Results 1  10
of
89
Modeling relations and their mentions without labeled text
 In Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases: Part III
, 2010
"... Abstract. Several recent works on relation extraction have been applying the distant supervision paradigm: instead of relying on annotated text to learn how to predict relations, they employ existing knowledge bases (KBs) as source of supervision. Crucially, these approaches are trained based on the ..."
Abstract

Cited by 75 (3 self)
 Add to MetaCart
(Show Context)
Abstract. Several recent works on relation extraction have been applying the distant supervision paradigm: instead of relying on annotated text to learn how to predict relations, they employ existing knowledge bases (KBs) as source of supervision. Crucially, these approaches are trained based on the assumption that each sentence which mentions the two related entities is an expression of the given relation. Here we argue that this leads to noisy patterns that hurt precision, in particular if the knowledge base is not directly related to the text we are working with. We present a novel approach to distant supervision that can alleviate this problem based on the following two ideas: First, we use a factor graph to explicitly model the decision whether two entities are related, and the decision whether this relation is mentioned in a given sentence; second, we apply constraintdriven semisupervision to train this model without any knowledge about which sentences express the relations in our training KB. We apply our approach to extract relations from the New York Times corpus and use Freebase as knowledge base. When compared to a stateoftheart approach for relation extraction under distant supervision, we achieve 31 % error reduction. 1
An Introduction to Conditional Random Fields
 Foundations and Trends in Machine Learning
, 2012
"... ..."
(Show Context)
LREC’10 Learning Based Java for Rapid Development of NLP Systems
"... Today’s natural language processing systems are growing more complex with the need to incorporate a wider range of language resources and more sophisticated statistical methods. In many cases, it is necessary to learn a component with input that includes the predictions of other learned components o ..."
Abstract

Cited by 22 (8 self)
 Add to MetaCart
(Show Context)
Today’s natural language processing systems are growing more complex with the need to incorporate a wider range of language resources and more sophisticated statistical methods. In many cases, it is necessary to learn a component with input that includes the predictions of other learned components or to assign simultaneously the values that would be assigned by multiple components with an expressive, data dependent structure among them. As a result, the design of systems with multiple learning components is inevitably quite technically complex, and implementations of conceptually simple NLP systems can be time consuming and prone to error. Our new modeling language, Learning Based Java (LBJ), facilitates the rapid development of systems that learn and perform inference. LBJ has already been used to build state of the art NLP systems. This paper details recent advancements in the language which generalize its computational model, making a wider class of algorithms available. 1.
Automan: A platform for integrating humanbased and digital computation
"... Humans can perform many tasks with ease that remain difficult or impossible for computers. Crowdsourcing platforms like Amazon’s Mechanical Turk make it possible to harness humanbased computational power at an unprecedented scale. However, their utility as a generalpurpose computational platform r ..."
Abstract

Cited by 20 (2 self)
 Add to MetaCart
(Show Context)
Humans can perform many tasks with ease that remain difficult or impossible for computers. Crowdsourcing platforms like Amazon’s Mechanical Turk make it possible to harness humanbased computational power at an unprecedented scale. However, their utility as a generalpurpose computational platform remains limited. The lack of complete automation makes it difficult to orchestrate complex or interrelated tasks. Scheduling more human workers to reduce latency costs real money, and jobs must be monitored and rescheduled when workers fail to complete their tasks. Furthermore, it is often difficult to predict the length of time and payment that should be budgeted for a given task. Finally, the results of humanbased computations are not necessarily reliable, both because human skills and accuracy vary widely, and because workers
Elementary: Largescale Knowledgebase Construction via Machine Learning and Statistical Inference
"... Researchers have approached knowledgebase construction (KBC) with a wide range of data resources and techniques. We present Elementary, a prototype KBC system that is able to combine diverse resources and different KBC techniques via machine learning and statistical inference to construct knowledge ..."
Abstract

Cited by 17 (5 self)
 Add to MetaCart
(Show Context)
Researchers have approached knowledgebase construction (KBC) with a wide range of data resources and techniques. We present Elementary, a prototype KBC system that is able to combine diverse resources and different KBC techniques via machine learning and statistical inference to construct knowledge bases. Using Elementary, we have implemented a solution to the TACKBP challenge with quality comparable to the state of the art, as well as an endtoend online demonstration that automatically and continuously enriches Wikipedia with structured data by reading millions of webpages on a daily basis. We describe several challenges and our solutions in designing, implementing, and deploying Elementary. In particular, we first describe the conceptual framework and architecture of Elementary, and then discuss how we address scalability challenges to enable Webscale deployment. First, to take advantage of diverse data resources and proven techniques, Elementary employs Markov logic, a succinct yet expressive language to specify probabilistic graphical models. Elementary accepts both domainknowledge rules and classical machinelearning models such as conditional random fields, thereby integrating different data resources and KBC techniques in a principled manner. Second, to support largescale KBC with terabytes of data and millions of entities, Elementary
Measure Transformer Semantics for Bayesian Machine Learning
"... Abstract. The Bayesian approach to machine learning amounts to inferring posterior distributions of random variables from a probabilistic model of how the variables are related (that is, a prior distribution) and a set of observations of variables. There is a trend in machine learning towards expres ..."
Abstract

Cited by 16 (4 self)
 Add to MetaCart
(Show Context)
Abstract. The Bayesian approach to machine learning amounts to inferring posterior distributions of random variables from a probabilistic model of how the variables are related (that is, a prior distribution) and a set of observations of variables. There is a trend in machine learning towards expressing Bayesian models as probabilistic programs. As a foundation for this kind of programming, we propose a core functional calculus with primitives for sampling prior distributions and observing variables. We define combinators for measure transformers, based on theorems in measure theory, and use these to give a rigorous semantics to our core calculus. The original features of our semantics include its support for discrete, continuous, and hybrid measures, and, in particular, for observations of zeroprobability events. We compile our core language to a small imperative language that has a straightforward semantics via factor graphs, data structures that enable many efficient inference algorithms. We use an existing inference engine for efficient approximate inference of posterior marginal distributions, treating thousands of observations per second for large instances of realistic models. 1
Synthesizing open worlds with constraints using locally annealed reversible jump mcmc
 ACM Transactions on Graphics (TOG
, 2012
"... Figure 1: The tablechair sets, arm chairs, plants, shelves, and floor lamps in this coffee shop were arranged using our locally annealed reversible jump MCMC sampling method. The users don’t need to specify the number of objects beforehand. We present a novel Markov chain Monte Carlo (MCMC) algorit ..."
Abstract

Cited by 15 (5 self)
 Add to MetaCart
Figure 1: The tablechair sets, arm chairs, plants, shelves, and floor lamps in this coffee shop were arranged using our locally annealed reversible jump MCMC sampling method. The users don’t need to specify the number of objects beforehand. We present a novel Markov chain Monte Carlo (MCMC) algorithm that generates samples from transdimensional distributions encoding complex constraints. We use factor graphs, a type of graphical model, to encode constraints as factors. Our proposed MCMC method, called locally annealed reversible jump MCMC, exploits knowledge of how dimension changes affect the structure of the factor graph. We employ a sequence of annealed distributions during the sampling process, allowing us to explore the state space across different dimensionalities more freely. This approach is motivated by the application of layout synthesis where relationships between objects are characterized as constraints. In particular, our method addresses the challenge of synthesizing open world layouts where the number of objects are not fixed and optimal configurations for different numbers of objects may be drastically different. We demonstrate the applicability of our approach on two open world layout synthesis problems: coffee shops and golf courses.
Grammatical structures for wordlevel sentiment detection
 In North American Association of Computational Linguistics
, 2012
"... Existing work in finegrained sentiment analysis focuses on sentences and phrases but ignores the contribution of individual words and their grammatical connections. This is because of a lack of both (1) annotated data at the word level and (2) algorithms that can leverage syntactic information in a ..."
Abstract

Cited by 13 (7 self)
 Add to MetaCart
(Show Context)
Existing work in finegrained sentiment analysis focuses on sentences and phrases but ignores the contribution of individual words and their grammatical connections. This is because of a lack of both (1) annotated data at the word level and (2) algorithms that can leverage syntactic information in a principled way. We address the first need by annotating articles from the information technology business press via crowdsourcing to provide training and testing data. To address the second need, we propose a suffixtree data structure to represent syntactic relationships between opinion targets and words in a sentence that are opinionbearing. We show that a factor graph derived from this data structure acquires these relationships with a small number of wordlevel features. We demonstrate that our supervised model performs better than baselines that ignore syntactic features and constraints. 1
Online MaxMargin Weight Learning for Markov Logic Networks
"... Most of the existing weightlearning algorithms for Markov Logic Networks (MLNs) use batch training which becomes computationally expensive and even infeasible for very large datasets since the training examples may not fit in main memory. To overcome this problem, previous work has used online lear ..."
Abstract

Cited by 11 (1 self)
 Add to MetaCart
(Show Context)
Most of the existing weightlearning algorithms for Markov Logic Networks (MLNs) use batch training which becomes computationally expensive and even infeasible for very large datasets since the training examples may not fit in main memory. To overcome this problem, previous work has used online learning algorithms to learn weights for MLNs. However, this prior work has only applied existing online algorithms, and there is no comprehensive study of online weight learning for MLNs. In this paper, we derive a new online algorithm for structured prediction using the primaldual framework, apply it to learn weights for MLNs, and compare against existing online algorithms on three large, realworld datasets. The experimental results show that our new algorithm generally achieves better accuracy than existing methods, especially on noisy datasets.
Towards HighThroughput Gibbs Sampling at Scale: A Study across Storage Managers
"... Factor graphs and Gibbs sampling are a popular combination for Bayesian statistical methods that are used to solve diverse problems including insurance risk models, pricing models, and information extraction. Given a fixed sampling method and a fixed amount of time, an implementation of a sampler th ..."
Abstract

Cited by 10 (5 self)
 Add to MetaCart
(Show Context)
Factor graphs and Gibbs sampling are a popular combination for Bayesian statistical methods that are used to solve diverse problems including insurance risk models, pricing models, and information extraction. Given a fixed sampling method and a fixed amount of time, an implementation of a sampler that achieves a higher throughput of samples will achieve a higher quality than a lowerthroughput sampler. We study how (and whether) traditional data processing choices about materialization, page layout, and bufferreplacement policy need to be changed to achieve highthroughput Gibbs sampling for factor graphs that are larger than main memory. We find that both new theoretical and new algorithmic techniques are required to understand the tradeoff space for each choice. On both real and synthetic data, we demonstrate that traditional baseline approaches may achieve two orders of magnitude lower throughput than an optimal approach. For a handful of popular tasks across several storage backends, including HBase and traditional unix files, we show that our simple prototype achieves competitive (and sometimes better) throughput compared to specialized stateoftheart approaches on factor graphs that are larger than main memory.