptation
German Aerospace Center (DLR) - Institute of Aerodynamics and Flow Technology, Center for Computer Applications in AeroSpace Science and Engineering（德国航空航天中心（DLR）- 流体力学与流动技术研究所，航空科学与工程计算机应用中心）；German Aerospace Center (DLR) - Institute of Aerodynamics（德国航空航天中心（DLR）- 流体力学与流动技术研究所）；Flow Technology, Center for Computer Applications in AeroSpace Science（流动技术，航空科学计算机应用中心）
Université d'Orléans（奥尔良大学）；Institut National Des Télécommunications et TIC（国家电信与信息通信技术学院）
Predicting the quality of multimedia content is often needed in different fields. In some applications, quality metrics are crucial with a high impact, and can affect decision making such as diagnosis from medical multimedia. In this paper, we focus on such applications by proposing an efficient and shallow model for predicting the quality of medical images without reference from a small amount of annotated data. Our model is based on convolution self-attention that aims to model complex representation from relevant local characteristics of images, which itself slide over the image to interpol…
To Adapt or Not to Adapt? Selective Adaptation for Vision-Language Models
School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences（中国科学院大学先进交叉科学学院）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Nanjing University（南京大学）
Bayesian Meta-Learning with Expert Feedback for Task-Shift Adaptation through Causal Embeddings
Department of Computer Science, Aalto University, Espoo, Finland（Aalto大学计算机科学系）；ELLIS Institute Finland, Espoo, Finland（芬兰ELLIS研究所）；Department of Computer Science, University of Manchester, United Kingdom（曼彻斯特大学计算机科学系）
University of Electronic Science and Technology of China（电子科技大学）
Unsupervised Domain Adaptation (UDA) aims to generalize the knowledge learned from a well-labeled source domain to an unlabeled target domain. Recently, adversarial domain adaptation with two distinct classifiers (bi-classifier) has been introduced into UDA which is effective to align distributions between different domains. Previous bi-classifier adversarial learning methods only focus on the similarity between the outputs of two distinct classifiers. However, the similarity of the outputs cannot guarantee the accuracy of target samples, i.e., target samples may match to wrong categories even…
University of Pennsylvania（宾夕法尼亚大学）；Massachusetts Institute of Technology（麻省理工学院）
We study the prevalent problem when a test distribution differs from the training distribution. We consider a setting where our training set consists of a small number of sample domains, but where we have many samples in each domain. Our goal is to generalize to a new domain. For example, we may want to learn a similarity function using only certain classes of objects, but we desire that this similarity function be applicable to object classes not present in our training sample (e.g. we might seek to learn that "dogs are similar to dogs" even though images of dogs were absent from our training…
This work connects language model adaptation with concepts of machine learning theory. We consider a training setup with a large out-of-domain set and a small in-domain set. We derive how the benefit of training a model on either set depends on the size of the sets and the distance between their underlying distributions. We analyze how out-of-domain pre-training before in-domain fine-tuning achieves better generalization than either solution independently. Finally, we present how adaptation techniques based on data selection, such as importance sampling, intelligent data selection and influenc…
Multi-source unsupervised domain adaptation (MUDA) is a framework to address the challenge of annotated data scarcity in a target domain via transferring knowledge from multiple annotated source domains. When the source domains are distributed, data privacy and security can become significant concerns and protocols may limit data sharing, yet existing MUDA methods overlook these constraints. We develop an algorithm to address MUDA when source domain data cannot be shared with the target or across the source domains. Our method is based on aligning the distributions of source and target domains…
An Initial Investigation of Language Adaptation for TTS Systems under Low-resource Scenarios
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；National Institute of Informatics（日本信息学研究所）；National Research Council Canada（加拿大国家研究委员会）；The Centre for Speech Technology Research, University of Edinburgh（爱丁堡大学言语技术研究中心）；National Institute of Information and Communications Technology（日本信息通信研究机构）
The image acquisition parameters (IAPs) used to create MRI scans are central to defining the appearance of the images. Deep learning models trained on data acquired using certain parameters might not generalize well to images acquired with different parameters. Being able to recover such parameters directly from an image could help determine whether a deep learning model is applicable, and could assist with data harmonization and/or domain adaptation. Here, we introduce a neural network model that can predict many complex IAPs used to generate an MR image with high accuracy solely using the im…
Prediction in a new domain without any training sample, called zero-shot domain adaptation (ZSDA), is an important task in domain adaptation. While prediction in a new domain has gained much attention in recent years, in this paper, we investigate another potential of ZSDA. Specifically, instead of predicting responses in a new domain, we find a description of a new domain given a prediction. The task is regarded as predictive optimization, but existing predictive optimization methods have not been extended to handling multiple domains. We propose a simple framework for predictive optimization…
We study the problem of predicting the future, though only in the probabilistic sense of estimating a future state of a time-varying probability distribution. This is not only an interesting academic problem, but solving this extrapolation problem also has many practical application, e.g. for training classifiers that have to operate under time-varying conditions. Our main contribution is a method for predicting the next step of the time-varying distribution from a given sequence of sample sets from earlier time steps. For this we rely on two recent machine learning techniques: embedding proba…
University of Lincoln（林肯大学）；University of Aberdeen（阿伯丁大学）
Recently, contrastive self-supervised learning has become a key component for learning visual representations across many computer vision tasks and benchmarks. However, contrastive learning in the context of domain adaptation remains largely underexplored. In this paper, we propose to extend contrastive learning to a new domain adaptation setting, a particular situation occurring where the similarity is learned and deployed on samples following different probability distributions without access to labels. Contrastive learning learns by comparing and contrasting positive and negative pairs of s…
Princeton University（普林斯顿大学）；Max Planck Institute for Empirical Aesthetics（马克斯·普朗克经验美学研究所）
Similarity judgments provide a well-established method for accessing mental representations, with applications in psychology, neuroscience and machine learning. However, collecting similarity judgments can be prohibitively expensive for naturalistic datasets as the number of comparisons grows quadratically in the number of stimuli. One way to tackle this problem is to construct approximation procedures that rely on more accessible proxies for predicting similarity. Here we leverage recent advances in language models and online recruitment, proposing an efficient domain-general procedure for pr…
IBM Hellas（IBM希腊公司）；National Technical University of Athens（雅典国立技术大学）；University of Lincoln（林肯大学）
This paper presents a new method for medical diagnosis of neurodegenerative diseases, such as Parkinson's, by extracting and using latent information from trained Deep convolutional, or convolutional-recurrent Neural Networks (DNNs). In particular, our approach adopts a combination of transfer learning, k-means clustering and k-Nearest Neighbour classification of deep neural network learned representations to provide enriched prediction of the disease based on MRI and/or DaT Scan data. A new loss function is introduced and used in the training of the DNNs, so as to perform adaptation of the ge…
BMW Group（宝马集团）；Technische Universität München（慕尼黑工业大学）；Google Inc.（谷歌公司）
Transfer learning is an important field of machine learning in general, and particularly in the context of fully autonomous driving, which needs to be solved simultaneously for many different domains, such as changing weather conditions and country-specific driving behaviors. Traditional transfer learning methods often focus on image data and are black-box models. In this work we propose a transfer learning framework, core of which is learning an explicit mapping between domains. Due to its interpretability, this is beneficial for safety-critical applications, like autonomous driving. We show …
Birmingham City University（伯明翰城市大学）；University of Wolverhampton（伍尔弗汉普顿大学）
This paper presents the team BRUMS submission to SemEval-2020 Task 3: Graded Word Similarity in Context. The system utilises state-of-the-art contextualised word embeddings, which have some task-specific adaptations, including stacked embeddings and average embeddings. Overall, the approach achieves good evaluation scores across all the languages, while maintaining simplicity. Following the final rankings, our approach is ranked within the top 5 solutions of each language while preserving the 1st position of Finnish subtask 2.
Natural Language Processing (NLP) has been widely used in the semantic analysis in recent years. Our paper mainly discusses a methodology to analyze the effect that context has on human perception of similar words, which is the third task of SemEval 2020. We apply several methods in calculating the distance between two embedding vector generated by Bidirectional Encoder Representation from Transformer (BERT). Our team will_go won the 1st place in Finnish language track of subtask1, the second place in English track of subtask1.
Université d’Avignon et des Pays de Vaucluse（阿维尼翁大学）；Universidade Federal do Ceará（塞阿拉联邦大学）；École Polytechnique de Montréal（蒙特利尔综合理工学院）
Semantic Textual Similarity (STS) is the basis of many applications in Natural Language Processing (NLP). Our system combines convolution and recurrent neural networks to measure the semantic similarity of sentences. It uses a convolution network to take account of the local context of words and an LSTM to consider the global context of sentences. This combination of networks helps to preserve the relevant information of sentences and improves the calculation of the similarity between sentences. Our model has achieved good results and is competitive with the best state-of-the-art systems.
Institute of Acoustics（声学研究所）；University of Chinese Academy of Sciences（中国科学院大学）；China Mobile Online Services Company Limited（中国移动在线服务有限公司）
When only limited target domain data is available, domain adaptation could be used to promote performance of deep neural network (DNN) acoustic model by leveraging well-trained source model and target domain data. However, suffering from domain mismatch and data sparsity, domain adaptation is very challenging. This paper proposes a novel adaptation method for DNN acoustic model using class similarity. Since the output distribution of DNN model contains the knowledge of similarity among classes, which is applicable to both source and target domain, it could be transferred from source to target …
Inference-time adaptation methods for semantic parsing are useful for leveraging examples from newly-observed domains without repeated fine-tuning. Existing approaches typically bias the decoder by simply concatenating input-output example pairs (cases) from the new domain at the encoder's input in a Seq-to-Seq model. Such methods cannot adequately leverage the structure of logical forms in the case examples. We propose StructCBR, a structured case-based reasoning approach, which leverages subtree-level similarity between logical forms of cases and candidate outputs, resulting in better decode…
Language Technology Lab, University of Cambridge（剑桥大学语言技术实验室）；Faculty of Industrial Engineering and Management, Technion, IIT（以色列理工学院工业工程与管理学院）
Performance in cross-lingual NLP tasks is impacted by the (dis)similarity of languages at hand: e.g., previous work has suggested there is a connection between the expected success of bilingual lexicon induction (BLI) and the assumption of (approximate) isomorphism between monolingual embedding spaces. In this work we present a large-scale study focused on the correlations between monolingual embedding space similarity and task performance, covering thousands of language pairs and four different tasks: BLI, parsing, POS tagging and MT. We hypothesize that statistics of the spectrum of each mon…
CovidLLM: A Robust Large Language Model with Missing Value Adaptation and Multi-Objective Learning Strategy for Predicting Disease Severity and Clinical Outcomes in COVID-19 Patients
School of Mathematics and Statistics, Xiamen University of Technology（厦门理工学院数学与统计学院）；School of Computer and Information Engineering, Xiamen University of Technology（厦门理工学院计算机与信息工程学院）；Tongji Medical College, Huazhong University of Science and Technology（华中科技大学同济医学院）
The goal of this paper is to investigate the connection between the performance gain that can be obtained by selftraining and the similarity between the corpora used in this approach. Self-training is a semi-supervised technique designed to increase the performance of machine learning algorithms by automatically classifying instances of a task and adding these as additional training material to the same classifier. In the context of language processing tasks, this training material is mostly an (annotated) corpus. Unfortunately self-training does not always lead to a performance increase and w…
Adapting a neural text-to-speech (TTS) model to a target speaker typically involves fine-tuning most if not all of the parameters of a pretrained multi-speaker backbone model. However, serving hundreds of fine-tuned neural TTS models is expensive as each of them requires significant footprint and separate computational resources (e.g., accelerators, memory). To scale speaker adapted neural TTS voices to hundreds of speakers while preserving the naturalness and speaker similarity, this paper proposes a parameter-efficient few-shot speaker adaptation, where the backbone model is augmented with t…
Machine translation systems are vulnerable to domain mismatch, especially in a low-resource scenario. Out-of-domain translations are often of poor quality and prone to hallucinations, due to exposure bias and the decoder acting as a language model. We adopt two approaches to alleviate this problem: lexical shortlisting restricted by IBM statistical alignments, and hypothesis re-ranking based on similarity. The methods are computationally cheap, widely known, but not extensively experimented on domain adaptation. We demonstrate success on low-resource out-of-domain test sets, however, the metho…
Domain-specific contextualized language models have demonstrated substantial effectiveness gains for domain-specific downstream tasks, like similarity matching, entity recognition or information retrieval. However successfully applying such models in highly specific language domains requires domain adaptation of the pre-trained models. In this paper we propose the empirically motivated Linguistically Informed Masking (LIM) method to focus domain-adaptative pre-training on the linguistic patterns of patents, which use a highly technical sublanguage. We quantify the relevant differences between …
