Results 1 - 10 of 165

A unified architecture for natural language processing: Deep neural networks with multitask learning

by Ronan Collobert, Jason Weston , 2008
"... 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 sem ..."
Abstract - Cited by 315 (13 self) - Add to MetaCart
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.
(Show Context)

Semi-Markov conditional random fields for information extraction

by Sunita Sarawagi, William W. Cohen - In Advances in Neural Information Processing Systems 17 , 2004
"... We describe semi-Markov conditional random fields (semi-CRFs), a conditionally trained version of semi-Markov chains. Intuitively, a semi-CRF on an input sequence x outputs a “segmentation ” of x, in which labels are assigned to segments (i.e., subsequences) of x rather than to individual elements x ..."
Abstract - Cited by 248 (10 self) - Add to MetaCart
We describe semi-Markov conditional random fields (semi-CRFs), a conditionally trained version of semi-Markov chains. Intuitively, a semi-CRF on an input sequence x outputs a “segmentation ” of x, in which labels are assigned to segments (i.e., subsequences) of x rather than to individual elements xi of x. Importantly, features for semi-CRFs can measure properties of segments, and transitions within a segment can be non-Markovian. In spite of this additional power, exact learning and inference algorithms for semi-CRFs are polynomial-time—often only a small constant factor slower than conventional CRFs. In experiments on five named entity recognition problems, semi-CRFs generally outperform conventional CRFs. 1
(Show Context)

Natural language processing (almost) from scratch

by Ronan Collobert, Jason Weston, Léon Bottou, Michael Karlen, Koray Kavukcuoglu, Pavel Kuksa , 2011
"... We propose a unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including part-of-speech tagging, chunking, named entity recognition, and semantic role labeling. This versatility is achieved by trying to avoid task-specific eng ..."
Abstract - Cited by 209 (17 self) - Add to MetaCart
We propose a unified neural network architecture and learning algorithm that can be applied to various natural language processing tasks including part-of-speech tagging, chunking, named entity recognition, and semantic role labeling. This versatility is achieved by trying to avoid task-specific engineering and therefore disregarding a lot of prior knowledge. Instead of exploiting man-made input features carefully optimized for each task, our system learns internal representations on the basis of vast amounts of mostly unlabeled training data. This work is then used as a basis for building a freely available tagging system with good performance and minimal computational requirements.

Piecewise training of undirected models

by Charles Sutton, Andrew Mccallum - In Proc. of UAI , 2005
"... For many large undirected models that arise in real-world applications, exact maximumlikelihood training is intractable, because it requires computing marginal distributions of the model. Conditional training is even more difficult, because the partition function depends not only on the parameters, ..."
Abstract - Cited by 102 (5 self) - Add to MetaCart
For many large undirected models that arise in real-world applications, exact maximumlikelihood training is intractable, because it requires computing marginal distributions of the model. Conditional training is even more difficult, because the partition function depends not only on the parameters, but also on the observed input, requiring repeated inference over each training example. An appealing idea for such models is to independently train a local undirected classifier over each clique, afterwards combining the learned weights into a single global model. In this paper, we show that this piecewise method can be justified as minimizing a new family of upper bounds on the log partition function. On three natural-language data sets, piecewise training is more accurate than pseudolikelihood, and often performs comparably to global training using belief propagation. 1
(Show Context)

Extracting social networks and contact information from email and the web

by Aron Culotta, Ron Bekkerman, Andrew Mccallum - In Proceedings of CEAS-1 , 2004
"... Abstract. We present an end-to-end system that extracts a user’s social network and its members’ contact information given the user’s email inbox. The system identifies unique people in email, finds their Web presence, and automatically fills the fields of a contact address book using conditional ra ..."
Abstract - Cited by 100 (4 self) - Add to MetaCart
Abstract. We present an end-to-end system that extracts a user’s social network and its members’ contact information given the user’s email inbox. The system identifies unique people in email, finds their Web presence, and automatically fills the fields of a contact address book using conditional random fields—a type of probabilistic model well-suited for such information extraction tasks. By recursively calling itself on new people discovered on the Web, the system builds a social network with multiple degrees of separation from the user. Additionally, a set of expertise-describing keywords are extracted and associated with each person. We outline the collection of statistical and learning components that enable this system, and present experimental results on the real email of two users; we also present results with a simple method of learning transfer, and discuss the capabilities of the system for addressbook population, expert-finding, and social network analysis. 1
(Show Context)

Latent-dynamic discriminative models for continuous gesture recognition

by Ariadna Quattoni, Trevor Darrell - Proceedings of CVPR’07 , 2007
"... Many problems in vision involve the prediction of a class label for each frame in an unsegmented sequence. In this paper, we develop a discriminative framework for simultaneous sequence segmentation and labeling which can capture both intrinsic and extrinsic class dynamics. Our approach incorporates ..."
Abstract - Cited by 96 (0 self) - Add to MetaCart
Many problems in vision involve the prediction of a class label for each frame in an unsegmented sequence. In this paper, we develop a discriminative framework for simultaneous sequence segmentation and labeling which can capture both intrinsic and extrinsic class dynamics. Our approach incorporates hidden state variables which model the sub-structure of a class sequence and learn dynamics between class labels. Each class label has a disjoint set of associated hidden states, which enables efficient training and inference in our model. We evaluated our method on the task of recognizing human gestures from unsegmented video streams and performed experiments on three different datasets of head and eye gestures. Our results demonstrate that our model compares favorably to Support Vector Machines, Hidden Markov Models, and Conditional Random Fields on visual gesture recognition tasks. 1.
(Show Context)

Learning conditional random fields for stereo

by Daniel Scharstein - In CVPR , 2007
"... State-of-the-art stereo vision algorithms utilize color changes as important cues for object boundaries. Most methods impose heuristic restrictions or priors on disparities, for example by modulating local smoothness costs with intensity gradients. In this paper we seek to replace such heuristics wi ..."
Abstract - Cited by 92 (3 self) - Add to MetaCart
State-of-the-art stereo vision algorithms utilize color changes as important cues for object boundaries. Most methods impose heuristic restrictions or priors on disparities, for example by modulating local smoothness costs with intensity gradients. In this paper we seek to replace such heuristics with explicit probabilistic models of disparities and intensities learned from real images. We have constructed a large number of stereo datasets with ground-truth disparities, and we use a subset of these datasets to learn the parameters of Conditional Random Fields (CRFs). We present experimental results illustrating the potential of our approach for automatically learning the parameters of models with richer structure than standard hand-tuned MRF models. 1. Introduction and
(Show Context)

Collective segmentation and labeling of distant entities in information extraction

by Charles Sutton , 2004
"... In information extraction, we often wish to identify all mentions of an entity, such as a person or organization. Traditionally, a group of words is labeled as an entity based only on local information. But information from throughout a document can be useful; for example, if the same word is used m ..."
Abstract - Cited by 90 (18 self) - Add to MetaCart
In information extraction, we often wish to identify all mentions of an entity, such as a person or organization. Traditionally, a group of words is labeled as an entity based only on local information. But information from throughout a document can be useful; for example, if the same word is used multiple times, it is likely to have the same label each time. We present a CRF that explicitly represents dependencies between the labels of pairs of similar words in a document. On a standard information extraction data set, we show that learning these dependencies leads to a 13.7% reduction in error on the field that had caused the most repetition errors. 1
(Show Context)

Structured Models for Fine-to-Coarse Sentiment Analysis

by Ryan Mcdonald, Kerry Hannan, Tyler Neylon, Mike Wells, Jeff Reynar - Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics , 2007
"... In this paper we investigate a structured model for jointly classifying the sentiment of text at varying levels of granularity. Inference in the model is based on standard sequence classification techniques using constrained Viterbi to ensure consistent solutions. The primary advantage of such a mod ..."
Abstract - Cited by 88 (6 self) - Add to MetaCart
In this paper we investigate a structured model for jointly classifying the sentiment of text at varying levels of granularity. Inference in the model is based on standard sequence classification techniques using constrained Viterbi to ensure consistent solutions. The primary advantage of such a model is that it allows classification decisions from one level in the text to influence decisions at another. Experiments show that this method can significantly reduce classification error relative to models trained in isolation. 1
(Show Context)

Dependency parsing by belief propagation

by David A. Smith, Jason Eisner - In Proceedings of EMNLP , 2008
"... We formulate dependency parsing as a graphical model with the novel ingredient of global constraints. We show how to apply loopy belief propagation (BP), a simple and effective tool for approximate learning and inference. As a parsing algorithm, BP is both asymptotically and empirically efficient. E ..."
Abstract - Cited by 85 (9 self) - Add to MetaCart
We formulate dependency parsing as a graphical model with the novel ingredient of global constraints. We show how to apply loopy belief propagation (BP), a simple and effective tool for approximate learning and inference. As a parsing algorithm, BP is both asymptotically and empirically efficient. Even with second-order features or latent variables, which would make exact parsing considerably slower or NP-hard, BP needs only O(n3) time with a small constant factor. Furthermore, such features significantly improve parse accuracy over exact first-order methods. Incorporating additional features would increase the runtime additively rather than multiplicatively. 1
(Show Context)