The pre-training of large language models usually requires massive amounts of resources, both in terms of computation and data. Frequently used web sources such as Common Crawl might contain enough ...noise to make this pretraining sub-optimal. In this work, we experiment with different sampling methods from the Spanish version of mC4, and present a novel data-centric technique which we name perplexity sampling that enables the pre-training of language models in roughly half the amount of steps and using one fifth of the data. The resulting models are comparable to the current state-of-the-art, and even achieve better results for certain tasks. Our work is proof of the versatility of Transformers, and paves the way for small teams to train their models on a limited budget.
Language models have traditionally been estimated based on relative frequencies, using count statistics that can be extracted from huge amounts of text data. More recently, it has been found that ...neural networks are particularly powerful at estimating probability distributions over word sequences, giving substantial improvements over state-of-the-art count models. However, the performance of neural network language models strongly depends on their architectural structure. This paper compares count models to feedforward, recurrent, and long short-term memory (LSTM) neural network variants on two large-vocabulary speech recognition tasks. We evaluate the models in terms of perplexity and word error rate, experimentally validating the strong correlation of the two quantities, which we find to hold regardless of the underlying type of the language model. Furthermore, neural networks incur an increased computational complexity compared to count models, and they differently model context dependences, often exceeding the number of words that are taken into account by count based approaches. These differences require efficient search methods for neural networks, and we analyze the potential improvements that can be obtained when applying advanced algorithms to the rescoring of word lattices on large-scale setups.
We present a new method, Soloist, that uses transfer learning and machine teaching to build task bots at scale. We parameterize classical modular task-oriented dialog systems using a ...Transformer-based auto-regressive language model, which subsumes different dialog modules into a single neural model. We pre-train, on heterogeneous dialog corpora, a task-grounded response generation model, which can generate dialog responses grounded in user goals and real-world knowledge for task completion. The pre-trained model can be efficiently adapted to accomplish new tasks with a handful of task-specific dialogs via machine teaching, where training samples are generated by human teachers interacting with the system. Experiments show that (i) Soloist creates new state-of-the-art on well-studied task-oriented dialog benchmarks, including CamRest676 and MultiWOZ; (ii) in the few-shot fine-tuning settings, Soloist significantly outperforms existing methods; and (iii) the use of machine teaching substantially reduces the labeling cost of fine-tuning. The pre-trained models and codes are available at https://aka.ms/soloist.
Scene text spotting is of great importance to the computer vision community due to its wide variety of applications. Recent methods attempt to introduce linguistic knowledge for challenging ...recognition rather than pure visual classification. However, how to effectively model the linguistic rules in end-to-end deep networks remains a research challenge. In this paper, we argue that the limited capacity of language models comes from 1) implicit language modeling; 2) unidirectional feature representation; and 3) language model with noise input. Correspondingly, we propose an autonomous, bidirectional and iterative ABINet++ for scene text spotting. First, the autonomous suggests enforcing explicitly language modeling by decoupling the recognizer into vision model and language model and blocking gradient flow between both models. Second, a novel bidirectional cloze network (BCN) as the language model is proposed based on bidirectional feature representation. Third, we propose an execution manner of iterative correction for the language model which can effectively alleviate the impact of noise input. Additionally, based on an ensemble of the iterative predictions, a self-training method is developed which can learn from unlabeled images effectively. Finally, to polish ABINet++ in long text recognition, we propose to aggregate horizontal features by embedding Transformer units inside a U-Net, and design a position and content attention module which integrates character order and content to attend to character features precisely. ABINet++ achieves state-of-the-art performance on both scene text recognition and scene text spotting benchmarks, which consistently demonstrates the superiority of our method in various environments especially on low-quality images. Besides, extensive experiments including in English and Chinese also prove that, a text spotter that incorporates our language modeling method can significantly improve its performance both in accuracy and speed compared with commonly used attention-based recognizers. Code is available at https://github.com/FangShancheng/ABINet-PP .
We introduce The Benchmark of Linguistic Minimal Pairs (BLiMP),
a challenge set for evaluating the linguistic knowledge of language models (LMs) on major grammatical phenomena in English. BLiMP ...consists of 67 individual datasets, each containing 1,000 minimal pairs—that is, pairs of minimally different sentences that contrast in grammatical acceptability and isolate specific phenomenon in syntax, morphology, or semantics. We generate the data according to linguist-crafted grammar templates, and human aggregate agreement with the labels is 96.4%. We evaluate
-gram, LSTM, and Transformer (GPT-2 and Transformer-XL) LMs by observing whether they assign a higher probability to the acceptable sentence in each minimal pair. We find that state-of-the-art models identify morphological contrasts related to agreement reliably, but they struggle with some subtle semantic and syntactic phenomena, such as negative polarity items and extraction islands.
•Handwritten Text Recognition is researched in this paper with a set of free available benchmarks.•Freely available tools are provided for Handwritten Text Recognition.•Competitive results are ...provided with Convolutional Recurrent Neural Networks and N-gram language models.•New challenges are described related to Handwritten Text Recognition.
Handwritten Text Recognition is a important requirement in order to make visible the contents of the myriads of historical documents residing in public and private archives and libraries world wide. Automatic Handwritten Text Recognition (HTR) is a challenging problem that requires a careful combination of several advanced Pattern Recognition techniques, including but not limited to Image Processing, Document Image Analysis, Feature Extraction, Neural Network approaches and Language Modeling. The progress of this kind of systems is strongly bound by the availability of adequate benchmarking datasets, software tools and reproducible results achieved using the corresponding tools and datasets. Based on English and German historical documents proposed in recent open competitions at ICDAR and ICFHR conferences between 2014 and 2017, this paper introduces four HTR benchmarks in order of increasing complexity from several points of view. For each benchmark, a specific system is proposed which overcomes results published so far under comparable conditions. Therefore, this paper establishes new state of the art baseline systems and results which aim at becoming new challenges that would hopefully drive further improvement of HTR technologies. Both the datasets and the software tools used to implement the baseline systems are made freely accessible for research purposes.
Recent work has shown that pre-trained language models such as BERT improve robustness to spurious correlations in the dataset. Intrigued by these results, we find that the key to their success is ...generalization from a small amount of counterexamples where the spurious correlations do not hold. When such minority examples are scarce, pre-trained models perform as poorly as models trained from scratch. In the case of extreme minority, we propose to use multi-task learning (MTL) to improve generalization. Our experiments on natural language inference and paraphrase identification show that MTL with the right auxiliary tasks significantly improves performance on challenging examples without hurting the in-distribution performance. Further, we show that the gain from MTL mainly comes from improved generalization from the minority examples. Our results highlight the importance of data diversity for overcoming spurious correlations.