Word2Vec is a prominent model for natural language processing (NLP) tasks. Similar inspiration is found in distributed embeddings for new state-of-the-art (SotA) deep neural networks. However, wrong combination of hyper-parameters can produce poor quality vectors. The objective of this work is to empirically show optimal combination of hyper-parameters exists and evaluate various combinations. We compare them with the released, pre-trained original word2vec model. Both intrinsic and extrinsic (downstream) evaluations, including named entity recognition (NER) and sentiment analysis (SA) were carried out. The downstream tasks reveal that the best model is usually task-specific, high analogy scores don't necessarily correlate positively with F1 scores and the same applies to focus on data alone. Increasing vector dimension size after a point leads to poor quality or performance. If ethical considerations to save time, energy and the environment are made, then reasonably smaller corpora may do just as well or even better in some cases. Besides, using a small corpus, we obtain better human-assigned WordSim scores, corresponding Spearman correlation and better downstream performances (with significance tests) compared to the original model, trained on 100 billion-word corpus.
Duke University（杜克大学）；Amazon Alexa AI（亚马逊Alexa人工智能）；Emory University（埃默里大学）
Numbers are essential components of text, like any other word tokens, from which natural language processing (NLP) models are built and deployed. Though numbers are typically not accounted for distinctly in most NLP tasks, there is still an underlying amount of numeracy already exhibited by NLP models. In this work, we attempt to tap this potential of state-of-the-art NLP models and transfer their ability to boost performance in related tasks. Our proposed classification of numbers into entities helps NLP models perform well on several tasks, including a handcrafted Fill-In-The-Blank (FITB) ta…
Facebook AI Research（Facebook AI研究院）；University College London（伦敦大学学院）；New York University（纽约大学）
Large pre-trained language models have been shown to store factual knowledge in their parameters, and achieve state-of-the-art results when fine-tuned on downstream NLP tasks. However, their ability to access and precisely manipulate knowledge is still limited, and hence on knowledge-intensive tasks, their performance lags behind task-specific architectures. Additionally, providing provenance for their decisions and updating their world knowledge remain open research problems. Pre-trained models with a differentiable access mechanism to explicit non-parametric memory can overcome this issue, b…
Athens University of Economics and Business（雅典经济与商业大学）
Transformer-based language models, such as BERT and its variants, have achieved state-of-the-art performance in several downstream natural language processing (NLP) tasks on generic benchmark datasets (e.g., GLUE, SQUAD, RACE). However, these models have mostly been applied to the resource-rich English language. In this paper, we present GREEK-BERT, a monolingual BERT-based language model for modern Greek. We evaluate its performance in three NLP tasks, i.e., part-of-speech tagging, named entity recognition, and natural language inference, obtaining state-of-the-art performance. Interestingly,…
Untether AI（Untether AI公司）；Manulife（宏利金融）；Tealbook（Tealbook公司）；CIBC（加拿大帝国商业银行）；Adeptmind（Adeptmind公司）；Intact（Intact公司）；University of Toronto（多伦多大学）；Vector Institute（矢量研究所）
With the growing amount of text in health data, there have been rapid advances in large pre-trained models that can be applied to a wide variety of biomedical tasks with minimal task-specific modifications. Emphasizing the cost of these models, which renders technical replication challenging, this paper summarizes experiments conducted in replicating BioBERT and further pre-training and careful fine-tuning in the biomedical domain. We also investigate the effectiveness of domain-specific and domain-agnostic pre-trained models across downstream biomedical NLP tasks. Our finding confirms that pr…
Document digitization is essential for the digital transformation of our societies, yet a crucial step in the process, Optical Character Recognition (OCR), is still not perfect. Even commercial OCR systems can produce questionable output depending on the fidelity of the scanned documents. In this paper, we demonstrate an effective framework for mitigating OCR errors for any downstream NLP task, using Named Entity Recognition (NER) as an example. We first address the data scarcity problem for model training by constructing a document synthesis pipeline, generating realistic but degraded data wi…
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Microsoft Research Montreal（微软研究院蒙特利尔分院）；Intuit AI（Intuit人工智能研究院）
Recent advances in NLP demonstrate the effectiveness of training large-scale language models and transferring them to downstream tasks. Can fine-tuning these models on tasks other than language modeling further improve performance? In this paper, we conduct an extensive study of the transferability between 33 NLP tasks across three broad classes of problems (text classification, question answering, and sequence labeling). Our results show that transfer learning is more beneficial than previously thought, especially when target task data is scarce, and can improve performance even when the sour…
Grainger College of Engineering, University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校格兰杰工程学院）；IBM Research（IBM研究院）；Apple Knowledge Platform（苹果知识平台）
Open Information Extraction (OpenIE) has been used in the pipelines of various NLP tasks. Unfortunately, there is no clear consensus on which models to use in which tasks. Muddying things further is the lack of comparisons that take differing training sets into account. In this paper, we present an application-focused empirical survey of neural OpenIE models, training sets, and benchmarks in an effort to help users choose the most suitable OpenIE systems for their applications. We find that the different assumptions made by different models and datasets have a statistically significant effect …
Alt Vietnam Co., Ltd（Alt Vietnam Co., Ltd（Alt越南有限公司））
In this paper, we present a feature-based named-entity recognition (NER) model that achieves the start-of-the-art accuracy for Vietnamese language. We combine word, word-shape features, PoS, chunk, Brown-cluster-based features, and word-embedding-based features in the Conditional Random Fields (CRF) model. We also explore the effects of word segmentation, PoS tagging, and chunking results of many popular Vietnamese NLP toolkits on the accuracy of the proposed feature-based NER model. Up to now, our work is the first work that systematically performs an extrinsic evaluation of basic Vietnamese …
Indian Institute of Technology, Kharagpur（印度理工学院卡拉格普尔分校）
In this paper we demonstrate how code-switching patterns can be utilised to improve various downstream NLP applications. In particular, we encode different switching features to improve humour, sarcasm and hate speech detection tasks. We believe that this simple linguistic observation can also be potentially helpful in improving other similar NLP applications.
UMass Amherst（马萨诸塞大学阿默斯特分校）；UMass Lowell（马萨诸塞大学洛厄尔分校）；UMass Medical School（马萨诸塞大学医学院）；U.S. Department of Veterans Affairs（美国退伍军人事务部）
This paper proposes a new natural language processing (NLP) application for identifying medical jargon terms potentially difficult for patients to comprehend from electronic health record (EHR) notes. We first present a novel and publicly available dataset with expert-annotated medical jargon terms from 18K+ EHR note sentences ($MedJ$). Then, we introduce a novel medical jargon extraction ($MedJEx$) model which has been shown to outperform existing state-of-the-art NLP models. First, MedJEx improved the overall performance when it was trained on an auxiliary Wikipedia hyperlink span dataset, w…
University of Cambridge（剑桥大学）；Sapienza University of Rome（罗马大学）
Lexical ambiguity can impede NLP systems from accurate understanding of semantics. Despite its potential benefits, the integration of sense-level information into NLP systems has remained understudied. By incorporating a novel disambiguation algorithm into a state-of-the-art classification model, we create a pipeline to integrate sense-level information into downstream NLP applications. We show that a simple disambiguation of the input text can lead to consistent performance improvement on multiple topic categorization and polarity detection datasets, particularly when the fine granularity of …
Information Retrieval (IR) is the task of obtaining pieces of data (such as documents) that are relevant to a particular query or need from a large repository of information. IR is a valuable component of several downstream Natural Language Processing (NLP) tasks. Practically, IR is at the heart of many widely-used technologies like search engines. While probabilistic ranking functions like the Okapi BM25 function have been utilized in IR systems since the 1970's, modern neural approaches pose certain advantages compared to their classical counterparts. In particular, the release of BERT (Bidi…
Pre-trained Natural Language Processing (NLP) models can be easily adapted to a variety of downstream language tasks. This significantly accelerates the development of language models. However, NLP models have been shown to be vulnerable to backdoor attacks, where a pre-defined trigger word in the input text causes model misprediction. Previous NLP backdoor attacks mainly focus on some specific tasks. This makes those attacks less general and applicable to other kinds of NLP models and tasks. In this work, we propose \Name, the first task-agnostic backdoor attack against the pre-trained NLP mo…
Encoded text representations often capture sensitive attributes about individuals (e.g., race or gender), which raise privacy concerns and can make downstream models unfair to certain groups. In this work, we propose FEDERATE, an approach that combines ideas from differential privacy and adversarial training to learn private text representations which also induces fairer models. We empirically evaluate the trade-off between the privacy of the representations and the fairness and accuracy of the downstream model on four NLP datasets. Our results show that FEDERATE consistently improves upon pre…
Contextualized representations from a pre-trained language model are central to achieve a high performance on downstream NLP task. The pre-trained BERT and A Lite BERT (ALBERT) models can be fine-tuned to give state-ofthe-art results in sentence-pair regressions such as semantic textual similarity (STS) and natural language inference (NLI). Although BERT-based models yield the [CLS] token vector as a reasonable sentence embedding, the search for an optimal sentence embedding scheme remains an active research area in computational linguistics. This paper explores on sentence embedding models fo…
The general goal of text simplification (TS) is to reduce text complexity for human consumption. This paper investigates another potential use of neural TS: assisting machines performing natural language processing (NLP) tasks. We evaluate the use of neural TS in two ways: simplifying input texts at prediction time and augmenting data to provide machines with additional information during training. We demonstrate that the latter scenario provides positive effects on machine performance on two separate datasets. In particular, the latter use of TS improves the performances of LSTM (1.82-1.98%) …
ELMo embeddings (Peters et. al, 2018) had a huge impact on the NLP community and may recent publications use these embeddings to boost the performance for downstream NLP tasks. However, integration of ELMo embeddings in existent NLP architectures is not straightforward. In contrast to traditional word embeddings, like GloVe or word2vec embeddings, the bi-directional language model of ELMo produces three 1024 dimensional vectors per token in a sentence. Peters et al. proposed to learn a task-specific weighting of these three vectors for downstream tasks. However, this proposed weighting scheme …
Qatar Computing Research Institute, HBKU（哈马德·本·哈利法大学卡塔尔计算研究所）
Transfer learning from pre-trained neural language models towards downstream tasks has been a predominant theme in NLP recently. Several researchers have shown that deep NLP models learn non-trivial amount of linguistic knowledge, captured at different layers of the model. We investigate how fine-tuning towards downstream NLP tasks impacts the learned linguistic knowledge. We carry out a study across popular pre-trained models BERT, RoBERTa and XLNet using layer and neuron-level diagnostic classifiers. We found that for some GLUE tasks, the network relies on the core linguistic information and…
University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）；Microsoft Research（微软研究院）；Google Research（谷歌研究院）
Meta-learning considers the problem of learning an efficient learning process that can leverage its past experience to accurately solve new tasks. However, the efficacy of meta-learning crucially depends on the distribution of tasks available for training, and this is often assumed to be known a priori or constructed from limited supervised datasets. In this work, we aim to provide task distributions for meta-learning by considering self-supervised tasks automatically proposed from unlabeled text, to enable large-scale meta-learning in NLP. We design multiple distributions of self-supervised t…
We investigate input-conditioned hypernetworks for multi-tasking in NLP, generating parameter-efficient adaptations for a decoder using a hypernetwork conditioned on the output of an encoder. This approach produces a unique decoder adaptation for every input instance, allowing the network a larger degree of flexibility than prior work that only produces one decoder adaptation per task. We apply our method to sequence classification tasks, extractive QA, and summarisation and find that it surpasses previous parameter efficient fine-tuning methods and often outperforms fully finetuning the under…
Transformers have greatly advanced the state-of-the-art in Natural Language Processing (NLP) in recent years, but present very large computation and storage requirements. We observe that the design process of Transformers (pre-train a foundation model on a large dataset in a self-supervised manner, and subsequently fine-tune it for different downstream tasks) leads to task-specific models that are highly over-parameterized, adversely impacting both accuracy and inference efficiency. We propose AxFormer, a systematic framework that applies accuracy-driven approximations to create optimized tran…
Google Research（谷歌研究院）；Jagiellonian University（雅盖隆大学）
Fine-tuning large pre-trained models is an effective transfer mechanism in NLP. However, in the presence of many downstream tasks, fine-tuning is parameter inefficient: an entire new model is required for every task. As an alternative, we propose transfer with adapter modules. Adapter modules yield a compact and extensible model; they add only a few trainable parameters per task, and new tasks can be added without revisiting previous ones. The parameters of the original network remain fixed, yielding a high degree of parameter sharing. To demonstrate adapter's effectiveness, we transfer the re…
Continued Pretraining of FinBERT on Finnish Histopathological Reports: Train-Time Signals and Proxy Downstream Correlations
Digital Workforce Services（数字劳动力服务）；Heart and Lung Center, Helsinki University Hospital（赫尔辛基大学医院心脏和肺中心）；Central Finland Biobank（中央芬兰生物库）；Wellbeing Services County of Central Finland（中央芬兰县福祉服务）
School of Information Science and Technology, Guangdong University of Foreign Studies（广东外语外贸大学信息科学与技术学院）；School of Mathematics and Statistics, Guangdong University of Foreign Studies（广东外语外贸大学数学与统计学院）；Guangzhou Key Laboratory of Multilingual Intelligent Processing, Guangdong University of Foreign Studies（广东外语外贸大学广州市多语言智能处理重点实验室）
Trained on the large corpus, pre-trained language models (PLMs) can capture different levels of concepts in context and hence generate universal language representations. They can benefit multiple downstream natural language processing (NLP) tasks. Although PTMs have been widely used in most NLP applications, especially for high-resource languages such as English, it is under-represented in Lao NLP research. Previous work on Lao has been hampered by the lack of annotated datasets and the sparsity of language resources. In this work, we construct a text classification dataset to alleviate the r…
Microsoft Corporation（微软公司）；Coleridge Initiative（科尔里奇倡议组织）
Many prior language modeling efforts have shown that pre-training on an in-domain corpus can significantly improve performance on downstream domain-specific NLP tasks. However, the difficulties associated with collecting enough in-domain data might discourage researchers from approaching this pre-training task. In this paper, we conducted a series of experiments by pre-training Bidirectional Encoder Representations from Transformers (BERT) with different sizes of biomedical corpora. The results demonstrate that pre-training on a relatively small amount of in-domain data (4GB) with limited trai…
Technion – Israel Institute of Technology（以色列理工学院）；University of Edinburgh（爱丁堡大学）
Common studies of gender bias in NLP focus either on extrinsic bias measured by model performance on a downstream task or on intrinsic bias found in models' internal representations. However, the relationship between extrinsic and intrinsic bias is relatively unknown. In this work, we illuminate this relationship by measuring both quantities together: we debias a model during downstream fine-tuning, which reduces extrinsic bias, and measure the effect on intrinsic bias, which is operationalized as bias extractability with information-theoretic probing. Through experiments on two tasks and mult…
Pre-trained Language Models (PLMs) have proven to be beneficial for various downstream NLP tasks. Recently, GPT-3, with 175 billion parameters and 570GB training data, drew a lot of attention due to the capacity of few-shot (even zero-shot) learning. However, applying GPT-3 to address Chinese NLP tasks is still challenging, as the training corpus of GPT-3 is primarily English, and the parameters are not publicly available. In this technical report, we release the Chinese Pre-trained Language Model (CPM) with generative pre-training on large-scale Chinese training data. To the best of our knowl…
The Ohio State University（俄亥俄州立大学）；University of Warwick（华威大学）
Analysis of word embedding properties to inform their use in downstream NLP tasks has largely been studied by assessing nearest neighbors. However, geometric properties of the continuous feature space contribute directly to the use of embedding features in downstream models, and are largely unexplored. We consider four properties of word embedding geometry, namely: position relative to the origin, distribution of features in the vector space, global pairwise distances, and local pairwise distances. We define a sequence of transformations to generate new embeddings that expose subsets of these …
Georgia Institute of Technology（佐治亚理工学院）；Microsoft Dynamics 365 AI（微软Dynamics 365 AI）；Microsoft Research（微软研究院）
Transfer learning has fundamentally changed the landscape of natural language processing (NLP) research. Many existing state-of-the-art models are first pre-trained on a large text corpus and then fine-tuned on downstream tasks. However, due to limited data resources from downstream tasks and the extremely large capacity of pre-trained models, aggressive fine-tuning often causes the adapted model to overfit the data of downstream tasks and forget the knowledge of the pre-trained model. To address the above issue in a more principled manner, we propose a new computational framework for robust a…
Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）；Institute for Artificial Intelligence, Tsinghua University（清华大学人工智能研究院）；Beijing National Research Center for Information Science and Technology（北京国家信息科学与技术研究中心）；State Key Lab on Intelligent Technology and Systems, Tsinghua University（清华大学智能技术与系统国家重点实验室）；Pattern Recognition Center, WeChat AI, Tencent Inc.（腾讯微信AI模式识别中心）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）
Language representation models such as BERT could effectively capture contextual semantic information from plain text, and have been proved to achieve promising results in lots of downstream NLP tasks with appropriate fine-tuning. However, most existing language representation models cannot explicitly handle coreference, which is essential to the coherent understanding of the whole discourse. To address this issue, we present CorefBERT, a novel language representation model that can capture the coreferential relations in context. The experimental results show that, compared with existing basel…
Plug-and-Play Knowledge Injection for Pre-trained Language Models
Renmin University of China（中国人民大学）；Tsinghua University（清华大学）；International Innovation Center of Tsinghua University（清华大学国际创新中心）；Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院（AIR））；Tencent Inc（腾讯公司）；Quan Cheng Laboratory（泉城实验室）
A post-pandemic world resulted in economic upheaval, particularly for the cities' communities. While significant work in NLP4PI focuses on national and international events, there is a gap in bringing such state-of-the-art methods into the community development field. In order to help with community development, we must learn about the communities we develop. To that end, we propose the task of community learning as a computational task of extracting natural language data about the community, transforming and loading it into a suitable knowledge graph structure for further downstream applicati…
Transformer-based pre-trained models with millions of parameters require large storage. Recent approaches tackle this shortcoming by training adapters, but these approaches still require a relatively large number of parameters. In this study, AdapterBias, a surprisingly simple yet effective adapter architecture, is proposed. AdapterBias adds a token-dependent shift to the hidden output of transformer layers to adapt to downstream tasks with only a vector and a linear layer. Extensive experiments are conducted to demonstrate the effectiveness of AdapterBias. The experiments show that our propos…
AfroLM: A Self-Active Learning-based Multilingual Pretrained Language Model for 23 African Languages
Mila Quebec AI Institute（米拉魁北克人工智能研究所）；McGill University（麦吉尔大学）；Instituto Politécnico Nacional（国家理工学院）；Uppsala University（乌普萨拉大学）；Universidad de Deusto（德乌斯托大学）；Ashesi University（阿希西大学）；Montclair State University（蒙特克莱尔州立大学）；The College of Saint Rose（圣罗斯学院）；Technical University of Munich（慕尼黑工业大学）
Semantic parsing is a key NLP task that maps natural language to structured meaning representations. As in many other NLP tasks, SOTA performance in semantic parsing is now attained by fine-tuning a large pretrained language model (PLM). While effective, this approach is inefficient in the presence of multiple downstream tasks, as a new set of values for all parameters of the PLM needs to be stored for each task separately. Recent work has explored methods for adapting PLMs to downstream tasks while keeping most (or all) of their parameters frozen. We examine two such promising techniques, pre…
Beijing University of Posts and Telecommunications（北京邮电大学）；Thomson Reuters Labs（汤森路透实验室）
Natural Language Processing (NLP) has been revolutionized by the use of Pre-trained Language Models (PLMs) such as BERT. Despite setting new records in nearly every NLP task, PLMs still face a number of challenges including poor interpretability, weak reasoning capability, and the need for a lot of expensive annotated data when applied to downstream tasks. By integrating external knowledge into PLMs, \textit{\underline{K}nowledge-\underline{E}nhanced \underline{P}re-trained \underline{L}anguage \underline{M}odels} (KEPLMs) have the potential to overcome the above-mentioned limitations. In this…
A wide range of NLP tasks benefit from the fine-tuning of pretrained language models (PLMs). However, a number of redundant parameters which contribute less to the downstream task are observed in a directly fine-tuned model. We consider the gap between pretraining and downstream tasks hinders the training of these redundant parameters, and results in a suboptimal performance of the overall model. In this paper, we present PATS (Perturbation According To Sensitivity), a noisy training mechanism which considers each parameter's importance in the downstream task to help fine-tune PLMs. The main i…
