Dependency Tree Research Articles

Recognizing sentiment of relations between entities in text

Recently, sentiment analysis for identifying positive or negative opinions from texts has received much attention. In this paper, we introduce sentiment analysis into a new field, which recognizes sentiment of relations between entities in the text. Three sentiment polarities between entities are recognized, namely positive, negative, and neutral. The difficulty in this work is that several pairs of entities may appear in the same sentence, and their sentiment polarities are determined by different related regions of the sentence. In addition, different features of words and their interactions in a related region will affect the final sentiment. It is difficult to process this using rigid rule‐based methods. Therefore, we propose a machine‐learning method based on statistics. In the proposed method, the model of conditional random fields (CRFs) is used to annotate the sentiment polarity between entities with the help of the syntactic dependency tree. The string of words that connects two entities in the dependency tree is used as the related region to recognize the sentiment. Experimental results and comparison with the other methods based on different principles and related regions suggest that the proposed method shows better performance and proves its validity. Moreover, the effect of different features on the CRF is word of the ith word in the sentence. We can get a CRF model using the CRF++ tool based on feature template and training corpus. After obtaining the model, sentiment of relations could be assigned automatically. The algorithm is shown in Fig. 2. © 2014 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

Using speaker adaptive training to realize Mandarin-Tibetan cross-lingual speech synthesis

This paper presents a method to realize the hidden Markov model (HMM)-based Mandarin-Tibetan cross-lingual statistical speech synthesis using speaker adaptive training. A set of Speech Assessment Methods Phonetic Alphabet (SAMPA) is designed to label the pronunciation of the initial and the final of Mandarin and Tibetan syllables according to the similarities in pronunciation between Mandarin and Tibetan. A grapheme-to-phoneme conversion method is realized to convert Chinese or Tibetan sentences to SAMPA-based Pinyin sequences. A Mandarin statistical speech synthesis framework is employed to realize Mandarin-Tibetan cross-lingual speech synthesis. A set of context-dependent label format is designed to label the context information of Mandarin and Tibetan sentences. A question set is also realized for context dependent decision tree clustering. The initial and the finalare used as the synthesis units with training using a set of average mixed-lingual models from a large Mandarin multi-speaker-based corpus and a small Tibetan one-speaker-based corpus using speaker adaptive training (SAT). Then, the speaker adaptation transformation is applied to the speaker dependent (SD) training data to obtain a set of speaker dependent Mandarin or Tibetan models from the average mixed-lingual models. The Mandarin speech or Tibetan speech is then synthesized from the speaker dependent Mandarin or Tibetan models. Tests show that this method outperforms the method using only Tibetan SD models when only a small number of Tibetan training utterances are available. When the number of training Tibetan utterances is increased, the performances of the two methods tend to be the same. Mixed Tibetan training sentences have a small effect on the quality of synthesized Mandarin speech.

VFH*TDT (VFH* with Time Dependent Tree): A new laser rangefinder based obstacle avoidance method designed for environment with non-static obstacles

New modifications of VFH+ and VFH* (Vector Field Histogram) methods are presented in the paper. The features of the histogramic algorithms are generally improved and also using a potential of advanced sensors such as laser scanners is enabled. The main focus of the work is an introduction of modifications that provides collision-free navigation in environments with moving obstacles. For this purpose, a new approach in creating a look-ahead tree is proposed. All new modifications are analyzed and experimentally verified. The results obtained using conventional and modified methods have been compared. Experiments have demonstrated the validity and the technical feasibility of the proposed methods.

Building HMM-TTS Voices on Diverse Data

The statistical models of hidden Markov model based text-to-speech (HMM-TTS) systems are typically built using homogeneous data. It is possible to acquire data from many different sources but combining them leads to a non-homogeneous or diverse dataset. This paper describes the application of average voice models (AVMs) and a novel application of cluster adaptive training (CAT) with multiple context dependent decision trees to create HMM-TTS voices using diverse data: speech data recorded in studios mixed with speech data obtained from the internet. Training AVM and CAT models on diverse data yields better quality speech than training on high quality studio data alone. Tests show that CAT is able to create a voice for a target speaker with as little as 7 seconds; an AVM would need more data to reach the same level of similarity to target speaker. Tests also show that CAT produces higher quality voices than AVMs irrespective of the amount of adaptation data. Lastly, it is shown that it is beneficial to model the data using multiple context clustering decision trees.

Mining Large-scale Event Knowledge from Web Text

This paper addresses the problem of automatic acquisition of semantic relations between events. While previous works on semantic relation automatic acquisition relied on annotated text corpus, it is still unclear how to develop more generic methods to meet the needs of identifying related event pairs and extracting event-arguments (especially the predicate, subject and object). Motivated by this limitation, we develop a three-phased approach that acquires causality from the Web text. First, we use explicit connective markers (such as “because”) as linguistic cues to discover causal related events. Next, we extract the event-arguments based on local dependency parse trees of event expressions. At the last step, we propose a statistical model to measure the potential causal relations. The results of our empirical evaluations on a large-scale Web text corpus show that (a) the use of local dependency tree extensively improves both the accuracy and recall of event-arguments extraction task, and (b) our measure improves the traditional PMI method.

Arc-Eager Parsing with the Tree Constraint

The arc-eager system for transition-based dependency parsing is widely used in natural language processing despite the fact that it does not guarantee that the output is a well-formed dependency tree. We propose a simple modification to the original system that enforces the tree constraint without requiring any modification to the parser training procedure. Experiments on multiple languages show that the method on average achieves 72% of the error reduction possible and consistently outperforms the standard heuristic in current use.

A Novel Reordering Model for Statistical Machine Translation

Word reordering is one of the fundamental problems of machine translation, and an important factor of its quality and efficiency. In this paper, we introduce a novel reordering model based on an innovative structure, named, phrasal dependency tree including syntactical and statistical information in context of a log-linear model. The phrasal dependency tree is a new modern syntactic structure based on dependency relations between contiguous non- syntactic phrases. In comparison with well-known and popular reordering models such as the distortion, lexicalized and hierarchical models, the experimental study demonstrates the superiority of our model regarding to the different evaluation measures. We evaluated the proposed model on a PersianEnglish SMT system. On average our model retrieved a significant impact on precision with comparable recall value respect to the lexicalized and distortion models, and is found to be effective for medium and long-distance reordering.

Finding Optimal 1-Endpoint-Crossing Trees

Dependency parsing algorithms capable of producing the types of crossing dependencies seen in natural language sentences have traditionally been orders of magnitude slower than algorithms for projective trees. For 95.8–99.8% of dependency parses in various natural language treebanks, whenever an edge is crossed, the edges that cross it all have a common vertex. The optimal dependency tree that satisfies this 1-Endpoint-Crossing property can be found with an O( n4) parsing algorithm that recursively combines forests over intervals with one exterior point. 1-Endpoint-Crossing trees also have natural connections to linguistics and another class of graphs that has been studied in NLP.

Automatic generation of multiple choice questions using dependency-based semantic relations

In this paper, we present an unsupervised dependency-based approach to extract semantic relations to be applied in the context of automatic generation of multiple choice questions (MCQs). MCQs also known as multiple choice tests provide a popular solution for large-scale assessments as they make it much easier for test-takers to take tests and for examiners to interpret their results. Manual generation of MCQs is a very expensive and time-consuming task and yet they often need to be produced on a large scale and within short iterative cycles. We approach the problem of automated MCQ generation with the help of unsupervised relation extraction, a technique used in a number of related natural language processing problems. The goal of Unsupervised relation extraction is to identify the most important named entities and terminology in a document and then recognise semantic relations between them, without any prior knowledge as to the semantic types of the relations or their specific linguistic realisation. We use these techniques to process instructional texts and identify those facts (terminology, entities, and semantic relations between them) that are likely to be important for assessing test-takers' familiarity with the instructional material. We investigate an approach to learn semantic relations between named entities by employing a dependency tree model. Our findings show that an optimised configuration of our MCQ generation system is capable of attaining high precision rates, which are much more important than recall in the automatic generation of MCQs. We also carried out a user-centric evaluation of the system, where subject domain experts evaluated automatically generated MCQ items in terms of readability, usefulness of semantic relations, relevance, acceptability of questions and distractors and overall MCQ usability. The results of this evaluation make it possible for us to draw conclusions about the utility of the approach in practical e-Learning applications.

Segmentation of Target Nuclei in Parkinson's Disease Based on Fuzzy Connectedness

With the development of nerve stereotactic technology, brain stereotactic surgery has become an effective method for the current treatment of Parkinson's disease. The accurate localization of the target nuclei is the key issue of the treatment. In this paper, we constructed a dependence tree model to identify the target nuclei further. Theory of fuzzy connectedness was used in the segmentation. Experimental results show it was more desirable and suitable to the clinical applications.

Attribution in Turkish with Dependency Tree Analyses

In the general system of the natural tongues, attribution, which undertakes the function of cluster restriction and cluster equipment, can be categorized in two main groups, namely, noun phrases and subordinate clauses. The process of cluster restriction is realized by way of the reduction of the number of elements in the cluster, to which a concept has been attributed, based on a certain characteristic. In the function of cluster equipment, the dimensions of a given concept remain unchanged. However, this concept can be enriched through a number additional attribution to be equipped. Noun phrases are determinative phrases, which report no judgement and which are constructed from more than one word aggregated around a head noun. In the general sequence of Turkish language, the simplest attributive phrase is the adjective phrase made up of adjective and noun. An adjective ascribes some property, quality or status to the entity denoted by a noun. When adjectives attribute nouns, they become attributive adjectives, and when they attribute the action they become adverbs of manner. Relative clauses with adjectival function are complicated structures which attribute noun phrases, and they are generally constructed by taking participle suffixes like -(y)An, DIK (-DIgI), mIs, or -(y)AcAK (-EcEgI). Relative clauses precede the noun phrase they modify, in the same way that adjectives precede the noun they modify. In this study an argument has been made about how the attributive functions of noun phrases and subordinating clauses are realized, and the structural characteristics of attribution in Turkish in the context of dependency model (dependency tree) developed by Tesniere’s Dependency Grammar Theory have been investigated.

Regression analysis using dependent Polya trees

Many commonly used models for linear regression analysis force overly simplistic shape and scale constraints on the residual structure of data. We propose a semiparametric Bayesian model for regression analysis that produces data-driven inference by using a new type of dependent Polya tree prior to model arbitrary residual distributions that are allowed to evolve across increasing levels of an ordinal covariate (e.g., time, in repeated measurement studies). By modeling residual distributions at consecutive covariate levels or time points using separate, but dependent Polya tree priors, distributional information is pooled while allowing for broad pliability to accommodate many types of changing residual distributions. We can use the proposed dependent residual structure in a wide range of regression settings, including fixed-effects and mixed-effects linear and nonlinear models for cross-sectional, prospective, and repeated measurement data. A simulation study illustrates the flexibility of our novel semiparametric regression model to accurately capture evolving residual distributions. In an application to immune development data on immunoglobulin G antibodies in children, our new model outperforms several contemporary semiparametric regression models based on a predictive model selection criterion.

Exploiting Tree Decomposition for Guiding Neighborhoods Exploration for VNS

Tree decomposition introduced by Robertson and Seymour aims to decompose a problem into clusters constituting an acyclic graph. There are works exploiting tree decomposition for complete search methods. In this paper, we show how tree decomposition can be used to efficiently guide local search methods that use large neighborhoods like VNS. We propose DGVNS (Decomposition Guided VNS) which uses the graph of clusters in order to build neighborhood structures enabling better diversification and intensification. Second, we introduce tightness dependent tree decomposition which allows to take advantage of both the structure of the problem and the constraints tightness. Third, experiments performed on random instances (GRAPH) and real life instances (CELAR, SPOT5 and tagSNP) show the appropriateness and the efficiency of our approach. Moreover, we study and discuss the influence of the width of the tree decomposition on our approach and the relevance of removing clusters with very few proper variables from the tree decomposition.

Flexible Disambiguation and Expressive Completeness in Dependency Tree Semantics

This paper proposes an extension of Dependency Tree Semantics (DTS), an underspecified formalism originally proposed in Robaldo (2007). The crucial advantage of DTS as compared to other contemporary proposals is its ability to represent Independent Set (IS) readings (a.k.a. scopeless readings), e.g. cumulative and collective readings. DTS achieves the expressivity needed to represent IS readings because it underspecifies Skolem-like functional dependencies. This paper extends DTS by introducing additional meta-constraints in First-Order Logic dedicated to disambiguating underspecified structures. However, it is worth noting that the meta-constraints are independent from DTS, and could be easily re-implemented in any underspecified theory. The meta-constraints achieve flexible disambiguation, in the sense that they allow ambiguous structures to be specified independently of the linguistic (rather than logical) knowledge used. Secondly, DTS, equipped with the meta-constraints, becomes an expressively complete formalism in the sense of Ebert (2005). Expressive completeness is a desirable property for an underspecified formalism, because it allows a representation for each possible subset of available readings.

Programmability and portability for exascale: Top down programming methodology and tools with StarSs

StarSs is a task-based programming model that allows to parallelize sequential applications by means of annotating the code with compiler directives. The model further supports transparent execution of designated tasks on heterogeneous platforms, including clusters of GPUs. This paper focuses on the methodology and tools that complements the programming model forming a consistent development environment with the objective of simplifying the live of application developers.The programming environment includes the tools TAREADOR and TEMANEJO, which have been designed specifically for StarSs. TAREADOR, a Valgrind-based tool, allows a top-down development approach by assisting the programmer in identifying tasks and their data-dependencies across all concurrency levels of an application. TEMANEJO is a graphical debugger supporting the programmer by visualizing the task dependency tree on one hand, but also allowing to manipulate task scheduling or dependencies. These tools are complemented with a set of performance analysis tools (Scalasca, Cube and Paraver) that enable to fine tune StarSs application.

Efficient Parsing for Head-Split Dependency Trees

Head splitting techniques have been successfully exploited to improve the asymptotic runtime of parsing algorithms for projective dependency trees, under the arc-factored model. In this article we extend these techniques to a class of non-projective dependency trees, called well-nested dependency trees with block-degree at most 2, which has been previously investigated in the literature. We define a structural property that allows head splitting for these trees, and present two algorithms that improve over the runtime of existing algorithms at no significant loss in coverage.

Going to the Roots of Dependency Parsing

Dependency trees used in syntactic parsing often include a root node representing a dummy word prefixed or suffixed to the sentence, a device that is generally considered a mere technical convenience and is tacitly assumed to have no impact on empirical results. We demonstrate that this assumption is false and that the accuracy of data-driven dependency parsers can in fact be sensitive to the existence and placement of the dummy root node. In particular, we show that a greedy, left-to-right, arc-eager transition-based parser consistently performs worse when the dummy root node is placed at the beginning of the sentence (following the current convention in data-driven dependency parsing) than when it is placed at the end or omitted completely. Control experiments with an arc-standard transition-based parser and an arc-factored graphbased parser reveal no consistent preferences but nevertheless exhibit considerable variation in results depending on root placement. We conclude that the treatment of dummy root nodes in data-driven dependency parsing is an underestimated source of variation in experiments andmay also be a parameter worth tuning for some parsers.

Divisible Transition Systems and Multiplanar Dependency Parsing

Transition-based parsing is a widely used approach for dependency parsing that combines high efficiency with expressive feature models. Many different transition systems have been proposed, often formalized in slightly different frameworks. In this article, we show that a large number of the known systems for projective dependency parsing can be viewed as variants of the same stack-based system with a small set of elementary transitions that can be composed into complex transitions and restricted in different ways. We call these systems divisible transition systems and prove a number of theoretical results about their expressivity and complexity. In particular, we characterize an important subclass called efficient divisible transition systems that parse planar dependency graphs in linear time. We go on to show, first, how this system can be restricted to capture exactly the set of planar dependency trees and, secondly, how the system can be generalized to k-planar trees by making use of multiple stacks. Using the first known efficient test for k-planarity, we investigate the coverage of k-planar trees in available dependency treebanks and find a very good fit for 2-planar trees. We end with an experimental evaluation showing that our 2-planar parser gives significant improvements in parsing accuracy over the corresponding 1-planar and projective parsers for data sets with non-projective dependency trees and performs on a par with the widely used arc-eager pseudo-projective parser.

Asynchronous Approach to Memory Management in Sparse Multifrontal Methods on Multiprocessors

This research covers the Intel? Direct Sparse Solver for Clusters, the software that implements a direct method for solving the Ax = b equation with sparse symmetric matrix A on a cluster. This method, researched by Intel, is based on Cholesky decomposition and could be considered as extension of functionality PARDISO from Intel? MKL. To achieve an efficient work balance on a large number of processes, the so-called “multifrontal” approach to Cholesky decomposition is implemented. This software implements parallelization that is based on nodes of the dependency tree and uses MPI, as well as parallelization inside a node of the tree that uses OpenMP directives. The article provides a high-level description of the algorithm to distribute the work between both computational nodes and cores within a single node, and between different computational nodes. A series of experiments shows that this implementation causes no growth of the computational time and decreases the amount of memory needed for the computations.

Catenae: Introducing a Novel Unit of Syntactic Analysis

Abstract. This paper introduces a novel unit of syntactic analysis, the catena (Latin for ‘chain’; plural catenae). The catena is defined in a dependency‐based grammar as a word or a combination of words that is continuous with respect to dominance. According to this definition, any dependency tree or any subtree (complete or partial) of a dependency tree qualifies as a catena. The paper demonstrates that idioms are stored as catenae and that the elided material of ellipsis mechanisms (e.g., answer fragments, gapping, stripping, VP ellipsis, pseudogapping, sluicing, and comparative deletion) is a catena. Constituents are always catenae, but many catenae are not constituents. Based on the flexibility and utility of the catena concept, the claim is put forth and defended that the catena is the fundamental unit of syntax, not the constituent.