BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
11 Oct 2018-pp 4171-4186
TL;DR: BERT as mentioned in this paper pre-trains deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.
Abstract: We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models (Peters et al., 2018a; Radford et al., 2018), BERT is designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial task-specific architecture modifications. BERT is conceptually simple and empirically powerful. It obtains new state-of-the-art results on eleven natural language processing tasks, including pushing the GLUE score to 80.5 (7.7 point absolute improvement), MultiNLI accuracy to 86.7% (4.6% absolute improvement), SQuAD v1.1 question answering Test F1 to 93.2 (1.5 point absolute improvement) and SQuAD v2.0 Test F1 to 83.1 (5.1 point absolute improvement).
Citations
More filters
Posted Content•
TL;DR: This article explored the suitability of self-attention models for character-level NMT and proposed a novel variant in which the encoder block combines information from nearby characters using convolutions.
Abstract: We explore the suitability of self-attention models for character-level neural machine translation. We test the standard transformer model, as well as a novel variant in which the encoder block combines information from nearby characters using convolutions. We perform extensive experiments on WMT and UN datasets, testing both bilingual and multilingual translation to English using up to three input languages (French, Spanish, and Chinese). Our transformer variant consistently outperforms the standard transformer at the character-level and converges faster while learning more robust character-level alignments.
6 citations
TL;DR: This paper explored how to incorporate structured domain knowledge, available in the form of a knowledge graph (UMLS), for the Medical NLI task, and fusing the domain-specific sentiment information for the task.
Abstract: Recently, biomedical version of embeddings obtained from language models such as BioELMo have shown state-of-the-art results for the textual inference task in the medical domain. In this paper, we explore how to incorporate structured domain knowledge, available in the form of a knowledge graph (UMLS), for the Medical NLI task. Specifically, we experiment with fusing embeddings obtained from knowledge graph with the state-of-the-art approaches for NLI task (ESIM model). We also experiment with fusing the domain-specific sentiment information for the task. Experiments conducted on MedNLI dataset clearly show that this strategy improves the baseline BioELMo architecture for the Medical NLI task.
6 citations
Proceedings Article•
03 May 2021TL;DR: The authors showed that while selective classification can improve average accuracies, it can simultaneously magnify existing accuracy disparities between various groups within a population, especially in the presence of spurious correlations and showed that increasing the abstention rate can even decrease accuracies on some groups.
Abstract: Selective classification, in which models are allowed to abstain on uncertain predictions, is a natural approach to improving accuracy in settings where errors are costly but abstentions are manageable In this paper, we find that while selective classification can improve average accuracies, it can simultaneously magnify existing accuracy disparities between various groups within a population, especially in the presence of spurious correlations We observe this behavior consistently across five datasets from computer vision and NLP Surprisingly, increasing the abstention rate can even decrease accuracies on some groups To better understand when selective classification improves or worsens accuracy on a group, we study its margin distribution, which captures the model’s confidences over all predictions For example, when the margin distribution is symmetric, we prove that whether selective classification monotonically improves or worsens accuracy is fully determined by the accuracy at full coverage (ie, without any abstentions) and whether the distribution satisfies a property we term left-log-concavity Our analysis also shows that selective classification tends to magnify accuracy disparities that are present at full coverage Fortunately, we find that it uniformly improves each group when applied to distributionally-robust models that achieve similar full-coverage accuracies across groups Altogether, our results imply selective classification should be used with care and underscore the importance of models that perform equally well across groups at full coverage
6 citations
Posted Content•
30 Apr 2020
TL;DR: A segment-aware BERT is proposed, by replacing the token position embedding of Transformer with a combination of paragraph index, sentence index, and token index embeddings, and Experimental results show that the pre-trained model can outperform the original BERT model on various NLP tasks.
Abstract: Pre-trained language models have achieved state-of-the-art results in various natural language processing tasks. Most of them are based on the Transformer architecture, which distinguishes tokens with the token position index of the input sequence. However, sentence index and paragraph index are also important to indicate the token position in a document. We hypothesize that better contextual representations can be generated from the text encoder with richer positional information. To verify this, we propose a segment-aware BERT, by replacing the token position embedding of Transformer with a combination of paragraph index, sentence index, and token index embeddings. We pre-trained the SegaBERT on the masked language modeling task in BERT but without any affiliated tasks. Experimental results show that our pre-trained model can outperform the original BERT model on various NLP tasks.
6 citations
Posted Content•
TL;DR: The authors used external fine-tuned word representations and DeepMoji sentence representations for emotion detection in textual conversations in SemEval-2019 and achieved good performance with a micro-F1 score of 0.7463.
Abstract: In this paper we present our model on the task of emotion detection in textual conversations in SemEval-2019. Our model extends the Recurrent Convolutional Neural Network (RCNN) by using external fine-tuned word representations and DeepMoji sentence representations. We also explored several other competitive pre-trained word and sentence representations including ELMo, BERT and InferSent but found inferior performance. In addition, we conducted extensive sensitivity analysis, which empirically shows that our model is relatively robust to hyper-parameters. Our model requires no handcrafted features or emotion lexicons but achieved good performance with a micro-F1 score of 0.7463.
6 citations
References
More filters
Proceedings Article•
12 Jun 2017TL;DR: This paper proposed a simple network architecture based solely on an attention mechanism, dispensing with recurrence and convolutions entirely and achieved state-of-the-art performance on English-to-French translation.
Abstract: The dominant sequence transduction models are based on complex recurrent orconvolutional neural networks in an encoder and decoder configuration. The best performing such models also connect the encoder and decoder through an attentionm echanisms. We propose a novel, simple network architecture based solely onan attention mechanism, dispensing with recurrence and convolutions entirely.Experiments on two machine translation tasks show these models to be superiorin quality while being more parallelizable and requiring significantly less timeto train. Our single model with 165 million parameters, achieves 27.5 BLEU onEnglish-to-German translation, improving over the existing best ensemble result by over 1 BLEU. On English-to-French translation, we outperform the previoussingle state-of-the-art with model by 0.7 BLEU, achieving a BLEU score of 41.1.
52,856 citations
20 Jun 2009
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Abstract: The explosion of image data on the Internet has the potential to foster more sophisticated and robust models and algorithms to index, retrieve, organize and interact with images and multimedia data. But exactly how such data can be harnessed and organized remains a critical problem. We introduce here a new database called “ImageNet”, a large-scale ontology of images built upon the backbone of the WordNet structure. ImageNet aims to populate the majority of the 80,000 synsets of WordNet with an average of 500-1000 clean and full resolution images. This will result in tens of millions of annotated images organized by the semantic hierarchy of WordNet. This paper offers a detailed analysis of ImageNet in its current state: 12 subtrees with 5247 synsets and 3.2 million images in total. We show that ImageNet is much larger in scale and diversity and much more accurate than the current image datasets. Constructing such a large-scale database is a challenging task. We describe the data collection scheme with Amazon Mechanical Turk. Lastly, we illustrate the usefulness of ImageNet through three simple applications in object recognition, image classification and automatic object clustering. We hope that the scale, accuracy, diversity and hierarchical structure of ImageNet can offer unparalleled opportunities to researchers in the computer vision community and beyond.
49,639 citations
01 Oct 2014
TL;DR: A new global logbilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods and produces a vector space with meaningful substructure.
Abstract: Recent methods for learning vector space representations of words have succeeded in capturing fine-grained semantic and syntactic regularities using vector arithmetic, but the origin of these regularities has remained opaque. We analyze and make explicit the model properties needed for such regularities to emerge in word vectors. The result is a new global logbilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods. Our model efficiently leverages statistical information by training only on the nonzero elements in a word-word cooccurrence matrix, rather than on the entire sparse matrix or on individual context windows in a large corpus. The model produces a vector space with meaningful substructure, as evidenced by its performance of 75% on a recent word analogy task. It also outperforms related models on similarity tasks and named entity recognition.
30,558 citations
Proceedings Article•
05 Dec 2013TL;DR: This paper presents a simple method for finding phrases in text, and shows that learning good vector representations for millions of phrases is possible and describes a simple alternative to the hierarchical softmax called negative sampling.
Abstract: The recently introduced continuous Skip-gram model is an efficient method for learning high-quality distributed vector representations that capture a large number of precise syntactic and semantic word relationships. In this paper we present several extensions that improve both the quality of the vectors and the training speed. By subsampling of the frequent words we obtain significant speedup and also learn more regular word representations. We also describe a simple alternative to the hierarchical softmax called negative sampling.
An inherent limitation of word representations is their indifference to word order and their inability to represent idiomatic phrases. For example, the meanings of "Canada" and "Air" cannot be easily combined to obtain "Air Canada". Motivated by this example, we present a simple method for finding phrases in text, and show that learning good vector representations for millions of phrases is possible.
24,012 citations
15 Feb 2018
TL;DR: This paper introduced a new type of deep contextualized word representation that models both complex characteristics of word use (e.g., syntax and semantics), and how these uses vary across linguistic contexts (i.e., to model polysemy).
Abstract: We introduce a new type of deep contextualized word representation that models both (1) complex characteristics of word use (e.g., syntax and semantics), and (2) how these uses vary across linguistic contexts (i.e., to model polysemy). Our word vectors are learned functions of the internal states of a deep bidirectional language model (biLM), which is pre-trained on a large text corpus. We show that these representations can be easily added to existing models and significantly improve the state of the art across six challenging NLP problems, including question answering, textual entailment and sentiment analysis. We also present an analysis showing that exposing the deep internals of the pre-trained network is crucial, allowing downstream models to mix different types of semi-supervision signals.
7,412 citations