arXiv subjects

Hal Daumé III

Publications and source records attributed to Hal Daumé III.

105 records · Page 6Linked to original sources

arXiv2009

Fast search for Dirichlet process mixture models

Dirichlet process (DP) mixture models provide a flexible Bayesian framework for density estimation. Unfortunately, their flexibility comes at a cost: inference in DP mixture models is computationally expensive, even when conjugate distributions are used. In the common case when one seeks only a maximum a posteriori assignment of data points to clusters, we show that search algorithms provide a practical alternative to expensive MCMC and variational techniques. When a true posterior sample is desired, the solution found by search can serve as a good initializer for MCMC. Experimental results show that using these techniques is it possible to apply DP mixture models to very large data sets.

cs.LG↗

arXiv2009

Bayesian Query-Focused Summarization

We present BayeSum (for ``Bayesian summarization''), a model for sentence extraction in query-focused summarization. BayeSum leverages the common case in which multiple documents are relevant to a single query. Using these documents as reinforcement for query terms, BayeSum is not afflicted by the paucity of information in short queries. We show that approximate inference in BayeSum is possible on large data sets and results in a state-of-the-art summarization system. Furthermore, we show how BayeSum can be understood as a justified query expansion technique in the language modeling for IR framework.

cs.CL↗

arXiv2009

Frustratingly Easy Domain Adaptation

We describe an approach to domain adaptation that is appropriate exactly in the case when one has enough ``target'' data to do slightly better than just using only ``source'' data. Our approach is incredibly simple, easy to implement as a preprocessing step (10 lines of Perl!) and outperforms state-of-the-art approaches on a range of datasets. Moreover, it is trivially extended to a multi-domain adaptation problem, where one has data from a variety of different domains.

cs.LG↗

arXiv2009

Bayesian Agglomerative Clustering with Coalescents

We introduce a new Bayesian model for hierarchical clustering based on a prior over trees called Kingman's coalescent. We develop novel greedy and sequential Monte Carlo inferences which operate in a bottom-up agglomerative fashion. We show experimentally the superiority of our algorithms over others, and demonstrate our approach in document clustering and phylolinguistics.

stat.ML↗

arXiv2009

Bayesian Multitask Learning with Latent Hierarchies

We learn multiple hypotheses for related tasks under a latent hierarchical relationship between tasks. We exploit the intuition that for domain adaptation, we wish to share classifier structure, but for multitask learning, we wish to share covariance structure. Our hierarchical model is seen to subsume several previously proposed multitask learning models and performs well on three distinct real-world data sets.

cs.LG↗

arXiv2009

Cross-Task Knowledge-Constrained Self Training

We present an algorithmic framework for learning multiple related tasks. Our framework exploits a form of prior knowledge that relates the output spaces of these tasks. We present PAC learning results that analyze the conditions under which such learning is possible. We present results on learning a shallow parser and named-entity recognition system that exploits our framework, showing consistent improvements over baseline methods.

cs.LG↗

arXiv2009

A Bayesian Model for Discovering Typological Implications

A standard form of analysis for linguistic typology is the universal implication. These implications state facts about the range of extant languages, such as ``if objects come after verbs, then adjectives come after nouns.'' Such implications are typically discovered by painstaking hand analysis over a small sample of languages. We propose a computational model for assisting at this process. Our model is able to discover both well-known implications as well as some novel implications that deserve further study. Moreover, through a careful application of hierarchical analysis, we are able to cope with the well-known sampling problem: languages are not independent.

cs.CL↗

arXiv2009

Search-based Structured Prediction

We present Searn, an algorithm for integrating search and learning to solve complex structured prediction problems such as those that occur in natural language, speech, computational biology, and vision. Searn is a meta-algorithm that transforms these complex problems into simple classification problems to which any binary classifier may be applied. Unlike current algorithms for structured learning that require decomposition of both the loss function and the feature functions over the predicted structure, Searn is able to learn prediction functions for any loss function and any class of features. Moreover, Searn comes with a strong, natural theoretical guarantee: good performance on the derived classification problems implies good performance on the structured prediction problem.

cs.LG↗

arXiv2009

Induction of Word and Phrase Alignments for Automatic Document Summarization

Current research in automatic single document summarization is dominated by two effective, yet naive approaches: summarization by sentence extraction, and headline generation via bag-of-words models. While successful in some tasks, neither of these models is able to adequately capture the large set of linguistic devices utilized by humans when they produce summaries. One possible explanation for the widespread use of these models is that good techniques have been developed to extract appropriate training data for them from existing document/abstract and document/headline corpora. We believe that future progress in automatic summarization will be driven both by the development of more sophisticated, linguistically informed models, as well as a more effective leveraging of document/abstract corpora. In order to open the doors to simultaneously achieving both of these goals, we have developed techniques for automatically producing word-to-word and phrase-to-phrase alignments between documents and their human-written abstracts. These alignments make explicit the correspondences that exist in such document/abstract pairs, and create a potentially rich data source from which complex summarization algorithms may learn. This paper describes experiments we have carried out to analyze the ability of humans to perform such alignments, and based on these analyses, we describe experiments for creating them automatically. Our model for the alignment task is based on an extension of the standard hidden Markov model, and learns to create alignments in a completely unsupervised fashion. We describe our model in detail and present experimental results that show that our model is able to learn to reliably identify word- and phrase-level alignments in a corpus of pairs.

cs.CL↗

arXiv2009

A Noisy-Channel Model for Document Compression

We present a document compression system that uses a hierarchical noisy-channel model of text production. Our compression system first automatically derives the syntactic structure of each sentence and the overall discourse structure of the text given as input. The system then uses a statistical hierarchical model of text production in order to drop non-important syntactic and discourse constituents so as to generate coherent, grammatical document compressions of arbitrary length. The system outperforms both a baseline and a sentence-based compression system that operates by simplifying sequentially all sentences in a text. Our results support the claim that discourse knowledge plays an important role in document summarization.

cs.CL↗

arXiv2009

A Large-Scale Exploration of Effective Global Features for a Joint Entity Detection and Tracking Model

Entity detection and tracking (EDT) is the task of identifying textual mentions of real-world entities in documents, extending the named entity detection and coreference resolution task by considering mentions other than names (pronouns, definite descriptions, etc.). Like NE tagging and coreference resolution, most solutions to the EDT task separate out the mention detection aspect from the coreference aspect. By doing so, these solutions are limited to using only local features for learning. In contrast, by modeling both aspects of the EDT task simultaneously, we are able to learn using highly complex, non-local features. We develop a new joint EDT model and explore the utility of many features, demonstrating their effectiveness on this task.

cs.CL↗

arXiv2009

A Bayesian Model for Supervised Clustering with the Dirichlet Process Prior

We develop a Bayesian framework for tackling the supervised clustering problem, the generic problem encountered in tasks such as reference matching, coreference resolution, identity uncertainty and record linkage. Our clustering model is based on the Dirichlet process prior, which enables us to define distributions over the countably infinite sets that naturally arise in this problem. We add supervision to our model by positing the existence of a set of unobserved random variables (we call these "reference types") that are generic across all clusters. Inference in our framework, which requires integrating over infinitely many parameters, is solved using Markov chain Monte Carlo techniques. We present algorithms for both conjugate and non-conjugate priors. We present a simple--but general--parameterization of our model based on a Gaussian assumption. We evaluate this model on one artificial task and three real-world tasks, comparing it against both unsupervised and state-of-the-art supervised algorithms. Our results show that our model is able to outperform other models across a variety of tasks and performance metrics.

cs.LG↗

arXiv2009

Learning as Search Optimization: Approximate Large Margin Methods for Structured Prediction

Mappings to structured output spaces (strings, trees, partitions, etc.) are typically learned using extensions of classification algorithms to simple graphical structures (eg., linear chains) in which search and parameter estimation can be performed exactly. Unfortunately, in many complex problems, it is rare that exact search or parameter estimation is tractable. Instead of learning exact models and searching via heuristic means, we embrace this difficulty and treat the structured output problem in terms of approximate search. We present a framework for learning as search optimization, and two parameter updates with convergence theorems and bounds. Empirical evidence shows that our integrated approach to learning and decoding can outperform exact models at smaller computational cost.

cs.LG↗

arXiv2009

Non-Parametric Bayesian Areal Linguistics

We describe a statistical model over linguistic areas and phylogeny. Our model recovers known areas and identifies a plausible hierarchy of areal features. The use of areas improves genetic reconstruction of languages both qualitatively and quantitatively according to a variety of metrics. We model linguistic areas by a Pitman-Yor process and linguistic phylogeny by Kingman's coalescent.

cs.CL↗

arXiv2009

Unsupervised Search-based Structured Prediction

We describe an adaptation and application of a search-based structured prediction algorithm "Searn" to unsupervised learning problems. We show that it is possible to reduce unsupervised learning to supervised learning and demonstrate a high-quality unsupervised shift-reduce parsing model. We additionally show a close connection between unsupervised Searn and expectation maximization. Finally, we demonstrate the efficacy of a semi-supervised extension. The key idea that enables this is an application of the predict-self idea for unsupervised learning.

cs.LG↗