We present a simple and effective semisupervised method for training dependency parsers. We focus on the problem of lexical representation, introducing features that incorporate word clusters derived from a large unannotated corpus. We demonstrate the effectiveness of the approach in a series of dependency parsing experiments on the Penn Treebank and Prague Dependency Treebank, and we show that the cluster-based features yield substantial gains in performance across a wide range of conditions. For example, in the case of English unlabeled second-order parsing, we improve from a baseline accuracy of 92.02 % to 93.16%, and in the case of Czech unlabeled second-order parsing, we improve from a baseline accuracy of 86.13% to 87.13%. In addition, we demonstrate that our method also improves performance when small amounts of training data are available, and can roughly halve the amount of supervised data required to reach a desired level of performance. 1

We describe a single convolutional neural network architecture that, given a sentence, outputs a host of language processing predictions: part-of-speech tags, chunks, named entity tags, semantic roles, semantically similar words and the likelihood that the sentence makes sense (grammatically and semantically) using a language model. The entire network is trained jointly on all these tasks using weight-sharing, an instance of multitask learning. All the tasks use labeled data except the language model which is learnt from unlabeled text and represents a novel form of semi-supervised learning for the shared tasks. We show how both multitask learning and semi-supervised learning improve the generalization of the shared tasks, resulting in stateof-the-art performance. 1.

We consider the problem of semi-supervised learning to extract categories (e.g., academic fields, athletes) and relations (e.g., PlaysSport(athlete, sport)) from web pages, starting with a handful of labeled training examples of each category or relation, plus hundreds of millions of unlabeled web documents. Semi-supervised training using only a few labeled examples is typically unreliable because the learning task is underconstrained. This paper pursues the thesis that much greater accuracy can be achieved by further constraining the learning task, by coupling the semi-supervised training of many extractors for different categories and relations. We characterize several ways in which the training of category and relation extractors can be coupled, and present experimental results demonstrating significantly improved accuracy as a result. Categories and Subject Descriptors I.2.6 [Artificial Intelligence]: Learning—knowledge acquisition;

Over the last few years, two of the main research directions in machine learning of natural language processing have been the study of semi-supervised learning algorithms as a way to train classifiers when the labeled data is scarce, and the study of ways to exploit knowledge and global information in structured learning tasks. In this paper, we suggest a method for incorporating domain knowledge in semi-supervised learning algorithms. Our novel framework unifies and can exploit several kinds of task specific constraints. The experimental results presented in the information extraction domain demonstrate that applying constraints helps the model to generate better feedback during learning, and hence the framework allows for high performance learning with significantly less training data than was possible before on these tasks. 1

The explosion of the Internet provides us with a tremendous resource of images shared online. It also confronts vision researchers the problem of finding effective methods to navigate the vast amount of visual information. Semantic image understanding plays a vital role towards solving this problem. One important task in image understanding is object recognition, in particular, generic object categorization. Critical to this problem are the issues of learning and dataset. Abundant data helps to train a robust recognition system, while a good object classifier can help to collect a large amount of images. This paper presents a novel object recognition algorithm that performs automatic dataset collecting and incremental model learning simultaneously. The goal of this work is to use the tremendous resources of the web to learn robust object category models for detecting and searching for objects in real-world cluttered scenes. Humans contiguously update the knowledge of objects when new examples are observed. Our framework emulates this human learning process by iteratively accumulating model knowledge and image examples. We adapt a non-parametric latent topic model and propose an incremental learning framework. Our algorithm is capable of automatically collecting much larger object category datasets for 22 randomly selected classes from the Caltech 101 dataset. Furthermore, our system offers not only more images in

This thesis is about estimating probabilistic models to uncover useful hidden structure in data; specifically, we address the problem of discovering syntactic structure in natural language text. We present three new parameter estimation techniques that generalize the standard approach, maximum likelihood estimation, in different ways. Contrastive estimation maximizes the conditional probability of the observed data given a “neighborhood” of implicit negative examples. Skewed deterministic annealing locally maximizes likelihood using a cautious parameter search strategy that starts with an easier optimization problem than likelihood, and iteratively moves to harder problems, culminating in likelihood. Structural annealing is similar, but starts with a heavy bias toward simple syntactic structures and gradually relaxes the bias. Our estimation methods do not make use of annotated examples. We consider their performance in both an unsupervised model selection setting, where models trained under different initialization and regularization settings are compared by evaluating the training objective on a small set of unseen, unannotated development data, and supervised model selection, where the most accurate model on the development set (now with annotations)

We investigate the effectiveness of selftraining PCFG grammars with latent annotations (PCFG-LA) for parsing languages with different amounts of labeled training data. Compared to Charniak’s lexicalized parser, the PCFG-LA parser was more effectively adapted to a language for which parsing has been less well developed (i.e., Chinese) and benefited more from selftraining. We show for the first time that self-training is able to significantly improve the performance of the PCFG-LA parser, a single generative parser, on both small and large amounts of labeled training data. Our approach achieves stateof-the-art parsing accuracies for a single parser on both English (91.5%) and Chinese (85.2%). 1

We present three approaches for unsupervised grammar induction that are sensitive to data complexity and apply them to Klein and Manning’s Dependency Model with Valence. The first, Baby Steps, bootstraps itself via iterated learning of increasingly longer sentences and requires no initialization. This method substantially exceeds Klein and Manning’s published scores and achieves 39.4 % accuracy on Section 23 (all sentences) of the Wall Street Journal corpus. The second, Less is More, uses a low-complexity subset of the available data: sentences up to length 15. Focusing on fewer but simpler examples trades off quantity against ambiguity; it attains 44.1% accuracy, using the standard linguisticallyinformed prior and batch training, beating state-of-the-art. Leapfrog, our third heuristic, combines Less is More with Baby Steps by mixing their models of shorter sentences, then rapidly ramping up exposure to the full training set, driving up accuracy to 45.0%. These trends generalize to the Brown corpus; awareness of data complexity may improve other parsing models and unsupervised algorithms.

We present a novel semi-supervised training algorithm for learning dependency parsers. By combining a supervised large margin loss with an unsupervised least squares loss, a discriminative, convex, semi-supervised learning algorithm can be obtained that is applicable to large-scale problems. To demonstrate the benefits of this approach, we apply the technique to learning dependency parsers from combined labeled and unlabeled corpora. Using a stochastic gradient descent algorithm, a parsing model can be efficiently learned from semi-supervised data that significantly outperforms corresponding supervised methods. 1

We show that Viterbi (or “hard”) EM is well-suited to unsupervised grammar induction. It is more accurate than standard inside-outside re-estimation (classic EM), significantly faster, and simpler. Our experiments with Klein and Manning’s Dependency Model with Valence (DMV) attain state-of-the-art performance — 44.8% accuracy on Section 23 (all sentences) of the Wall Street Journal corpus — without clever initialization; with a good initializer, Viterbi training improves to 47.9%. This generalizes to the Brown corpus, our held-out set, where accuracy reaches 50.8 % — a 7.5 % gain over previous best results. We find that classic EM learns better from short sentences but cannot cope with longer ones, where Viterbi thrives. However, we explain that both algorithms optimize the wrong objectives and prove that there are fundamental disconnects between the likelihoods of sentences, best parses, and true parses, beyond the wellestablished discrepancies between likelihood, accuracy and extrinsic performance. 1