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

We explore the use of Wikipedia as external knowledge to improve named entity recognition (NER). Our method retrieves the corresponding Wikipedia entry for each candidate word sequence and extracts a category label from the first sentence of the entry, which can be thought of as a definition

This paper presents six novel approaches to biographic fact extraction that model structural, transitive and latent properties of biographical data. The ensemble of these proposed models substantially outperforms standard pattern-based biographic fact extraction methods and performance is further improved by modeling inter-attribute correlations and distributions over functions of attributes, achieving an average extraction accuracy of 80% over seven types of biographic attributes. 1

This paper presents a method for unsupervised discovery of semantic patterns.

This paper presents a method for unsupervised discovery of semantic patterns.

Most approaches to event extraction focus on mentions anchored in verbs. However, many mentions of events surface as noun phrases. Detecting them can increase the recall of event extraction and provide the foundation for detecting relations between events. This paper describes a weaklysupervised method for detecting nominal event mentions that combines techniques from word sense disambiguation (WSD) and lexical acquisition to create a classifier that labels noun phrases as denoting events or non-events. The classifier uses bootstrapped probabilistic generative models of the contexts of events and non-events. The contexts are the lexically-anchored semantic dependency relations that the NPs appear in. Our method dramatically improves with bootstrapping, and comfortably outperforms lexical lookup methods which are based on very much larger handcrafted resources. 1

In this paper, we present a weakly supervised learning approach for spoken language understanding in domain-specific dialogue systems. We model the task of spoken language understanding as a successive classification problem. The first classifier (topic classifier) is used to identify the topic of an input utterance. With the restriction of the recognized target topic, the second classifier (semantic classifier) is trained to extract the corresponding slot-value pairs. It is mainly data-driven and requires only minimally annotated corpus for training whilst retaining the understanding robustness and deepness for spoken language. Most importantly, it allows the employment of weakly supervised strategies for training the two classifiers. We first apply the training strategy of combining active learning and self-training (Tur et al., 2005) for topic classifier. Also, we propose a practical method for bootstrapping the topic-dependent semantic classifiers from a small amount of labeled sentences. Experiments have been conducted in the context of Chinese public transportation information inquiry domain. The experimental results demonstrate the effectiveness of our proposed SLU framework and show the possibility to reduce human labeling efforts significantly. 1

When people describe a scene, they often include information that is not visually apparent; sometimes based on background knowledge, sometimes to tell a story. We aim to separate visual text—descriptions of what is being seen—from non-visual text in natural images and their descriptions. To do so, we first concretely define what it means to be visual, annotate visual text and then develop algorithms to automatically classify noun phrases as visual or non-visual. We find that using text alone, we are able to achieve high accuracies at this task, and that incorporating features derived from computer vision algorithms improves performance. Finally, we show that we can reliably mine visual nouns and adjectives from large corpora and that we can use these effectively in the classification task. 1

Many natural language processing problems involve constructing large nearest-neighbor graphs. We propose a system called FLAG to construct such graphs approximately from large data sets. To handle the large amount of data, our algorithm maintains approximate counts based on sketching algorithms. To find the approximate nearest neighbors, our algorithm pairs a new distributed online-PMI algorithm with novel fast approximate nearest neighbor search algorithms (variants of PLEB). These algorithms return the approximate nearest neighbors quickly. We show our system’s efficiency in both intrinsic and extrinsic experiments. We further evaluate our fast search algorithms both quantitatively and qualitatively on two NLP applications. 1