Our world is open-ended, non-stationary, and constantly evolving; thus what we talk about and how we talk about it change over time. This inherent dynamic nature of language contrasts with the current static language modelling paradigm, which trains and evaluates models on utterances from overlapping time periods. Despite impressive recent progress, we demonstrate that Transformer-XL language models perform worse in the realistic setup of predicting future utterances from beyond their training period, and that model performance becomes increasingly worse with time. We find that, while increasing model size alone -- a key driver behind recent progress -- does not solve this problem, having models that continually update their knowledge with new information can indeed mitigate this performance degradation over time. Hence, given the compilation of ever-larger language modelling datasets, combined with the growing list of language-model-based NLP applications that require up-to-date factual knowledge about the world, we argue that now is the right time to rethink the static way in which we currently train and evaluate our language models, and develop adaptive language models that can remain up-to-date with respect to our ever-changing and non-stationary world. We publicly release our dynamic, streaming language modelling benchmarks for WMT and arXiv to facilitate language model evaluation that takes temporal dynamics into account.

0
下载
关闭预览

相关内容

ACM/IEEE第23届模型驱动工程语言和系统国际会议,是模型驱动软件和系统工程的首要会议系列,由ACM-SIGSOFT和IEEE-TCSE支持组织。自1998年以来,模型涵盖了建模的各个方面,从语言和方法到工具和应用程序。模特的参加者来自不同的背景,包括研究人员、学者、工程师和工业专业人士。MODELS 2019是一个论坛,参与者可以围绕建模和模型驱动的软件和系统交流前沿研究成果和创新实践经验。今年的版本将为建模社区提供进一步推进建模基础的机会,并在网络物理系统、嵌入式系统、社会技术系统、云计算、大数据、机器学习、安全、开源等新兴领域提出建模的创新应用以及可持续性。 官网链接:http://www.modelsconference.org/

Keeping the performance of language technologies optimal as time passes is of great practical interest. Here we survey prior work concerned with the effect of time on system performance, establishing more nuanced terminology for discussing the topic and proper experimental design to support solid conclusions about the observed phenomena. We present a set of experiments with systems powered by large neural pretrained representations for English to demonstrate that {\em temporal model deterioration} is not as big a concern, with some models in fact improving when tested on data drawn from a later time period. It is however the case that {\em temporal domain adaptation} is beneficial, with better performance for a given time period possible when the system is trained on temporally more recent data. Our experiments reveal that the distinctions between temporal model deterioration and temporal domain adaptation becomes salient for systems built upon pretrained representations. Finally we examine the efficacy of two approaches for temporal domain adaptation without human annotations on new data, with self-labeling proving to be superior to continual pre-training. Notably, for named entity recognition, self-labeling leads to better temporal adaptation than human annotation.

0
0
下载
预览

The dominating NLP paradigm of training a strong neural predictor to perform one task on a specific dataset has led to state-of-the-art performance in a variety of applications (eg. sentiment classification, span-prediction based question answering or machine translation). However, it builds upon the assumption that the data distribution is stationary, ie. that the data is sampled from a fixed distribution both at training and test time. This way of training is inconsistent with how we as humans are able to learn from and operate within a constantly changing stream of information. Moreover, it is ill-adapted to real-world use cases where the data distribution is expected to shift over the course of a model's lifetime. The first goal of this thesis is to characterize the different forms this shift can take in the context of natural language processing, and propose benchmarks and evaluation metrics to measure its effect on current deep learning architectures. We then proceed to take steps to mitigate the effect of distributional shift on NLP models. To this end, we develop methods based on parametric reformulations of the distributionally robust optimization framework. Empirically, we demonstrate that these approaches yield more robust models as demonstrated on a selection of realistic problems. In the third and final part of this thesis, we explore ways of efficiently adapting existing models to new domains or tasks. Our contribution to this topic takes inspiration from information geometry to derive a new gradient update rule which alleviate catastrophic forgetting issues during adaptation.

0
8
下载
预览

Pre-trained Language Models (PLMs) have shown superior performance on various downstream Natural Language Processing (NLP) tasks. However, conventional pre-training objectives do not explicitly model relational facts in text, which are crucial for textual understanding. To address this issue, we propose a novel contrastive learning framework ERICA to obtain a deep understanding of the entities and their relations in text. Specifically, we define two novel pre-training tasks to better understand entities and relations: (1) the entity discrimination task to distinguish which tail entity can be inferred by the given head entity and relation; (2) the relation discrimination task to distinguish whether two relations are close or not semantically, which involves complex relational reasoning. Experimental results demonstrate that ERICA can improve typical PLMs (BERT and RoBERTa) on several language understanding tasks, including relation extraction, entity typing and question answering, especially under low-resource settings.

0
5
下载
预览

As we seek to deploy machine learning models beyond virtual and controlled domains, it is critical to analyze not only the accuracy or the fact that it works most of the time, but if such a model is truly robust and reliable. This paper studies strategies to implement adversary robustly trained algorithms towards guaranteeing safety in machine learning algorithms. We provide a taxonomy to classify adversarial attacks and defenses, formulate the Robust Optimization problem in a min-max setting and divide it into 3 subcategories, namely: Adversarial (re)Training, Regularization Approach, and Certified Defenses. We survey the most recent and important results in adversarial example generation, defense mechanisms with adversarial (re)Training as their main defense against perturbations. We also survey mothods that add regularization terms that change the behavior of the gradient, making it harder for attackers to achieve their objective. Alternatively, we've surveyed methods which formally derive certificates of robustness by exactly solving the optimization problem or by approximations using upper or lower bounds. In addition, we discuss the challenges faced by most of the recent algorithms presenting future research perspectives.

0
3
下载
预览

We propose to pre-train a unified language model for both autoencoding and partially autoregressive language modeling tasks using a novel training procedure, referred to as a pseudo-masked language model (PMLM). Given an input text with masked tokens, we rely on conventional masks to learn inter-relations between corrupted tokens and context via autoencoding, and pseudo masks to learn intra-relations between masked spans via partially autoregressive modeling. With well-designed position embeddings and self-attention masks, the context encodings are reused to avoid redundant computation. Moreover, conventional masks used for autoencoding provide global masking information, so that all the position embeddings are accessible in partially autoregressive language modeling. In addition, the two tasks pre-train a unified language model as a bidirectional encoder and a sequence-to-sequence decoder, respectively. Our experiments show that the unified language models pre-trained using PMLM achieve new state-of-the-art results on a wide range of natural language understanding and generation tasks across several widely used benchmarks.

0
13
下载
预览

Recent progress in pretraining language models on large textual corpora led to a surge of improvements for downstream NLP tasks. Whilst learning linguistic knowledge, these models may also be storing relational knowledge present in the training data, and may be able to answer queries structured as "fill-in-the-blank" cloze statements. Language models have many advantages over structured knowledge bases: they require no schema engineering, allow practitioners to query about an open class of relations, are easy to extend to more data, and require no human supervision to train. We present an in-depth analysis of the relational knowledge already present (without fine-tuning) in a wide range of state-of-the-art pretrained language models. We find that (i) without fine-tuning, BERT contains relational knowledge competitive with traditional NLP methods that have some access to oracle knowledge, (ii) BERT also does remarkably well on open-domain question answering against a supervised baseline, and (iii) certain types of factual knowledge are learned much more readily than others by standard language model pretraining approaches. The surprisingly strong ability of these models to recall factual knowledge without any fine-tuning demonstrates their potential as unsupervised open-domain QA systems. The code to reproduce our analysis is available at https://github.com/facebookresearch/LAMA.

0
5
下载
预览

We explore deep autoregressive Transformer models in language modeling for speech recognition. We focus on two aspects. First, we revisit Transformer model configurations specifically for language modeling. We show that well configured Transformer models outperform our baseline models based on the shallow stack of LSTM recurrent neural network layers. We carry out experiments on the open-source LibriSpeech 960hr task, for both 200K vocabulary word-level and 10K byte-pair encoding subword-level language modeling. We apply our word-level models to conventional hybrid speech recognition by lattice rescoring, and the subword-level models to attention based encoder-decoder models by shallow fusion. Second, we show that deep Transformer language models do not require positional encoding. The positional encoding is an essential augmentation for the self-attention mechanism which is invariant to sequence ordering. However, in autoregressive setup, as is the case for language modeling, the amount of information increases along the position dimension, which is a positional signal by its own. The analysis of attention weights shows that deep autoregressive self-attention models can automatically make use of such positional information. We find that removing the positional encoding even slightly improves the performance of these models.

0
5
下载
预览

The field of natural language processing has seen impressive progress in recent years, with neural network models replacing many of the traditional systems. A plethora of new models have been proposed, many of which are thought to be opaque compared to their feature-rich counterparts. This has led researchers to analyze, interpret, and evaluate neural networks in novel and more fine-grained ways. In this survey paper, we review analysis methods in neural language processing, categorize them according to prominent research trends, highlight existing limitations, and point to potential directions for future work.

0
4
下载
预览

Natural Language Inference (NLI) is fundamental to many Natural Language Processing (NLP) applications including semantic search and question answering. The NLI problem has gained significant attention thanks to the release of large scale, challenging datasets. Present approaches to the problem largely focus on learning-based methods that use only textual information in order to classify whether a given premise entails, contradicts, or is neutral with respect to a given hypothesis. Surprisingly, the use of methods based on structured knowledge -- a central topic in artificial intelligence -- has not received much attention vis-a-vis the NLI problem. While there are many open knowledge bases that contain various types of reasoning information, their use for NLI has not been well explored. To address this, we present a combination of techniques that harness knowledge graphs to improve performance on the NLI problem in the science questions domain. We present the results of applying our techniques on text, graph, and text-to-graph based models, and discuss implications for the use of external knowledge in solving the NLI problem. Our model achieves the new state-of-the-art performance on the NLI problem over the SciTail science questions dataset.

0
3
下载
预览

Artificial intelligence (AI) has undergone a renaissance recently, making major progress in key domains such as vision, language, control, and decision-making. This has been due, in part, to cheap data and cheap compute resources, which have fit the natural strengths of deep learning. However, many defining characteristics of human intelligence, which developed under much different pressures, remain out of reach for current approaches. In particular, generalizing beyond one's experiences--a hallmark of human intelligence from infancy--remains a formidable challenge for modern AI. The following is part position paper, part review, and part unification. We argue that combinatorial generalization must be a top priority for AI to achieve human-like abilities, and that structured representations and computations are key to realizing this objective. Just as biology uses nature and nurture cooperatively, we reject the false choice between "hand-engineering" and "end-to-end" learning, and instead advocate for an approach which benefits from their complementary strengths. We explore how using relational inductive biases within deep learning architectures can facilitate learning about entities, relations, and rules for composing them. We present a new building block for the AI toolkit with a strong relational inductive bias--the graph network--which generalizes and extends various approaches for neural networks that operate on graphs, and provides a straightforward interface for manipulating structured knowledge and producing structured behaviors. We discuss how graph networks can support relational reasoning and combinatorial generalization, laying the foundation for more sophisticated, interpretable, and flexible patterns of reasoning.

0
4
下载
预览
小贴士
相关论文
Oshin Agarwal,Ani Nenkova
0+阅读 · 11月24日
Yujia Qin,Yankai Lin,Ryuichi Takanobu,Zhiyuan Liu,Peng Li,Heng Ji,Minlie Huang,Maosong Sun,Jie Zhou
5+阅读 · 5月26日
Samuel Henrique Silva,Peyman Najafirad
3+阅读 · 2020年7月3日
Hangbo Bao,Li Dong,Furu Wei,Wenhui Wang,Nan Yang,Xiaodong Liu,Yu Wang,Songhao Piao,Jianfeng Gao,Ming Zhou,Hsiao-Wuen Hon
13+阅读 · 2020年2月28日
Fabio Petroni,Tim Rocktäschel,Patrick Lewis,Anton Bakhtin,Yuxiang Wu,Alexander H. Miller,Sebastian Riedel
5+阅读 · 2019年9月4日
Kazuki Irie,Albert Zeyer,Ralf Schlüter,Hermann Ney
5+阅读 · 2019年7月11日
Analysis Methods in Neural Language Processing: A Survey
Yonatan Belinkov,James Glass
4+阅读 · 2019年1月14日
Improving Natural Language Inference Using External Knowledge in the Science Questions Domain
Xiaoyan Wang,Pavan Kapanipathi,Ryan Musa,Mo Yu,Kartik Talamadupula,Ibrahim Abdelaziz,Maria Chang,Achille Fokoue,Bassem Makni,Nicholas Mattei,Michael Witbrock
3+阅读 · 2018年9月15日
Peter W. Battaglia,Jessica B. Hamrick,Victor Bapst,Alvaro Sanchez-Gonzalez,Vinicius Zambaldi,Mateusz Malinowski,Andrea Tacchetti,David Raposo,Adam Santoro,Ryan Faulkner,Caglar Gulcehre,Francis Song,Andrew Ballard,Justin Gilmer,George Dahl,Ashish Vaswani,Kelsey Allen,Charles Nash,Victoria Langston,Chris Dyer,Nicolas Heess,Daan Wierstra,Pushmeet Kohli,Matt Botvinick,Oriol Vinyals,Yujia Li,Razvan Pascanu
4+阅读 · 2018年6月4日
相关VIP内容
相关资讯
【论文笔记】通俗理解少样本文本分类 (Few-Shot Text Classification) (1)
深度学习自然语言处理
6+阅读 · 2020年4月8日
BERT/Transformer/迁移学习NLP资源大列表
专知
17+阅读 · 2019年6月9日
Hierarchically Structured Meta-learning
CreateAMind
12+阅读 · 2019年5月22日
A Technical Overview of AI & ML in 2018 & Trends for 2019
待字闺中
10+阅读 · 2018年12月24日
推荐|深度强化学习聊天机器人(附论文)!
全球人工智能
4+阅读 · 2018年1月30日
【推荐】直接未来预测:增强学习监督学习
机器学习研究会
6+阅读 · 2017年11月24日
【推荐】自然语言处理(NLP)指南
机器学习研究会
33+阅读 · 2017年11月17日
【学习】Hierarchical Softmax
机器学习研究会
3+阅读 · 2017年8月6日
强化学习 cartpole_a3c
CreateAMind
9+阅读 · 2017年7月21日
Top