We introduce Biomedical Event Extraction as Sequence Labeling (BeeSL), a joint end-to-end neural information extraction model.
Automatically detecting the intent of an utterance is important for various downstream natural language processing tasks.
Various historical languages, which used to be lingua franca of science and arts, deserve the attention of current NLP research.
For low-resource syntactic tasks, we observe impacts of segment embedding and multilingual BERT choice.
1 code implementation • • Rob van der Goot, Alan Ramponi, Arkaitz Zubiaga, Barbara Plank, Benjamin Muller, Iñaki San Vicente Roncal, Nikola Ljubešić, Özlem Çetinoğlu, Rahmad Mahendra, Talha Çolakoğlu, Timothy Baldwin, Tommaso Caselli, Wladimir Sidorenko
This task is beneficial for downstream analysis, as it provides a way to harmonize (often spontaneous) linguistic variation.
Existing models for language identification in code-switched data are all supervised, requiring annotated training data which is only available for a limited number of language pairs.
However, the introduction of neural networks in NLP has led to a different use of these standard splits; the development set is now often used for model selection during the training procedure.
With the COVID-19 pandemic raging world-wide since the beginning of the 2020 decade, the need for monitoring systems to track relevant information on social media is vitally important.
The best single source treebank (nl_alpino) resulted in an LAS of 54. 7 whereas our data selection outperformed the single best transfer treebank and led to 55. 6 LAS on the test data.
Aggregated data obtained from job postings provide powerful insights into labor market demands, and emerging skills, and aid job matching.
Making an informed choice of pre-trained language model (LM) is critical for performance, yet environmentally costly, and as such widely underexplored.
The field of Deep Learning (DL) has undergone explosive growth during the last decade, with a substantial impact on Natural Language Processing (NLP) as well.
Recent work has shown that monolingual masked language models learn to represent data-driven notions of language variation which can be used for domain-targeted training data selection.
We examine language-specific versus multilingual BERT, and study the effect of lexical normalization on NER.
To tackle the challenge, we propose a joint learning approach, with English SLU training data and non-English auxiliary tasks from raw text, syntax and translation for transfer.
Lexical normalization, the translation of non-canonical data to standard language, has shown to improve the performance of many natural language processing tasks on social media.
However, it remains unclear in which situations these dataset embeddings are most effective, because they are used in a large variety of settings, languages and tasks.
This paper explores the difficulties of annotating transcribed spoken Dutch-Frisian code-switch utterances into Universal Dependencies.
Lexical normalization, the translation of non-canonical data to standard language, has shown to improve the performance of manynatural language processing tasks on social media.
Analogies such as man is to king as woman is to X are often used to illustrate the amazing power of word embeddings.
In this paper we present MaChAmp, a toolkit for easy fine-tuning of contextualized embeddings in multi-task settings.
However, for Italian, there is no benchmark available for lexical normalization, despite the presence of many benchmarks for other tasks involving social media data.
With this system, we score 94. 29 accuracy on the test data, compared to 95. 22 when it is trained on human-annotated data.
Existing natural language processing systems have often been designed with standard texts in mind.
This paper describes our submission to SIGMORPHON 2019 Task 2: Morphological analysis and lemmatization in context.
In this paper, we introduce and demonstrate the online demo as well as the command line interface of a lexical normalization system (MoNoise) for a variety of languages.
In this paper, we present our approach to detection of hate speech against women and immigrants in tweets for our participation in the SemEval-2019 Task 5.
However, beside the intrinsic problems with the analogy task as a bias detection tool, in this paper we show that a series of issues related to how analogies have been implemented and used might have yielded a distorted picture of bias in word embeddings.
Recently introduced neural network parsers allow for new approaches to circumvent data sparsity issues by modeling character level information and by exploiting raw data in a semi-supervised setting.
Gender prediction has typically focused on lexical and social network features, yielding good performance, but making systems highly language-, topic-, and platform-dependent.
We show that MoNoise beats the state-of-the-art on different normalization benchmarks for English and Dutch, which all define the task of normalization slightly different.
Ranked #1 on Lexical Normalization on LexNorm
We introduce the Denoised Web Treebank: a treebank including a normalization layer and a corresponding evaluation metric for dependency parsing of noisy text, such as Tweets.