Advances in innovation to capture and process a lot of data have left us suffocating in information. This makes it hard to extricate insights from data at the rate we get it. This is the place where machine learning offers some benefit to a digital business. We need strategies to improve machine learning performance all the more effectively. Since, supposing that we put forth efforts in the wrong direction, we can't get a lot of progress and burn through a lot of time.
One of the most crucial preprocessing steps in any machine learning project is feature encoding. It is the process of turning categorical data in a dataset into numerical data. It is essential that we perform feature encoding because most machine learning models can only interpret numerical data and not data in text form. As usual, I will demonstrate these concepts through a practical case study using the students' performance in exams dataset on Kaggle. You can find the complete notebook up on my GitHub here.
Khashabi, Daniel, Cohan, Arman, Shakeri, Siamak, Hosseini, Pedram, Pezeshkpour, Pouya, Alikhani, Malihe, Aminnaseri, Moin, Bitaab, Marzieh, Brahman, Faeze, Ghazarian, Sarik, Gheini, Mozhdeh, Kabiri, Arman, Mahabadi, Rabeeh Karimi, Memarrast, Omid, Mosallanezhad, Ahmadreza, Noury, Erfan, Raji, Shahab, Rasooli, Mohammad Sadegh, Sadeghi, Sepideh, Azer, Erfan Sadeqi, Samghabadi, Niloofar Safi, Shafaei, Mahsa, Sheybani, Saber, Tazarv, Ali, Yaghoobzadeh, Yadollah
Despite the progress made in recent years in addressing natural language understanding (NLU) challenges, the majority of this progress remains to be concentrated on resource-rich languages like English. This work focuses on Persian language, one of the widely spoken languages in the world, and yet there are few NLU datasets available for this rich language. The availability of high-quality evaluation datasets is a necessity for reliable assessment of the progress on different NLU tasks and domains. We introduce ParsiNLU, the first benchmark in Persian language that includes a range of high-level tasks -- Reading Comprehension, Textual Entailment, etc. These datasets are collected in a multitude of ways, often involving manual annotations by native speakers. This results in over 14.5$k$ new instances across 6 distinct NLU tasks. Besides, we present the first results on state-of-the-art monolingual and multi-lingual pre-trained language-models on this benchmark and compare them with human performance, which provides valuable insights into our ability to tackle natural language understanding challenges in Persian. We hope ParsiNLU fosters further research and advances in Persian language understanding.
The AI and ML deployments are well underway, but for CXOs the biggest issue will be managing these initiatives, and figuring out where the data science team fits in and what algorithms to buy versus build. IBM said it is adding reading comprehension, the ability to extract information from FAQ documents, support for new languages and intent classification models to Watson. The new features outlined by IBM are designed to advance natural language processing and make it a bigger part of automation workflows. IBM has been looking to distinguish Watson with its natural language processing research efforts. For instance, IBM recently said it is commercializing its Project Debater technology that enables artificial intelligence to debate humans and handle complex topics.
Machine Learning has seen tremendous growth recently, which has led to a larger adoption of ML systems for educational assessments, credit risk, healthcare, employment, criminal justice, to name a few. Trustworthiness of ML and NLP systems is a crucial aspect and requires guarantee that the decisions they make are fair and robust. Aligned with this, we propose a framework GYC, to generate a set of counterfactual text samples, which are crucial for testing these ML systems. Our main contributions include a) We introduce GYC, a framework to generate counterfactual samples such that the generation is plausible, diverse, goal-oriented, and effective, b) We generate counterfactual samples, that can direct the generation towards a corresponding condition such as named-entity tag, semantic role label, or sentiment. Our experimental results on various domains show that GYC generates counterfactual text samples exhibiting the above four properties. %The generated counterfactuals can then be fed complementary to the existing data augmentation for improving the debiasing algorithms performance as compared to existing counterfactuals generated by token substitution. GYC generates counterfactuals that can act as test cases to evaluate a model and any text debiasing algorithm.
Multi-choice Machine Reading Comprehension (MRC) is a major and challenging form of MRC tasks that requires model to select the most appropriate answer from a set of candidates given passage and question. Most of the existing researches focus on the modeling of the task datasets without explicitly referring to external fine-grained commonsense sources, which is a well-known challenge in multi-choice tasks. Thus we propose a novel reference-based knowledge enhancement model based on span extraction called Reference Knowledgeable Network (RekNet), which simulates human reading strategy to refine critical information from the passage and quote external knowledge in necessity. In detail, RekNet refines fine-grained critical information and defines it as Reference Span, then quotes external knowledge quadruples by the co-occurrence information of Reference Span and answer options. Our proposed method is evaluated on two multi-choice MRC benchmarks: RACE and DREAM, which shows remarkable performance improvement with observable statistical significance level over strong baselines.
Optimizing AI and Deep Learning Performance Sven Breuner (DesignRage/Shutterstock) As AI and deep learning uses skyrocket, organizations are finding they are running these systems on similar resource as they do with high-performance computing (HPC) systems – and wondering if this is the path to peak efficiency. Ostensibly AI and HPC architectures have a lot in common, as AI has evolved into even more data-intensive machine learning (ML) and deep learning (DL) domains (Figure 1). Workloads often require multiple GPU systems as a cluster, and share those systems in a coordinated way among multiple data scientists. Secondly, both AI and HPC workloads require shared access to data at a high level of performance and communicate over a fast RDMA-enabled network. Especially in scientific research, the classic HPC systems nowadays tend to have GPUs added to the compute nodes to have the same cluster suitable for classic HPC and new AI/DL workloads.
The capabilities of supervised machine learning (SML), especially compared to human abilities, are being discussed in scientific research and in the usage of SML. This study provides an answer to how learning performance differs between humans and machines when there is limited training data. We have designed an experiment in which 44 humans and three different machine learning algorithms identify patterns in labeled training data and have to label instances according to the patterns they find. The results show a high dependency between performance and the underlying patterns of the task. Whereas humans perform relatively similarly across all patterns, machines show large performance differences for the various patterns in our experiment. After seeing 20 instances in the experiment, human performance does not improve anymore, which we relate to theories of cognitive overload. Machines learn slower but can reach the same level or may even outperform humans in 2 of the 4 of used patterns. However, machines need more instances compared to humans for the same results. The performance of machines is comparably lower for the other 2 patterns due to the difficulty of combining input features.
As AI and deep learning uses skyrocket, organizations are finding they are running these systems on similar resource as they do with high-performance computing (HPC) systems – and wondering if this is the path to peak efficiency. Ostensibly AI and HPC architectures have a lot in common, as AI has evolved into even more data-intensive machine learning (ML) and deep learning (DL) domains (Figure 1). Workloads often require multiple GPU systems as a cluster, and share those systems in a coordinated way among multiple data scientists. Secondly, both AI and HPC workloads require shared access to data at a high level of performance and communicate over a fast RDMA-enabled network. Especially in scientific research, the classic HPC systems nowadays tend to have GPUs added to the compute nodes to have the same cluster suitable for classic HPC and new AI/DL workloads.
Multiple-choice questions (MCQs) offer the most promising avenue for skill evaluation in the era of virtual education and job recruiting, where traditional performance-based alternatives such as projects and essays have become less viable, and grading resources are constrained. The automated generation of MCQs would allow assessment creation at scale. Recent advances in natural language processing have given rise to many complex question generation methods. However, the few methods that produce deployable results in specific domains require a large amount of domain-specific training data that can be very costly to acquire. Our work provides an initial foray into MCQ generation under high data-acquisition cost scenarios by strategically emphasizing paraphrasing the question context (compared to the task). In addition to maintaining semantic similarity between the question-answer pairs, our pipeline, which we call AGenT Zero, consists of only pre-trained models and requires no fine-tuning, minimizing data acquisition costs for question generation. AGenT Zero successfully outperforms other pre-trained methods in fluency and semantic similarity. Additionally, with some small changes, our assessment pipeline can be generalized to a broader question and answer space, including short answer or fill in the blank questions.