Data augmentation is an important component in the robustness evaluation of models in natural language processing (NLP) and in enhancing the diversity of the data they are trained on. In this paper, we present NL-Augmenter, a new participatory Python-based natural language augmentation framework which supports the creation of both transformations (modifications to the data) and filters (data splits according to specific features). We describe the framework and an initial set of 117 transformations and 23 filters for a variety of natural language tasks. We demonstrate the efficacy of NL-Augmenter by using several of its transformations to analyze the robustness of popular natural language models. The infrastructure, datacards and robustness analysis results are available publicly on the NL-Augmenter repository (\url{https://github.com/GEM-benchmark/NL-Augmenter}).

Artificial Intelligence (AI) in Education has been said to have the potential for building more personalised curricula, as well as democratising education worldwide and creating a Renaissance of new ways of teaching and learning. Millions of students are already starting to benefit from the use of these technologies, but millions more around the world are not. If this trend continues, the first delivery of AI in Education could be greater educational inequality, along with a global misallocation of educational resources motivated by the current technological determinism narrative. In this paper, we focus on speculating and posing questions around the future of AI in Education, with the aim of starting the pressing conversation that would set the right foundations for the new generation of education that is permeated by technology. This paper starts by synthesising how AI might change how we learn and teach, focusing specifically on the case of personalised learning companions, and then move to discuss some socio-technical features that will be crucial for avoiding the perils of these AI systems worldwide (and perhaps ensuring their success). This paper also discusses the potential of using AI together with free, participatory and democratic resources, such as Wikipedia, Open Educational Resources and open-source tools. We also emphasise the need for collectively designing human-centered, transparent, interactive and collaborative AI-based algorithms that empower and give complete agency to stakeholders, as well as support new emerging pedagogies. Finally, we ask what would it take for this educational revolution to provide egalitarian and empowering access to education, beyond any political, cultural, language, geographical and learning ability barriers.

This work applies Minimum Bayes Risk (MBR) decoding to optimize diverse automated metrics of translation quality. Automatic metrics in machine translation have made tremendous progress recently. In particular, neural metrics, fine-tuned on human ratings (e.g. BLEURT, or COMET) are outperforming surface metrics in terms of correlations to human judgements. Our experiments show that the combination of a neural translation model with a neural reference-based metric, BLEURT, results in significant improvement in automatic and human evaluations. This improvement is obtained with translations different from classical beam-search output: these translations have much lower likelihood and are less favored by surface metrics like BLEU.

Let's be honest, all language learners have turned to Google Translate to brush up on vocabulary, verify their work, or complete a class assignment. We probably lean a little too much on the application, at least according to many language teachers, considering the inherent faults and bias can be found in the translated phrases. Countless videos and articles have been uploaded to the internet showing how a few simple English sentences were mangled after running them through the translator like the worlds most convoluted game of telephone. Yet, the convenience of Google's online translator never fails to draw us back. One source of faults between language translations arise from a globally common history of male-dominated society and is further exacerbated by the recent movement toward more inclusive language for gender nonconforming individuals.

The Conference on Empirical Methods in Natural Language Processing (EMNLP 2021) took place from the 7th to the 11th of November both in Punta Cana and online. If you did not have time to check the papers and the keynotes at the main conference, here are the livetweeted keynotes and papers sorted by language. Live Notes of EMNLP 2021 #EMNLP2021 Keynote by Ido Dagan on 3 directions that #NLProc should pursue: https://t.co/LLeBjcffOP At #EMNLP2021 Evelina Fedorenko makes a strong case to defuse criticism that neural language models cannot "think". Neither can the human language modules in the brain, she argues, based on human brain studies.

There is a tendency across different subfields in AI to valorize a small collection of influential benchmarks. These benchmarks operate as stand-ins for a range of anointed common problems that are frequently framed as foundational milestones on the path towards flexible and generalizable AI systems. State-of-the-art performance on these benchmarks is widely understood as indicative of progress towards these long-term goals. In this position paper, we explore the limits of such benchmarks in order to reveal the construct validity issues in their framing as the functionally "general" broad measures of progress they are set up to be.

Recently many studies have been conducted on the topic of relation extraction. The DrugProt track at BioCreative VII provides a manually-annotated corpus for the purpose of the development and evaluation of relation extraction systems, in which interactions between chemicals and genes are studied. We describe the ensemble system that we used for our submission, which combines predictions of fine-tuned bioBERT, sciBERT and const-bioBERT models by majority voting. We specifically tested the contribution of syntactic information to relation extraction with BERT. We observed that adding constituentbased syntactic information to BERT improved precision, but decreased recall, since relations rarely seen in the train set were less likely to be predicted by BERT models in which the syntactic information is infused. Our code is available online [https://github.com/Maple177/drugprot-relation-extraction].

Let the OSS Enterprise newsletter guide your open source journey! Microsoft this week announced Tutel, a library to support the development of mixture of experts (MoE) models -- a particular type of large-scale AI model. Tutel, which is open source and has been integrated into fairseq, one of Facebook's toolkits in PyTorch, is designed to enable developers across AI disciplines to "execute MoE more easily and efficiently," Microsoft says. MoE are made up of small clusters of "neurons" that are only active under special, specific circumstances. Lower "layers" of the MoE model extract features and experts are called upon to evaluate those features.

We have many public platforms and social media platforms for communications, exchange/share of information, expressing feelings, etc… There are many state-of-the-art NLP tasks that run on the text data available on these public or social media platforms, but the test data is not up to the distribution of standard English language which affects the performance of the said tasks. So here we take the input sentence which is corrupted and project it to the target sentence which is in the distribution of standard English. By using this we can improve the performance of most NLP tasks. Input sentences will have corruption and we convert it into standard English while preserving the semantic meaning of the sentences. As mentioned in the research paper, we will be using Sequence cross-entropy (Categorical cross-entropy) as our loss function, where we sum over cross-entropy loss at each time step in predicting the character for the current time step.

Next, we introduced a new bridge mining strategy, in which we group languages into 14 language groups based on linguistic classification, geography, and cultural similarities. People living in countries with languages of the same family tend to communicate more often and would benefit from high-quality translations. For instance, one group would include languages spoken in India, like Bengali, Hindi, Marathi, Nepali, Tamil, and Urdu. To connect the languages of different groups, we identified a small number of bridge languages, which are usually one to three major languages of each group. In the example above, Hindi, Bengali, and Tamil would be bridge languages for Indo-Aryan languages.