In this paper, our main contributions are that embeddings from relatively smaller corpora can outperform ones from larger corpora and we make the new Swedish analogy test set publicly available. To achieve a good network performance in natural language processing (NLP) downstream tasks, several factors play important roles: dataset size, the right hyper-parameters, and well-trained embeddings. We show that, with the right set of hyper-parameters, good network performance can be reached even on smaller datasets. We evaluate the embeddings at both the intrinsic and extrinsic levels. The embeddings are deployed with the Transformer in named entity recognition (NER) task and significance tests conducted. This is done for both Swedish and English. We obtain better performance in both languages on the downstream task with smaller training data, compared to recently released, Common Crawl versions; and character n-grams appear useful for Swedish, a morphologically rich language.
Synapse Développement（Synapse发展公司）；IRIT, Université Paul Sabatier（保罗·萨巴捷大学IRIT研究所）
We present our system for the CAp 2017 NER challenge which is about named entity recognition on French tweets. Our system leverages unsupervised learning on a larger dataset of French tweets to learn features feeding a CRF model. It was ranked first without using any gazetteer or structured external data, with an F-measure of 58.89\%. To the best of our knowledge, it is the first system to use fasttext embeddings (which include subword representations) and an embedding-based sentence representation for NER.
This paper introduces the Swedish BERT ("KB-BERT") developed by the KBLab for data-driven research at the National Library of Sweden (KB). Building on recent efforts to create transformer-based BERT models for languages other than English, we explain how we used KB's collections to create and train a new language-specific BERT model for Swedish. We also present the results of our model in comparison with existing models - chiefly that produced by the Swedish Public Employment Service, Arbetsförmedlingen, and Google's multilingual M-BERT - where we demonstrate that KB-BERT outperforms these in …
Traditional text classification techniques in clinical domain have heavily relied on the manually extracted textual cues. This paper proposes a generally supervised machine learning method that is equally hassle-free and does not use clinical knowledge. The employed methods were simple to implement, fast to run and yet effective. This paper proposes a novel named entity recognition (NER) based an ensemble system capable of learning the keyword features in the document. Instead of merely considering the whole sentence/paragraph for analysis, the NER based keyword features can stress the importa…
Voice-assistants text classification and named-entity recognition (NER) models are trained on millions of example utterances. Because of the large datasets, long training time is one of the bottlenecks for releasing improved models. In this work, we develop F10-SGD, a fast optimizer for text classification and NER elastic-net linear models. On internal datasets, F10-SGD provides 4x reduction in training time compared to the OWL-QN optimizer without loss of accuracy or increase in model size. Furthermore, we incorporate biased sampling that prioritizes harder examples towards the end of the tra…
Language models are notoriously difficult to evaluate. We release SuperSim, a large-scale similarity and relatedness test set for Swedish built with expert human judgments. The test set is composed of 1,360 word-pairs independently judged for both relatedness and similarity by five annotators. We evaluate three different models (Word2Vec, fastText, and GloVe) trained on two separate Swedish datasets, namely the Swedish Gigaword corpus and a Swedish Wikipedia dump, to provide a baseline for future comparison. We release the fully annotated test set, code, baseline models, and data.
Indian Institute of Technology Guwahati（印度理工学院古瓦哈提分校）
We present the AsNER, a named entity annotation dataset for low resource Assamese language with a baseline Assamese NER model. The dataset contains about 99k tokens comprised of text from the speech of the Prime Minister of India and Assamese play. It also contains person names, location names and addresses. The proposed NER dataset is likely to be a significant resource for deep neural based Assamese language processing. We benchmark the dataset by training NER models and evaluating using state-of-the-art architectures for supervised named entity recognition (NER) such as Fasttext, BERT, XLM-…
A number of morphology-based word embedding models were introduced in recent years. However, their evaluation was mostly limited to English, which is known to be a morphologically simple language. In this paper, we explore whether and to what extent incorporating morphology into word embeddings improves performance on downstream NLP tasks, in the case of morphologically rich Russian language. NLP tasks of our choice are POS tagging, Chunking, and NER -- for Russian language, all can be mostly solved using only morphology without understanding the semantics of words. Our experiments show that m…
National Library of Finland, Centre for Preservation and Digitization（芬兰国家图书馆，保存与数字化中心）；Aalto University, Semantic Computing Research Group（阿尔托大学，语义计算研究组）；University of Helsinki, Department of Modern Languages（赫尔辛基大学，现代语言系）；Department of Linguistics and English Language, Lancaster University（兰卡斯特大学，语言学与英语语言系）
Named Entity Recognition (NER), search, classification and tagging of names and name like frequent informational elements in texts, has become a standard information extraction procedure for textual data. NER has been applied to many types of texts and different types of entities: newspapers, fiction, historical records, persons, locations, chemical compounds, protein families, animals etc. In general a NER system's performance is genre and domain dependent and also used entity categories vary (Nadeau and Sekine, 2007). The most general set of named entities is usually some version of three pa…
University of Ljubljana, Faculty of Computer and Information Science（卢布尔雅那大学计算机与信息科学学院）
Recent results show that deep neural networks using contextual embeddings significantly outperform non-contextual embeddings on a majority of text classification task. We offer precomputed embeddings from popular contextual ELMo model for seven languages: Croatian, Estonian, Finnish, Latvian, Lithuanian, Slovenian, and Swedish. We demonstrate that the quality of embeddings strongly depends on the size of training set and show that existing publicly available ELMo embeddings for listed languages shall be improved. We train new ELMo embeddings on much larger training sets and show their advantag…
University of Ljubljana（卢布尔雅那大学）；University of Helsinki（赫尔辛基大学）；University of Tartu（塔尔图大学）；University of Latvia（拉脱维亚大学）
In text processing, deep neural networks mostly use word embeddings as an input. Embeddings have to ensure that relations between words are reflected through distances in a high-dimensional numeric space. To compare the quality of different text embeddings, typically, we use benchmark datasets. We present a collection of such datasets for the word analogy task in nine languages: Croatian, English, Estonian, Finnish, Latvian, Lithuanian, Russian, Slovenian, and Swedish. We redesigned the original monolingual analogy task to be much more culturally independent and also constructed cross-lingual …
Bayerische Staatsbibliothek München（慕尼黑巴伐利亚州立图书馆）；University of Vienna（维也纳大学）；Volkswagen AG（大众汽车集团）
Compared to standard Named Entity Recognition (NER), identifying persons, locations, and organizations in historical texts constitutes a big challenge. To obtain machine-readable corpora, the historical text is usually scanned and Optical Character Recognition (OCR) needs to be performed. As a result, the historical corpora contain errors. Also, entities like location or organization can change over time, which poses another challenge. Overall, historical texts come with several peculiarities that differ greatly from modern texts and large labeled corpora for training a neural tagger are hardl…
University of the Basque Country (UPV/EHU)（巴斯克大学（UPV/EHU））；Elhuyar Foundation（埃尔胡亚基金会）
Word embeddings and pre-trained language models allow to build rich representations of text and have enabled improvements across most NLP tasks. Unfortunately they are very expensive to train, and many small companies and research groups tend to use models that have been pre-trained and made available by third parties, rather than building their own. This is suboptimal as, for many languages, the models have been trained on smaller (or lower quality) corpora. In addition, monolingual pre-trained models for non-English languages are not always available. At best, models for those languages are …
