Search

We present a detailed analysis of a graph- based annotation strategy that we employed to annotate a corpus of 11,292 real-world En- glish to Spanish automatic translations with relative (ranking) and absolute (adequate/non- adequate) quality assessments. The proposed approach, inspired by previous work in In- teractive Evolutionary Computation and Inter- active Genetic Algorithms, results in a sim- pler and faster annotation process. We em- pirically compare the method against a tra- ditional, explicit ranking approach, and show that the graph-based strategy: 1) is consider- ably faster, and 2) produces consistently more reliable annotations

In this paper, we describe the UPC system that participated in the WMT 2012 shared task on Quality Estimation for Machine Translation. Based on the empirical evidence that fluencyrelated features have a very high correlation with post-editing effort, we present a set of features for the assessment of quality estimation for machine translation designed around different kinds of n-gram language models, plus another set of features that model the quality of dependency parses automatically projected from source sentences to translations. We document the results obtained on the shared task dataset, obtained by combining the features that we designed with the baseline features provided by the task organizers.

Tree Kernel functions are powerful tools for solving different classes of problems requiring large amounts of structured information. Combined with accurate learning algorithms, such as Support Vector Machines, they allow us to directly encode rich syntactic data in our learning problems without requiring an explicit feature mapping function or deep specific domain knowledge. However, as other very high dimensional kernel families, they come with two major drawbacks: first, the computational complexity induced by the dual representation makes them unpractical for very large datasets or for situations where very fast classifiers are necessary, e.g. real time systems or web applications; second, their implicit nature somehow limits their scientific appeal, as the implicit models that we learn cannot cast new light on the studied problems. As a possible solution to these two problems, this Thesis presents an approach to feature selection for tree kernel functions in the context of Support Vector learning, based on a greedy exploration of the fragment space. Features are selected according to a gradient norm preservation criterion, i.e. we select the heaviest features that account for a large percentage of the gradient norm, and are explicitly modeled and represented. The result of the feature extraction process is a data structure that can be used to decode the input structured data, i.e. to explicitly describe a tree in terms of its more relevant fragments. We present theoretical insights that justify the adopted strategy and detail the algorithms and data structures used to explore the feature space and store the most relevant features. Experiments on three different multi-class NLP tasks and data sets, namely question classification, relation extraction and semantic role labeling, confirm the theoretical findings and show that the decoding process can produce very fast and accurate linear classifiers, along with the explicit representation of the most relevant structured features identified for each class.

Guided by multiple heuristics, a unified taxonomy of entities and categories is distilled from the Wikipedia category network. A comprehensive evaluation, based on the analysis of upward generalization paths, demonstrates that the taxonomy supports generalizations which are more than twice as accurate as the state of the art. The taxonomy is available at http://headstaxonomy.com.

This paper is concerned with the task of bilingual lexicon induction using image-based features. By applying features from a convolutional neural network (CNN), we obtain state-of-the-art performance on a standard dataset, obtaining a 79% relative improvement over previous work which uses bags of visual words based on SIFT features. The CNN image-based approach is also compared with state-of-the-art linguistic approaches to bilingual lexicon induction, even outperforming these for one of three language pairs on another standard dataset. Furthermore, we shed new light on the type of visual similarity metric to use for genuine similarity versus relatedness tasks, and experiment with using multiple layers from the same network in an attempt to improve performance. ispartof: pages:148-158 ispartof: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP 2015) pages:148-158 ispartof: 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP 2015) location:Lisbon, Portugal date:17 Sep - 21 Sep 2015 status: accepted

© 2015 Association for Computational Linguistics. Domain adaptation is a challenge for supervised NLP systems because of expensive and time-consuming manual annotated resources. We present a novel method to adapt a supervised coreference resolution system trained on newswire to short narrative stories without retraining the system. The idea is to perform inference via an Integer Linear Programming (ILP) formulation with the features of narratives adopted as soft constraints. When testing on the UMIREC1 and N22 corpora with the-stateof-the-art Berkeley coreference resolution system trained on OntoNotes3, our inference substantially outperforms the original inference on the CoNLL 2011 metric. ispartof: pages:2262-2267 ispartof: Proceedings of the 2015 conference on empirical methods in natural language processing pages:2262-2267 ispartof: The 2015 conference on empirical methods in natural language processing location:Lisbon, Portugal date:17 Sep - 21 Sep 2015 status: published