Self-Training with Weak Supervision

State-of-the-art deep neural networks require large-scale labeled training data that is often expensive to obtain or not available for many tasks. Weak supervision in the form of domain-specific rules has been shown to be useful in such settings to automatically generate weakly labeled training data. However, learning with weak rules is challenging due to their inherent heuristic and noisy nature. An additional challenge is rule coverage and overlap, where prior work on weak supervision only considers instances that are covered by weak rules, thus leaving valuable unlabeled data behind. In this work, we develop a weak supervision framework (ASTRA) that leverages all the available data for a given task. To this end, we leverage task-specific unlabeled data through self-training with a model (student) that considers contextualized representations and predicts pseudo-labels for instances that may not be covered by weak rules. We further develop a rule attention network (teacher) that learns how to aggregate student pseudo-labels with weak rule labels, conditioned on their fidelity and the underlying context of an instance. Finally, we construct a semi-supervised learning objective for end-to-end training with unlabeled data, domain-specific rules, and a small amount of labeled data. Extensive experiments on six benchmark datasets for text classification demonstrate the effectiveness of our approach with significant improvements over state-of-the-art baselines.

X-Class: Text Classification with Extremely Weak Supervision

In this paper, we explore text classification with extremely weak supervision, i.e., only relying on the surface text of class names. This is a more challenging setting than the seed-driven weak supervision, which allows a few seed words per class. We opt to attack this problem from a representation learning perspective---ideal document representations should lead to nearly the same results between clustering and the desired classification. In particular, one can classify the same corpus differently (e.g., based on topics and locations), so document representations should be adaptive to the given class names. We propose a novel framework X-Class to realize the adaptive representations. Specifically, we first estimate class representations by incrementally adding the most similar word to each class until inconsistency arises. Following a tailored mixture of class attention mechanisms, we obtain the document representation via a weighted average of contextualized word representations. With the prior of each document assigned to its nearest class, we then cluster and align the documents to classes. Finally, we pick the most confident documents from each cluster to train a text classifier. Extensive experiments demonstrate that X-Class can rival and even outperform seed-driven weakly supervised methods on 7 benchmark datasets.

Testing weak form efficiency in Damascus securities market: Acomparisation study with Amman, Muscat securities markets

This paper aims to test weak form efficiency in Damascus , Amman , Muscat securities market .It examines daily stock return index during ( 1 - 4- 2010 ) , ( 31 - 12 - 2016 ) using normal distribution test , runs test , autocorrelation test , unit root test , variance ratio test , auto regressive integrated moving average test

Testing the Random Walk Model on the Stock Returns of Firms Listed in the Damascus Securities Exchange

This study aimed to examine the weak form efficiency of the Damascus Securities Exchange (DSE). The study used the monthly returns, adjusted for thin trading, of firms listed in the Damascus Securities Exchange from 2009 until 2014 and applied various tests to examine the random walk behavior in returns: the unit root test, the autocorrelation test, the runs test and the GARCH model. To take the impact of the Syrian crisis into account when judging the efficiency of the market, the study period was divided into three periods, the pre-crisis period, the crisis period and the whole period. The results revealed inability to reject the weak form efficient market hypothesis for more than half of the studied firms. Also it showed that the Syrian crisis, in general, has negatively affected the efficiency of most of the studied firms.

Weak Forms: How Do Arabic-speaking Learners of English Use Them?

This paper attempts to investigate the way Arab learners of English deal with weak form items and the difficulty they encounter in using such grammatical items in context. This problem was approached from two different avenues. I therefore carried out two separate tests. The first test, the pronunciation test, showed that Arab learners have a serious problem with pronouncing weak form items. The second test, the identification test, also demonstrated that Arab learners had a problem with identifying weak form words in context.