Parsing System Research Articles

Robust Rule-based Approach in Arabic Processing

parsing system is a key element of many computer applications such as Information Retrieval, Knowledge Extraction and automatic translation. This paper presents a robust large-scale parser system for parsing Arabic sentences. From a practical point of view, the system is able to analyze real-world sentences thanks to a wide coverage of its linguistic knowledge that is realized within the DIINAR-MBC European project 1 . The parser is designed for robustness against difficult input that cannot be parsed correctly according to the standard grammar rules in the system, whether it is an extra-grammatical, ill-formed or unexpected input. Most systems use algorithmic approaches to robustness where parsing programs are extended to include heuristics to handle defect cases. This study adopts another solution based on a robust grammar-based approach for parsing. It consists of introducing robust rules in the grammar itself and relaxing constraints if necessary. The parser has been evaluated against real-world sentences and the results were very encouraging. The parser provides 95% coverage.

Joint Video and Text Parsing for Understanding Events and Answering Queries

This article proposes a multimedia analysis framework to process video and text jointly for understanding events and answering user queries. The framework produces a parse graph that represents the compositional structures of spatial information (objects and scenes), temporal information (actions and events), and causal information (causalities between events and fluents) in the video and text. The knowledge representation of the framework is based on a spatial-temporal-causal AND-OR graph (S/T/C-AOG), which jointly models possible hierarchical compositions of objects, scenes, and events as well as their interactions and mutual contexts, and specifies the prior probabilistic distribution of the parse graphs. The authors present a probabilistic generative model for joint parsing that captures the relations between the input video/text, their corresponding parse graphs, and the joint parse graph. Based on the probabilistic model, the authors propose a joint parsing system consisting of three modules: video parsing, text parsing, and joint inference. Video parsing and text parsing produce two parse graphs from the input video and text, respectively. The joint inference module produces a joint parse graph by performing matching, deduction, and revision on the video and text parse graphs. The proposed framework has the following objectives: to provide deep semantic parsing of video and text that goes beyond the traditional bag-of-words approaches; to perform parsing and reasoning across the spatial, temporal, and causal dimensions based on the joint S/T/C-AOG representation; and to show that deep joint parsing facilitates subsequent applications such as generating narrative text descriptions and answering queries in the forms of who, what, when, where, and why. The authors empirically evaluated the system based on comparison against ground-truth as well as accuracy of query answering and obtained satisfactory results.

MaltOptimizer: Fast and effective parser optimization

AbstractStatistical parsers often require careful parameter tuning and feature selection. This is a nontrivial task for application developers who are not interested in parsing for its own sake, and it can be time-consuming even for experienced researchers. In this paper we present MaltOptimizer, a tool developed to automatically explore parameters and features for MaltParser, a transition-based dependency parsing system that can be used to train parser's given treebank data. MaltParser provides a wide range of parameters for optimization, including nine different parsing algorithms, an expressive feature specification language that can be used to define arbitrarily rich feature models, and two machine learning libraries, each with their own parameters. MaltOptimizer is an interactive system that performs parser optimization in three stages. First, it performs an analysis of the training set in order to select a suitable starting point for optimization. Second, it selects the best parsing algorithm and tunes the parameters of this algorithm. Finally, it performs feature selection and tunes machine learning parameters. Experiments on a wide range of data sets show that MaltOptimizer quickly produces models that consistently outperform default settings and often approach the accuracy achieved through careful manual optimization.

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.

Distributed and Parallel Big Textual Data Parsing for Social Sensor Network

Recently, due to the popularization of the smartphone and social network service (SNS), many SNS users write their opinions for social events. According to these social phenomena, social sensor network which analyzes social events by utilizing those users' text data is proposed. Parsing is essential module to analyze user's text contents because it gives the understanding of semantics by extracting the words and their classes from texts. However, parsing requires much time because it needs to analyze all context information from the users' text. In addition, as users' text data are generated and transferred in streaming, the required parsing time increases too. This situation occurs that it is hard to parse the text on the single machine. Therefore, to drastically enhance the parsing speed, we propose distributed and parallel parsing system on the MapReduce. It applies the legacy parser to the MapReduce through loose coupling. Also, to reduce communication overheads, the statistical model used by the parser is resided on local cache in each mapper. The experimental result shows that the speed of proposed system is 2–19 times better than that of the legacy parser. As a result, we prove that the proposed system is useful for parsing text data in social sensor network.

Parse views with Boolean grammars

We propose an enhancement to current parsing and transformation systems by leveraging the expressive power of Boolean grammars, a generalization of context-free grammars that adds conjunction and negation operators. In addition to naturally expressing a larger class of languages, Boolean grammars capture multiple parse trees of the same document simultaneously and the ability to switch between these parse “views”. In particular, source transformation and reengineering tasks can benefit from parse views by recasting the input text into whichever parse is most suitable for the task at hand.

Advanced news video parsing via visual characteristics of anchorperson scenes

In this paper, we present an advanced news video parsing system via exploring the visual characteristics of anchorperson scenes, which aims to provide personalized news services over Internet or mobile platforms. As the anchorperson shots serve as the root shots for constructing news video, the addressed system firstly performs anchorperson detection which divides the news into several segments. Due to the manipulation of multi-features and post-processing, our method of anchorperson detection can even be efficiently applied to news video whose anchorperson scenes are most challenging and complicated. Usually, the segments produced from anchorperson detection are regarded as news stories. However, an observation in our database proves this is not true because of the existing of interview scenes. These interview scenes are showed in the form that interviewer (anchorperson) and interviewee recursively appear. Thus, a technique called interview clustering based on face similarity is carried out to merge these interview segments. Another novel aspect of our system is entity summarization of interview scenes. We adopt it in the system at final. The effectiveness and robustness of the proposed system are demonstrated by the evaluation on 19 hours of news programs from 6 different TV Channels.

구간 분할과 논항정보를 이용한 구문분석시스템 구현에 관한 연구

본 논문에서는 한국어 구문분석에서 발생하는 중의성을 해결하기 위하여 구간분할 방법과 논항정보를 사용하여 개선한 구문분석시스템을 소개한다. 본 논문에서 제안하는 구문분석 시스템은 어절대신 형태소를 입력으로 사용하고, 또한 주어진 형태소에 대하여 가능한 모든 구문 분석 구조를 생성하는 알고리즘을 사용한다. 따라서 많은 중의성을 포함한 구문 분석 결과를 생성한다. 이러한 중의성 구조 결과를 해결하기 위하여 세 가지 방법을 사용했다. 첫째 방법은 형태소분석 결과에서 중의성을 제거하는 방법이고 두 번째는 구문 분석시 구간 분할하는 방법, 세 번째 방법은 논항정보를 이용하는 것이다. 이러한 방법을 사용하여 많은 중의성을 제거할 수 있었다. 실험을 통하여 약 53%의 중의성을 제거할 수 있었음을 보여준다. One of the most important problems in syntactic analysis is syntactic ambiguities. This paper proposes a parsing system and this system can reduce syntactic ambiguities by using segmentation method and argument information method. The proposed system uses morphemes for the input of syntax analysis system, and syntactic analysis system generates all possible parse trees from the given morphemes. Therefore, this system generates many syntactic ambiguity problems. We use three methods to solve these problems. First is disambiguation method in morphological analysis, second is segmentation method in syntactic analysis processing, and the last method is using argument information. Using these three methods, we can reduce many ambiguities in Korean syntactic analysis. In our experiment, our approach decreases about 53% of syntactic ambiguities.

The market future of automated price parsing systems for the electric power

The market future of automated price parsing systems for the electric power

Word Segmentation, Unknown-word Resolution, and Morphological Agreement in a Hebrew Parsing System

We present a constituency parsing system for Modern Hebrew. The system is based on the PCFG-LA parsing method of Petrov et al. 2006 , which is extended in various ways in order to accommodate the specificities of Hebrew as a morphologically rich language with a small treebank. We show that parsing performance can be enhanced by utilizing a language resource external to the treebank, specifically, a lexicon-based morphological analyzer. We present a computational model of interfacing the external lexicon and a treebank-based parser, also in the common case where the lexicon and the treebank follow different annotation schemes. We show that Hebrew word-segmentation and constituency-parsing can be performed jointly using CKY lattice parsing. Performing the tasks jointly is effective, and substantially outperforms a pipeline-based model. We suggest modeling grammatical agreement in a constituency-based parser as a filter mechanism that is orthogonal to the grammar, and present a concrete implementation of the method. Although the constituency parser does not make many agreement mistakes to begin with, the filter mechanism is effective in fixing the agreement mistakes that the parser does make. These contributions extend outside of the scope of Hebrew processing, and are of general applicability to the NLP community. Hebrew is a specific case of a morphologically rich language, and ideas presented in this work are useful also for processing other languages, including English. The lattice-based parsing methodology is useful in any case where the input is uncertain. Extending the lexical coverage of a treebank-derived parser using an external lexicon is relevant for any language with a small treebank.

What eye movements can tell us about sentence comprehension.

Eye movement data have proven to be very useful for investigating human sentence processing. Eyetracking research has addressed a wide range of questions, such as recovery mechanisms following garden-pathing, the timing of processes driving comprehension, the role of anticipation and expectation in parsing, the role of semantic, pragmatic, and prosodic information, and so on. However, there are some limitations regarding the inferences that can be made on the basis of eye movements. One relates to the nontrivial interaction between parsing and the eye movement control system which complicates the interpretation of eye movement data. Detailed computational models that integrate parsing with eye movement control theories have the potential to unpack the complexity of eye movement data and can therefore aid in the interpretation of eye movements. Another limitation is the difficulty of capturing spatiotemporal patterns in eye movements using the traditional word-based eyetracking measures. Recent research has demonstrated the relevance of these patterns and has shown how they can be analyzed. In this review, we focus on reading, and present examples demonstrating how eye movement data reveal what events unfold when the parser runs into difficulty, and how the parsing system interacts with eye movement control. WIREs Cogn Sci 2013, 4:125-134. doi: 10.1002/wcs.1209 For further resources related to this article, please visit the WIREs website.

An Empirical Analysis of Malware Blacklists

Besides all the advantages and reliefs the Internet brought us over the years, there are also a lot of suspicious and malicious activities taking place. Attackers are constantly developing new techniques to compromise computer systems. Furthermore, there are many malicious servers on the Internet that host, for example, exploits, drive-by download toolkits, or malicious software. We want to track the network locations of these malicious servers by analyzing different kinds of blacklists that provide a listing of suspicious servers. In this article, we present the design and implementation of our blacklist parser system that tracks 49 different blacklists. We have collected more than 2.2 million distinct blacklist entries and more than 410,000 distinct URLs in the first 80 days of running the system. Besides discussing the design, we also provide an overview of the first empirical results of analyzing the collected data. In the future, we plan to extend the system such that it provides a comprehensive overview of malicious activities on the Internet.

Nonparametric Scene Parsing via Label Transfer

While there has been a lot of recent work on object recognition and image understanding, the focus has been on carefully establishing mathematical models for images, scenes, and objects. In this paper, we propose a novel, nonparametric approach for object recognition and scene parsing using a new technology we name label transfer. For an input image, our system first retrieves its nearest neighbors from a large database containing fully annotated images. Then, the system establishes dense correspondences between the input image and each of the nearest neighbors using the dense SIFT flow algorithm [28], which aligns two images based on local image structures. Finally, based on the dense scene correspondences obtained from SIFT flow, our system warps the existing annotations and integrates multiple cues in a Markov random field framework to segment and recognize the query image. Promising experimental results have been achieved by our nonparametric scene parsing system on challenging databases. Compared to existing object recognition approaches that require training classifiers or appearance models for each object category, our system is easy to implement, has few parameters, and embeds contextual information naturally in the retrieval/alignment procedure.

What is the scanpath signature of syntactic reanalysis?

Which repair strategy does the language system deploy when it gets garden-pathed, and what can regressive eye movements in reading tell us about reanalysis strategies? Several influential eye-tracking studies on syntactic reanalysis ( Frazier & Rayner, 1982; Meseguer, Carreiras, & Clifton, 2002; Mitchell, Shen, Green, & Hodgson, 2008) have addressed this question by examining scanpaths, i.e., sequential patterns of eye fixations. However, in the absence of a suitable method for analyzing scanpaths, these studies relied on simplified dependent measures that are arguably ambiguous and hard to interpret. We address the theoretical question of repair strategy by developing a new method that quantifies scanpath similarity. Our method reveals several distinct fixation strategies associated with reanalysis that went undetected in a previously published data set ( Meseguer et al., 2002). One prevalent pattern suggests re-parsing of the sentence, a strategy that has been discussed in the literature ( Frazier & Rayner, 1982); however, readers differed tremendously in how they orchestrated the various fixation strategies. Our results suggest that the human parsing system non-deterministically adopts different strategies when confronted with the disambiguating material in garden-path sentences.

Joint reranking of parsing and word recognition with automatic segmentation

Abstract Evaluation and optimization of automatic speech recognition (ASR) and parsing systems are often done separately. In the context of spoken language processing, however, these problems may be explored jointly via a reranking architecture. In this work, the effects of reranking for word error rate (WER) or reranking for the Sparseval parse-quality measure are examined in conversational speech recognition, while considering the impact of automatic segmentation. Under a WER criterion, the results indicate that the parse language model alone provides little benefit over a large n-gram model, but adding non-local syntactic features leads to improved performance. Under a Sparseval criterion, it is shown that including alternative word-sequence hypotheses has a much greater impact on parse accuracy than including alternate parse hypotheses. In both cases, the biggest performance improvements are obtained with high quality sentence segmentations. Qualitative analyses show that parse features help recover pronouns and improve recognition of main verbs.

Penn Treebank-Based Syntactic Parsers for South Dravidian Languages using a Machine Learning Approach

With the availability of limited electronic resources, development of a syntactic parser for all types of sentence forms is a challenging and demanding task for any natural language. This paper presents the development of Penn Treebank based statistical syntactic parsers for two South Dravidian languages namely Kannada and Malayalam. Syntactic parsing is the task of recognizing a sentence and assigning a syntactic structure to it. A syntactic parser is an essential tool used for various natural language processing (NLP) applications and natural language understanding. The well known grammar formalism called Penn Treebank structure was used to create the corpus for proposed statistical syntactic parsers. Both the parsing systems were trained using Treebank based corpus consists of 1,000 Kannada and Malayalam sentences that were carefully constructed. The developed corpus has been already annotated with correct segmentation and Part-Of-Speech (POS) information. We have used our own POS tagger generator for assigning proper tags to each and every word in the training and test sentences. The proposed syntactic parser was implemented using supervised machine learning and probabilistic context free grammars (PCFG) approaches. Training, testing and evaluations were done by support vector method (SVM) algorithms. From the experiment we found that the performance of our systems are significantly well and achieves a very competitive accuracy.

부분 구문 분석 결과에 기반한 두 단계 부분 의미 분석 시스템

부분 의미 분석 시스템은 문장의 구성 요소들이 술어와 갖는 관계를 분석하는 것으로 문장에서 술어의 주체, 객체, 도구 등을 나타내는 의미 논항을 확인하게 된다. 본 논문에서 개발한 부분 의미 분석 시스템은 두 단계로 구성되어 있는데, 먼저 부분 구문 분석 결과로부터 의미 논항의 경계를 찾는 의미 논항 확인 단계를 수행하고 다음으로 확인된 의미 논항에 적절한 의미역을 부착하는 의미역 할당 단계를 수행한다. 순차적인 두 단계 방법을 적용하는 것에 의해서, 학습 성능 저하의 주요한 원인인 클래스 분포의 불균형 문제를 완화할 수 있고, 각 단계에 적합한 자질을 선별하여 사용할 수 있다. 본 논문에서는 PropBank 말뭉치에 기반한 CoNLL-2004 shared task의 데이터 집합 및 평가 프로그램을 사용하여 각 단계가 시스템의 전체 성능에 기여하는 정도를 보인다. A shallow semantic parsing system analyzes the relationship that a syntactic constituent of the sentence has with a predicate. It identifies semantic arguments representing agent, patient, instrument, etc. of the predicate. In this study, we propose a two-phase shallow semantic parsing model which consists of the identification phase and the classification phase. We first find the boundary of semantic arguments from partial syntactic parsing results, and then assign appropriate semantic roles to the identified semantic arguments. By taking the sequential two-phase approach, we can alleviate the unbalanced class distribution problem, and select the features appropriate for each task. Experiments show the relative contribution of each phase on the test data.

Visual Software Development Environment Based on Graph Grammars

In software design and development, program diagrams are often used for good visualization. Many kinds of program diagrams have been proposed and used. To process such diagrams automatically and efficiently, the program diagram structure needs to be formalized. We aim to construct a diagram processing system with an efficient parser for our program diagram Hichart. In this paper, we give a precedence graph grammar for Hichart that can parse in linear time. We also describe a parsing method and processing system incorporating the Hichart graphical editor that is based on the precedence graph grammar.

Wide-Coverage Deep Statistical Parsing Using Automatic Dependency Structure Annotation

A number of researchers have recently conducted experiments comparing “deep” hand-crafted wide-coverage with “shallow” treebank- and machine-learning-based parsers at the level of dependencies, using simple and automatic methods to convert tree output generated by the shallow parsers into dependencies. In this article, we revisit such experiments, this time using sophisticated automatic LFG f-structure annotation methodologies with surprising results. We compare various PCFG and history-based parsers to find a baseline parsing system that fits best into our automatic dependency structure annotation technique. This combined system of syntactic parser and dependency structure annotation is compared to two hand-crafted, deep constraint-based parsers, RASP and XLE. We evaluate using dependency-based gold standards and use the Approximate Randomization Test to test the statistical significance of the results. Our experiments show that machine-learning-based shallow grammars augmented with sophisticated automatic dependency annotation technology outperform hand-crafted, deep, wide-coverage constraint grammars. Currently our best system achieves an f-score of 82.73% against the PARC 700 Dependency Bank, a statistically significant improvement of 2.18% over the most recent results of 80.55% for the hand-crafted LFG grammar and XLE parsing system and an f-score of 80.23% against the CBS 500 Dependency Bank, a statistically significant 3.66% improvement over the 76.57% achieved by the hand-crafted RASP grammar and parsing system.

Parsers for SMILES and SMARTS

SMILES [1] and SMARTS [2] are two line notations developed by Daylight and implemented in a number of chemical informatics software tools. For the most part these are hand-written parsers and quite complicated and hard to read, modify, maintain, optimize or reuse. A traditional computer science approach would use a parsing system like lex/yacc but that has not made much inroad in computational chemistry. The tools have been difficult to use, especially for error reporting and recovery, and most of the developers have a chemistry background and don't know the language theory underlying this approach. Modern programming languages and parser systems have made many of the difficulties disappear. I have been working with people from OpenSMILES [3] and several of the existing open source toolkits (Open Babel [4], CDK [5] and RDKit [6]) develop valid, useful grammars for SMILES and SMARTS. I have also been evaluating how to implement those grammars using parsing systems like ANTLR [7], PLY [8] and ragel [9]. My plan is to fold that work back into the different projects so there is a broader and more consistent support for these two important notations. I expect also that resulting code will be faster, more maintainable, and more flexible for trying new ideas. By documenting the different parts I hope the knowledge of how to use parser frameworks is disseminated into the computational chemistry development community and helps to develop the next generation of chemistry toolkits and line notations like MQL[10]. This poster presents some of the preliminary results of that work including a SMILES grammar, implementations for ANTLR and PLY, and early performance analysis.