Dependency Tree Research Articles

Goal-oriented dependency analysis for service identification

Highly mature service-oriented architecture systems have great flexibility and reusability, and can align business processes and information technologies with high quality. Service identification plays a key role in this respect. Further, of the different methods employed, the most popular and preferred is process-oriented service identification. However, the absence of dependency analysis in the business process management domain remains a challenge for the quality of future systems. In this paper, we propose a goal-oriented dependency analysis for service identification via business process modeling. In our analysis solution, we apply a dependency tree featuring the relationships among requirements. The dependency relations are analyzed to create business processes via scenarios comprising requirements and process fragments.

Feature Fusion for Negation Scope Detection in Sentiment Analysis: Comprehensive Analysis over Social Media

Negation control for sentiment analysis is essential and effective decision support system. Negation control include identification of negation cues, scope of negation and their influence within it. Negation can either shift or change the polarity score of opinionated word. This paper present a framework for feature fusion of text feature extraction, negation cue and scope detection technique for enhancing the performance of recent sen-timent classifier for negation control. Explore text feature POS, BOW and HT with negation cue and scope detection techniques for classification technique over social media data set. This paper has included the evaluation of sentiment classification (Support vector machine, Navies Bayes, Linear Regression and Random Forest) and Nine feature fusion over presented prepossessing framework. This paper yield interesting result about collective response of feature fusion for negation scope detection and clas-sification technique. Feature Fusion vector significantly increase the polarity classification accuracy of sentiment classification technique. POS with Grammatical dependency tree can detect negation with better accuracy as compared to other feature fusion.

Mining layered technological information in scientific papers: A semi-supervised method

Tech mining is the application of text mining tools to science and technology information resources. The ever-increasing volume of scientific outputs is a boom to technological innovation, but it also complicates efforts to obtain useful and concise information for problem solving. This challenge extends to tech mining, where the development of techniques compatible with big data is an urgent issue. This article introduces a semi-supervised method for extracting layered technological information from scientific papers in order to extend the reach of tech mining. Our method starts with several pre-set seed patterns used to extract candidate phrases by matching the dependency tree of each sentence. Then, after a series of judgements, phrases are divided into two categories: ‘main technique’ and ‘tech-component’. (A technique, for the purposes of this study, is a method or tool used in the article being analysed.) In order to generate new patterns for subsequent iterations, a weighted pattern learning method is also adopted. Finally, multiple iterations of the method are applied to extract technological information from each paper. A dataset from the field of optical switcher is used to verify the method’s effectiveness. Our findings are that (1) by two loops of extraction process in each iteration, our method realises the layered technological information extraction, which contains the ‘part–whole’ relationships between main techniques and tech-components; (2) the recall rate for main techniques is superior to the baseline after iterating 23 rounds; (3) when layering is disregarded, in the aspect of the precision and the volume of techniques, the new method is higher than that for the baseline; and (4) adjusting another two parameters can optimise the efficiency – however, the effect is neither pronounced nor straightforward.

Improving short-text representation in convolutional networks by dependency parsing

Automatic question answering (QA) system is the inevitable trend of future search engines. As the essential steps of QA, question classification and text retrieval both require algorithms to capture the semantic information and syntactic structure of natural language. This paper proposes dependency-based convolutional networks to learn a representation of sentences. First, we use dependency layer to map discrete word depth on the dependency tree of a sentence into continuous real space. Then, the mapping result serves as weight of word vectors and convolutional kernels are employed as feature extractors for further specific tasks. The method proposed allows convolutional networks to take the advantage of higher representational ability of dependency structure. Experiments involving three tasks including text classification, duplicate classification and text pairs ranking confirm the advantages of our model.

Shallow and Deep Syntactic/Semantic Structures for Passage Reranking in Question-Answering Systems

In this article, we extensively study the use of syntactic and semantic structures obtained with shallow and full syntactic parsers for answer passage reranking. We propose several dependency and constituent-based structures, also enriched with Linked Open Data (LD) knowledge to represent pairs of questions and answer passages. We encode such tree structures in learning-to-rank (L2R) algorithms using tree kernels, which can project them in tree substructure spaces, where each dimension represents a powerful syntactic/semantic feature. Additionally, since we define links between question and passage structures, our tree kernel spaces also include relational structural features. We carried out an extensive comparative experimentation of our models for automatic answer selection benchmarks on different TREC QA corpora as well as the newer Wikipedia-based dataset, namely WikiQA, which has been widely used to test sentence rerankers. The results consistently demonstrate that our structural semantic models achieve the state of the art in passage reranking. In particular, we derived the following important findings: (i) relational syntactic structures are essential to achieve superior results; (ii) models trained with dependency trees can outperform those trained with shallow trees, e.g., in case of sentence reranking; (iii) external knowledge automatically generated with focus and question classifiers is very effective; and (iv) the semantic information derived by LD and incorporated in syntactic structures can be used to replace the knowledge provided by the above-mentioned classifiers. This is a remarkable advantage as it enables our models to increase coverage and portability over new domains.

Automatic Classification of Online Doctor Reviews: Evaluation of Text Classifier Algorithms.

BackgroundAn increasing number of doctor reviews are being generated by patients on the internet. These reviews address a diverse set of topics (features), including wait time, office staff, doctor’s skills, and bedside manners. Most previous work on automatic analysis of Web-based customer reviews assumes that (1) product features are described unambiguously by a small number of keywords, for example, battery for phones and (2) the opinion for each feature has a positive or negative sentiment. However, in the domain of doctor reviews, this setting is too restrictive: a feature such as visit duration for doctor reviews may be expressed in many ways and does not necessarily have a positive or negative sentiment.ObjectiveThis study aimed to adapt existing and propose novel text classification methods on the domain of doctor reviews. These methods are evaluated on their accuracy to classify a diverse set of doctor review features.MethodsWe first manually examined a large number of reviews to extract a set of features that are frequently mentioned in the reviews. Then we proposed a new algorithm that goes beyond bag-of-words or deep learning classification techniques by leveraging natural language processing (NLP) tools. Specifically, our algorithm automatically extracts dependency tree patterns and uses them to classify review sentences.ResultsWe evaluated several state-of-the-art text classification algorithms as well as our dependency tree–based classifier algorithm on a real-world doctor review dataset. We showed that methods using deep learning or NLP techniques tend to outperform traditional bag-of-words methods. In our experiments, the 2 best methods used NLP techniques; on average, our proposed classifier performed 2.19% better than an existing NLP-based method, but many of its predictions of specific opinions were incorrect.ConclusionsWe conclude that it is feasible to classify doctor reviews. Automatically classifying these reviews would allow patients to easily search for doctors based on their personal preference criteria.

Non-configurationality in diachrony

Abstract Non-configurationality is a linguistic property associated with free word order, discontinuous constituents, including NPs, and null anaphora of referential arguments. Quantitative metrics, based both on local networks (syntactic trees and word order within sentences) and on global networks (incorporating the relations within a whole treebank into a shared graph), can reveal correlations among these features. Using treebanks we focus on diachronic varieties of Ancient Greek and Latin, in which non-configurationality tapered off over time, leading to the largely configurational nature of the Romance languages and of Modern Greek. A property of global networks (density of their spectra around zero eigenvalues) measuring the regularity in word order is shown to be strengthened from classical to late varieties. Discontinuous NPs are traced by counting the words creating non-projectivity in dependency trees: these drop dramatically in late varieties. Finally, developments in the use of null referential direct objects are gauged by assessing the percentage of third-person personal pronouns among verb objects. All three features turn out to change over time due to the decay of non-configurationality. Evaluation of the strength of their pairwise correlation shows that null direct objects and discontinuous NPs are deeply intertwined.

Dependency-to-Dependency Neural Machine Translation

Recent research has proven that syntactic knowledge is effective to improve the performance of neural machine translation (NMT). Most previous work focuses on leveraging either source or target syntax in the recurrent neural network (RNN) based encoder–decoder model. In this paper, we simultaneously use both source and target dependency tree to improve the NMT model. First, we propose a simple but effective syntax-aware encoder to incorporate source dependency tree into NMT. The new encoder enriches each source state with dependence relations from the tree. Then, we propose a novel sequence-to-dependence framework. In this framework, the target translation and its corresponding dependence tree are jointly constructed and modeled. During decoding, the tree structure is used as context to facilitate word generations. Finally, we extend the sequence-to-dependence framework with the syntax-aware encoder to build a dependence-NMT model and apply the dependence-based framework to the Transformer. Experimental results on several translation tasks show that both source and target dependence structures can improve the translation quality and their effects can be accumulated.

A neural reordering model based on phrasal dependency tree for statistical machine translation

A neural reordering model based on phrasal dependency tree for statistical machine translation

A Systematic Methodology Based on Word Embedding for Identifying the Relation Between Online Customer Reviews and Sales Rank

In the buying decision process, online reviews become an important source of information. They become the basis of evaluating alternatives before making purchase decision. This paper proposes a methodology to reveal one of the hidden alternative evaluation processes by identifying the relation between the observable online customer reviews and sales rank. This methodology applies a combined approach of word embedding (word2vec) and X-means clustering, which produces product-feature words. It is followed by identifying sentiment words and their intensity, determining connection of words from dependency tree, and finally relating variables from the reviews to the sales rank of a product by a regression model. The methodology is applied to two data sets of wearable technology and laptop products. As implied by the high predicted R-squared values, the models are generalizable into new data sets. Among the interesting findings are the statements of problems or issues of a product are related to better sales rank, and many product features that are mentioned in the review title are significantly related to sales rank. For product designers, the significant variables in the regression models suggest the possible product features to be improved.

TEITOK as a tool for Dependency Grammar

TEITOK is an online platform for visualizing, searching, and editing TEI-based corpora. TEITOK has a modular set-up, and amongst other things provides an interface to easily add dependency relations to a tokenized TEI document, and provides the option to visualize the dependency trees, edit them, and search through the corpus using dependency relations.

Koko

K oko is a declarative information extraction system that incorporates advances in natural language processing techniques in its extraction language. K oko 's extraction language supports simultaneous specification of conditions over the surface syntax and on the structure of the dependency parse tree of sentences, thereby allowing for more refined extractions. Furthermore, the K oko extraction language allows for aggregating evidence from an input document and supports conditions that are tolerant of linguistic variation of expressing concepts. In this demo, we outline the design of K oko , a system for extracting information and understanding the results of the extraction. K oko provides an interactive interface that allows participants to write queries, understand the input and results of the queries. In particular, the user can customize the input text, visualize the input text's dependency parse trees, and understand the correspondences between query components, dependency tree nodes, text tokens, and the computation and associated scores that led to an extraction.

Chemical-induced disease relation extraction with dependency information and prior knowledge

Chemical-disease relation (CDR) extraction is significantly important to various areas of biomedical research and health care. Nowadays, many large-scale biomedical knowledge bases (KBs) containing triples about entity pairs and their relations have been built. KBs are important resources for biomedical relation extraction. However, previous research pays little attention to prior knowledge. In addition, the dependency tree contains important syntactic and semantic information, which helps to improve relation extraction. So how to effectively use it is also worth studying. In this paper, we propose a novel convolutional attention network (CAN) for CDR extraction. Firstly, we extract the shortest dependency path (SDP) between chemical and disease pairs in a sentence, which includes a sequence of words, dependency directions, and dependency relation tags. Then the convolution operations are performed on the SDP to produce deep semantic dependency features. After that, an attention mechanism is employed to learn the importance/weight of each semantic dependency vector related to knowledge representations learned from KBs. Finally, in order to combine dependency information and prior knowledge, the concatenation of weighted semantic dependency representations and knowledge representations is fed to the softmax layer for classification. Experiments on the BioCreative V CDR dataset show that our method achieves comparable performance with the state-of-the-art systems, and both dependency information and prior knowledge play important roles in CDR extraction task.

Prosodic boundary detection using syntactic and acoustic information

This paper presents a two-stage procedure for automatic prosodic boundary detection in Russian based on textual and acoustic data. The key idea of the method is (1) to predict all potential prosodic boundaries based on syntax and (2) among these potential boundaries, to choose those which are marked acoustically. For the first stage we developed a system which predicted a potential boundary whenever two adjacent words were not connected with each other in terms of syntax; for this we used a dependency tree parser and added several simple rules. At the second stage we run a random forest classifier to detect the actual prosodic boundaries using a small set of acoustic features. Of all the observed prosodic features pause duration worked best, and for some speakers it could be used as the only acoustic cue with no change in efficiency. For other speakers, however, other features were useful, such as tempo and amplitude resets or F0 range, and the choice of the features was speaker-dependent. In the end the procedure worked with the F1 measure of 0.91, recall of 0.90 and precision of 0.93, which is the best published result for Russian.

A Novel Statistical Cost Model and an Algorithm for Efficient Application Offloading to Clouds

This work presents a novel statistical cost model for applications that can be offloaded to cloud computing environments. The model constructs a tree structure, referred to as the execution dependency tree (EDT), to accurately represent various execution relations, or dependencies (e.g., sequential, parallel and conditional branching) among the application modules, along its different execution paths. Contrary to existing models that assume fixed average offloading costs, each module’s cost is modelled as a random variable described by its Cumulative Distribution Function (CDF) that is statistically estimated through application profiling. Using this model, we generalize the offloading cost optimization functions to those that use more user tailored statistical measures such as cost percentiles. We employ these functions to propose an efficient offloading algorithm based on a dynamic programming formulation. We also show that the proposed model can be used as an efficient tool for application analysis by developers to gain insights on the applications’ statistical performance under varying network conditions and users behaviours. Performance evaluation results show that the achieved mean absolute percentage error between the model-based estimated cost and the measured one for the application execution time can be as small as $5$ percent for applications with sequential and branching module dependencies.

Semantic Matching Similarity Algorithm Based on Dependency Trees

The measure of semantic matching similarity is widely used in question answering system, knowledge discovery, search engine and other fields. This paper presents a semantic matching similarity algorithm based on dependency trees, through the analysis of statements to generate a new dependent tree model. Through experimental analysis, our algorithm has a better correct rates as compared to the traditional algorithm at a reasonable weight.

A Dependency Perspective on RST Discourse Parsing and Evaluation

Computational text-level discourse analysis mostly happens within Rhetorical Structure Theory (RST), whose structures have classically been presented as constituency trees, and relies on data from the RST Discourse Treebank (RST-DT); as a result, the RST discourse parsing community has largely borrowed from the syntactic constituency parsing community. The standard evaluation procedure for RST discourse parsers is thus a simplified variant of PARSEVAL, and most RST discourse parsers use techniques that originated in syntactic constituency parsing. In this article, we isolate a number of conceptual and computational problems with the constituency hypothesis. We then examine the consequences, for the implementation and evaluation of RST discourse parsers, of adopting a dependency perspective on RST structures, a view advocated so far only by a few approaches to discourse parsing. While doing that, we show the importance of the notion of headedness of RST structures. We analyze RST discourse parsing as dependency parsing by adapting to RST a recent proposal in syntactic parsing that relies on head-ordered dependency trees, a representation isomorphic to headed constituency trees. We show how to convert the original trees from the RST corpus, RST-DT, and their binarized versions used by all existing RST parsers to head-ordered dependency trees. We also propose a way to convert existing simple dependency parser output to constituent trees. This allows us to evaluate and to compare approaches from both constituent-based and dependency-based perspectives in a unified framework, using constituency and dependency metrics. We thus propose an evaluation framework to compare extant approaches easily and uniformly, something the RST parsing community has lacked up to now. We can also compare parsers’ predictions to each other across frameworks. This allows us to characterize families of parsing strategies across the different frameworks, in particular with respect to the notion of headedness. Our experiments provide evidence for the conceptual similarities between dependency parsers and shift-reduce constituency parsers, and confirm that dependency parsing constitutes a viable approach to RST discourse parsing.

A preordering model based on phrasal dependency tree

A preordering model based on phrasal dependency tree

Tree-Structured Neural Machine for Linguistics-Aware Sentence Generation

Different from other sequential data, sentences in natural language are structured by linguistic grammars. Previous generative conversational models with chain-structured decoder ignore this structure in human language and might generate plausible responses with less satisfactory relevance and fluency. In this study, we aim to incorporate the results from linguistic analysis into the process of sentence generation for high-quality conversation generation. Specifically, we use a dependency parser to transform each response sentence into a dependency tree and construct a training corpus of sentence-tree pairs. A tree-structured decoder is developed to learn the mapping from a sentence to its tree, where different types of hidden states are used to depict the local dependencies from an internal tree node to its children. For training acceleration, we propose a tree canonicalization method, which transforms trees into equivalent ternary trees. Then, with a proposed tree-structured search method, the model is able to generate the most probable responses in the form of dependency trees, which are finally flattened into sequences as the system output. Experimental results demonstrate that the proposed X2Tree framework outperforms baseline methods over 11.15% increase of acceptance ratio.

SEE: Syntax-Aware Entity Embedding for Neural Relation Extraction

Distant supervised relation extraction is an efficient approach to scale relation extraction to very large corpora, and has been widely used to find novel relational facts from plain text. Recent studies on neural relation extraction have shown great progress on this task via modeling the sentences in low-dimensional spaces, but seldom considered syntax information to model the entities. In this paper, we propose to learn syntax-aware entity embedding for neural relation extraction. First, we encode the context of entities on a dependency tree as sentence-level entity embedding based on tree-GRU. Then, we utilize both intra-sentence and inter-sentence attentions to obtain sentence set-level entity embedding over all sentences containing the focus entity pair. Finally, we combine both sentence embedding and entity embedding for relation classification. We conduct experiments on a widely used real-world dataset and the experimental results show that our model can make full use of all informative instances and achieve state-of-the-art performance of relation extraction.