We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models, 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).

BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

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).

Data Mining - Concepts and Techniques.

Recent progress in natural language processing has been driven by advances in both model architecture and model pretraining. Transformer architectures have facilitated building higher-capacity models and pretraining has made it possible to effectively utilize this capacity for a wide variety of tasks. Transformers is an open-source library with the goal of opening up these advances to the wider machine learning community. The library consists of carefully engineered state-of-the art Transformer architectures under a unified API. Backing this library is a curated collection of pretrained models made by and available for the community. Transformers is designed to be extensible by researchers, simple for practitioners, and fast and robust in industrial deployments. The library is available at https://github.com/huggingface/transformers.

/pdf/transformers-state-of-the-art-natural-language-processing-1zozhnrntv.pdf

Transformers: State-of-the-Art Natural Language Processing

Recent progress in natural language processing has been driven by advances in both model architecture and model pretraining. Transformer architectures have facilitated building higher-capacity models and pretraining has made it possible to effectively utilize this capacity for a wide variety of tasks. \textit{Transformers} is an open-source library with the goal of opening up these advances to the wider machine learning community. The library consists of carefully engineered state-of-the art Transformer architectures under a unified API. Backing this library is a curated collection of pretrained models made by and available for the community. \textit{Transformers} is designed to be extensible by researchers, simple for practitioners, and fast and robust in industrial deployments. The library is available at \url{this https URL}.

HuggingFace's Transformers: State-of-the-art Natural Language Processing.

Recent advances in language modeling using recurrent neural networks have made it viable to model language as distributions over characters. By learning to predict the next character on the basis of previous characters, such models have been shown to automatically internalize linguistic concepts such as words, sentences, subclauses and even sentiment. In this paper, we propose to leverage the internal states of a trained character language model to produce a novel type of word embedding which we refer to as contextual string embeddings. Our proposed embeddings have the distinct properties that they (a) are trained without any explicit notion of words and thus fundamentally model words as sequences of characters, and (b) are contextualized by their surrounding text, meaning that the same word will have different embeddings depending on its contextual use. We conduct a comparative evaluation against previous embeddings and find that our embeddings are highly useful for downstream tasks: across four classic sequence labeling tasks we consistently outperform the previous state-of-the-art. In particular, we significantly outperform previous work on English and German named entity recognition (NER), allowing us to report new state-of-the-art F1-scores on the CoNLL03 shared task. We release all code and pre-trained language models in a simple-to-use framework to the research community, to enable reproduction of these experiments and application of our proposed embeddings to other tasks: https://github.com/zalandoresearch/flair

Contextual String Embeddings for Sequence Labeling

We present FLAIR, an NLP framework designed to facilitate training and distribution of state-of-the-art sequence labeling, text classification and language models. The core idea of the framework is to present a simple, unified interface for conceptually very different types of word and document embeddings. This effectively hides all embedding-specific engineering complexity and allows researchers to “mix and match” various embeddings with little effort. The framework also implements standard model training and hyperparameter selection routines, as well as a data fetching module that can download publicly available NLP datasets and convert them into data structures for quick set up of experiments. Finally, FLAIR also ships with a “model zoo” of pre-trained models to allow researchers to use state-of-the-art NLP models in their applications. This paper gives an overview of the framework and its functionality. The framework is available on GitHub at https://github.com/zalandoresearch/flair .

FLAIR: An Easy-to-Use Framework for State-of-the-Art NLP

Contextual string embeddings are a recent type of contextualized word embedding that were shown to yield state-of-the-art results when utilized in a range of sequence labeling tasks. They are based on character-level language models which treat text as distributions over characters and are capable of generating embeddings for any string of characters within any textual context. However, such purely character-based approaches struggle to produce meaningful embeddings if a rare string is used in a underspecified context. To address this drawback, we propose a method in which we dynamically aggregate contextualized embeddings of each unique string that we encounter. We then use a pooling operation to distill a ”global” word representation from all contextualized instances. We evaluate these ”pooled contextualized embeddings” on common named entity recognition (NER) tasks such as CoNLL-03 and WNUT and show that our approach significantly improves the state-of-the-art for NER. We make all code and pre-trained models available to the research community for use and reproduction.

Pooled Contextualized Embeddings for Named Entity Recognition.

Semantic role labeling (SRL) is crucial to natural language understanding as it identifies the predicate-argument structure in text with semantic labels. Unfortunately, resources required to construct SRL models are expensive to obtain and simply do not exist for most languages. In this paper, we present a two-stage method to enable the construction of SRL models for resourcepoor languages by exploiting monolingual SRL and multilingual parallel data. Experimental results show that our method outperforms existing methods. We use our method to generate Proposition Banks with high to reasonable quality for 7 languages in three language families and release these resources to the research community.

Generating High Quality Proposition Banks for Multilingual Semantic Role Labeling

Current techniques for Open Information Extraction (OIE) focus on the extraction of binary facts and suffer significant quality loss for the task of extracting higher order N-ary facts. This quality loss may not only affect the correctness, but also the completeness of an extracted fact. We present KrakeN, an OIE system specifically designed to capture N-ary facts, as well as the results of an experimental study on extracting facts from Web text in which we examine the issue of fact completeness. Our preliminary experiments indicate that KrakeN is a high precision OIE approach that captures more facts per sentence at greater completeness than existing OIE approaches, but is vulnerable to noisy and ungrammatical text.

Alan Akbik

Papers

Contextual String Embeddings for Sequence Labeling

FLAIR: An Easy-to-Use Framework for State-of-the-Art NLP

Pooled Contextualized Embeddings for Named Entity Recognition.

Generating High Quality Proposition Banks for Multilingual Semantic Role Labeling

KrakeN: N-ary Facts in Open Information Extraction