Parsing System Research Articles

Spell: Online Streaming Parsing of Large Unstructured System Logs

System event logs have been frequently used as a valuable resource in data-driven approaches to enhance system health and stability. A typical procedure in system log analytics is to first parse unstructured logs to structured data, and then apply data mining and machine learning techniques and/or build workflow models from the resulting structured data. Previous work on parsing system event logs focused on offline, batch processing of raw log files. But increasingly, applications demand online monitoring and processing. As a result, a streaming method to parse unstructured logs is needed. We propose an online streaming method $\mathsf{Spell}$Spell, which utilizes a longest common subsequence based approach, to parse system event logs. We show how to dynamically extract log patterns from incoming logs and how to maintain a set of discovered message types in streaming fashion. An enhancement to find more accurate message types is also proposed. We also propose and evaluate a method to automatically discover semantic meanings for parameter fields identified by Spell. We compare $\mathsf{Spell}$Spell against state-of-the-art methods to extract patterns from system event logs on large real data. The results demonstrate that, compared with other log parsing alternatives, $\mathsf{Spell}$Spell shows its superiority in terms of both efficiency and effectiveness.

Effects of Case-marking on the Anticipatory Processing of Korean Sentences

The goal of this study was to explore the effect of the case-marking information from pre-verbal arguments on the anticipatory processing of Korean sentences. More specifically, it was examined whether the case-markers can be used to predict an upcoming argument even before it is introduced into the string. In our eye-tracking experiment using the visual-world paradigm, 24 adult native speakers of Korean showed significantly more anticipatory eye-movements to the potential referent of a Theme object as soon as hearing the sequence of a nominative-marked NP and a dative-marked NP, as compared to when the second NP is accusative-marked. These results confirm the predictive mechanism of the parsing system and the case effect on the prediction in Korean: that is, guided by the case-marking information which is available earlier in the input, the parser can predict a forthcoming argument and thus activate a structural representation of the currently processed sentence. In this way, a verb-final sentence can be interpreted incrementally and predictively as well at each moment of processing.

Devil in the Details: Towards Accurate Single and Multiple Human Parsing

Human parsing has received considerable interest due to its wide application potentials. Nevertheless, it is still unclear how to develop an accurate human parsing system in an efficient and elegant way. In this paper, we identify several useful properties, including feature resolution, global context information and edge details, and perform rigorous analyses to reveal how to leverage them to benefit the human parsing task. The advantages of these useful properties finally result in a simple yet effective Context Embedding with Edge Perceiving (CE2P) framework for single human parsing. Our CE2P is end-to-end trainable and can be easily adopted for conducting multiple human parsing. Benefiting the superiority of CE2P, we won the 1st places on all three human parsing tracks in the 2nd Look into Person (LIP) Challenge. Without any bells and whistles, we achieved 56.50% (mIoU), 45.31% (mean APr) and 33.34% (APp0.5) in Track 1, Track 2 and Track 5, which outperform the state-of-the-arts more than 2.06%, 3.81% and 1.87%, respectively. We hope our CE2P will serve as a solid baseline and help ease future research in single/multiple human parsing. Code has been made available at https://github.com/liutinglt/CE2P.

Dependency parsing of Polish

AbstractThe predicate-argument structure transparently encoded in dependency-based syntactic representations supports machine translation, question answering, information extraction, etc. The quality of dependency parsing is therefore a crucial issue in natural language processing. In the current paper we discuss the fundamental ideas of the dependency theory and provide an overview of selected dependency-based resources for Polish. Furthermore, we present some state-of-the-art dependency parsing systems whose models can be estimated on correctly annotated data. In the experimental part, we provide an in-depth evaluation of these systems on Polish data. Our results show that graph-based parsers, even those without any neural component, are better suited for Polish than transition-based parsing systems.

Anniversary article: Then and now: 25 years of progress in natural language engineering

AbstractThe paper reviews the state of the art of natural language engineering (NLE) around 1995, when this journal first appeared, and makes a critical comparison with the current state of the art in 2018, as we prepare the 25th Volume. Specifically the then state of the art in parsing, information extraction, chatbots, and dialogue systems, speech processing and machine translation are briefly reviewed. The emergence in the 1980s and 1990s of machine learning (ML) and statistical methods (SM) is noted. Important trends and areas of progress in the subsequent years are identified. In particular, the move to the use of n-grams or skip grams and/or chunking with part of speech tagging and away from whole sentence parsing is noted, as is the increasing dominance of SM and ML. Some outstanding issues which merit further research are briefly pointed out, including metaphor processing and the ethical implications of NLE.

Embedded stems as a bootstrapping mechanism for morphological parsing during reading development

The aim of the current research was to test the hypothesis that the activation of embedded words (e.g., the farm in farmhouse) is the starting point for the development of an abstract morphological parsing system in children’s reading. To test this hypothesis, we examined the developmental trajectory of compound priming effects in third- and fifth-grade primary school children, high school students, and adults. Both children and adults participated in a masked priming lexical decision study comparing transparent compound (farmhouse–farm), opaque compound (butterfly–butter), and noncompound (sandwich–sand) word priming effects measured relative to an unrelated control. The results showed significant and equal priming effects in the two compound conditions but not in the noncompound priming condition. This robust pattern was clearly and unequivocally observed across all groups of participants. Our data suggest that even the youngest readers have already acquired the ability to rapidly and automatically identify embedded stems and are sensitive to the overall structure of compound words (full decomposition). We conclude that the activation of embedded stems provides a critical starting point in children’s use of morphological information when learning to read.

Automated Feedback Can Improve Hypothesis Quality

Stating a hypothesis is one of the central processes in inquiry learning, and often forms the starting point of the inquiry process. We designed, implemented and evaluated an automated parsing and feedback system that informed students about the quality of hypotheses they had created in an online tool, the hypothesis scratchpad. In two pilot studies in different domains (‘supply and demand’ from economics and ‘electrical circuits’ from physics) we determined the parser’s accuracy by comparing its judgments with those of human experts. A satisfactory to high accuracy was reached. In the main study (in the ‘electrical circuits’ domain), students were assigned to one of two conditions: no feedback (control) and automated feedback. We found that the subset of students in the experimental condition who asked for automated feedback on their hypotheses were much more likely to create a syntactically correct hypothesis than students in either condition who did not ask for feedback.

SYSTEM FOR WEB RESOURCES CONTENT STRUCTURING AND RECOGNIZING WITH THE MACHINE LEARNING ELEMENTS

Context. A large number of web resources of different organizations requires checking of relevance and correctness of the content, in particular, concerning characteristics of the organization, staff, etc. For this, it is necessary to develop a system of the automated content analysis. This task causes the need to develop a method and software for structuring and recognizing of web resources content. Existing parsing systems do not provide solving of the specified task, since they do not contain elements of machine learning. The object of the research is the process of automated analysis of the web resources content. Objective. The goal of the work is the creation of the system for web resources content structuring and recognizing. Method. The system of structuring and recognizing of text content of web resources with elements of machine learning is considered. Models of the system functioning are proposed. The architecture for realizing of software system for structuring and recognizing of text content of web resources is developed. Example of implementation of the model of developed system for structuring, recognizing and revealing of outdated and incorrect information about personnel on the web resource of educational institution is given. Results. The developed software may be used by support services in order to update and correct the information content. Conclusions. The system of structuring and recognizing of content of web resources with the machine learning elements has been considered. The proposed system compared with the known ones, ensures automated content structuring, recognizing of outdated, non-relevant or wrong information. Represented example of the structuring and recognizing of outdated and incorrect information on the website of educational institution confirms the effectiveness of the proposed system.

Method to Overcome the Ambiguities in Shallow Parse and Transfer Machine Translation

The manuscript proposes a new architecture for a Shallow Parsing and Shallow Transfer Rule-Based Machine Translation System. The newly proposed architecture omits the disambiguation module in the starting phases of the translation pipeline and stores all translation candidates generated by the ambiguous process in the morphological analysis phase. The architecture is based on multigraphs. We propose a simplified version of k-best shortest path algorithm for this special case of directed multigraph. The k-best set is ranked using a trigram language model. The empirical evaluation shows that the new architecture produces better translation quality results with constant delay in time.

In-Order Transition-based Constituent Parsing

Both bottom-up and top-down strategies have been used for neural transition-based constituent parsing. The parsing strategies differ in terms of the order in which they recognize productions in the derivation tree, where bottom-up strategies and top-down strategies take post-order and pre-order traversal over trees, respectively. Bottom-up parsers benefit from rich features from readily built partial parses, but lack lookahead guidance in the parsing process; top-down parsers benefit from non-local guidance for local decisions, but rely on a strong encoder over the input to predict a constituent hierarchy before its construction. To mitigate both issues, we propose a novel parsing system based on in-order traversal over syntactic trees, designing a set of transition actions to find a compromise between bottom-up constituent information and top-down lookahead information. Based on stack-LSTM, our psycholinguistically motivated constituent parsing system achieves 91.8 F1 on the WSJ benchmark. Furthermore, the system achieves 93.6 F1 with supervised reranking and 94.2 F1 with semi-supervised reranking, which are the best results on the WSJ benchmark.

Using Particle Swarm Optimization to Accurately Identify Syntactic Phrases in Free Text

Abstract The present article reviews the application of Particle Swarm Optimization (PSO) algorithms to optimize a phrasing model, which splits any text into linguistically-motivated phrases. In terms of its functionality, this phrasing model is equivalent to a shallow parser. The phrasing model combines attractive and repulsive forces between neighbouring words in a sentence to determine which segmentation points are required. The extrapolation of phrases in the specific application is aimed towards the automatic translation of unconstrained text from a source language to a target language via a phrase-based system, and thus the phrasing needs to be accurate and consistent to the training data. Experimental results indicate that PSO is effective in optimising the weights of the proposed parser system, using two different variants, namely sPSO and AdPSO. These variants result in statistically significant improvements over earlier phrasing results. An analysis of the experimental results leads to a proposed modification in the PSO algorithm, to prevent the swarm from stagnation, by improving the handling of the velocity component of particles. This modification results in more effective training sequences where the search for new solutions is extended in comparison to the basic PSO algorithm. As a consequence, further improvements are achieved in the accuracy of the phrasing module.

Automatic Model Generation for Gate-Level Circuit PDES with Reverse Computation

Gate-level circuit simulation is an important step in the design and validation of complex circuits. This step of the process relies on existing libraries for gate specifications. We start with a generic gate model for Rensselaer’s Optimistic Simulation System, a parallel discrete-event simulation framework. This generic model encompasses all functionality needed by optimistic simulation using reverse computation. We then describe a parser system that uses a standardized gate library to create a specific model for simulation. The generated model is composed of several functions, including those needed for an accurate model of timing behavior. To quantify the improvements that an automatically generated model can have over a hand written model, we compare two gate library models: an automatically generated lsi -10 k library model and a previously investigated, handwritten, simplified gtech library model. We conclude that the automatically generated model is a more accurate model of actual hardware. In comparison to previous results, we find that the automatically generated model is able to achieve better optimistic simulation performance when measured against conservative simulation. To test the automatically generated model, we evaluate the performance of a simulation of a full-scale OpenSPARC T2 processor model. This model consists of nearly 6 million LPs. We achieve a peak performance of 1.63 million events per second during a conservative simulation. To understand the relatively weaker performance of optimistic simulation, we investigate hot spots of event activity and visually identify a workload imbalance.

Building an RRG computational grammar

Several grammatical models have shown a growing interest for the development of the conditions necessary to satisfy the so-called criterion of computational adequacy. Within Role and Reference Grammar (RRG [Van Valin & LaPolla, 1997; Van Valin, 2005; Pavey, 2010]), there have been some works seeking to implement the model in different computational environments (Diedrichsen, 2011, 2013; Guest, 2009; Nolan & Perinan-Pascual, 2014; Salem et al., 2008). In this scenario, the works of Van Valin & Mairal (2014), Perinan-Pascual (2013) and PerinanPascual & Arcas (2014) have set up the guidelines to devise a parsing system called ARTEMIS (Automatically Representing TExt Meaning via an InterlinguaBased System) for the computational treatment of the syntax and semantics of sentences. The goal of this paper is to contribute to the development of ARTEMIS focusing specifically on the design of the rules necessary for the effective computational parsing of unmarked simple clauses following the format of the Layered Structure of the Clause as described in RRG. Such rules should yield, as a result for every sentence, a parsed tree following the format of grammatical analyses in RRG.

Linguistics: The Garden and the Bush

Linguistics: The Garden and the Bush

Transition-Based Dependency Parsing Exploiting Supertags

Lexical information, including surface word form and part-of-speech (POS) information, plays a crucial role when predicting ambiguous dependency relationships in dependency parsing. However, for resolving dependency ambiguities, surface word information may be too sparse, while POS information may be too coarse. Supertags, which are lexical templates that represent rich syntactic information, have been shown to provide effective features at an intermediate level on the coarse-to-fine scale. In this work, we present a supertag design framework that allows us to instantiate various supertag sets based on the dependency structures. Using this framework, we instantiate various supertag sets and utilize them as features in transition-based dependency parsing systems. Performing experiments on the Penn Treebank and Universal Dependencies data sets, we show that our supertags are effective for transition-based parsers in multilingual parsing as well as English parsing. The comparison of the results of the different supertag sets shows that it is crucial to incorporate the head directionality, head labels, and dependent possession information in supertags to improve the parser performance.

A syntactic component for Vietnamese language processing

This paper presents the development of a syntactic component for the Vietnamese language. We first discuss the construction of a lexicalized tree-adjoining grammar using an automatic extraction approach. We then present the construction and evaluation of a deep syntactic parser based on the extracted grammar. This is a complete system integrating necessary tools to process Vietnamese text, which permits to take as input raw texts and produce syntactic structures. A dependency annotation scheme for Vietnamese and an algorithm for extracting dependency structures from derivation trees are also proposed. At present, this is the first Vietnamese parsing system capable of producing both constituency and dependency analyses with encouraging performances: 69.33% and 73.21% for constituency and dependency analysis accuracy, respectively. The parser also compares favourably to a statistical parser which is trained and tested on the same data sets.

English

In this paper, we focus on the application of Natural Language Processing (NLP) in an e-assessment system for Arabic language. The development of some linguistic tools as lexicon, morphological analyzer and parser is crucial. Lexicon represents the most important resources for the system Morphological analyzer represents a decomposition, an analysis and research tool for Arab texts. But other evaluation activities require a parsing system. Parsing is a fundamental step in the process of automatic analysis of natural languages. In this paper we describe, firstly the building of a lexicon of Arabic language using the Head Driven phrase Structure Grammar (HPSG) formalism. The lexicon is represented in XML as a list of item elements, and it lists several lexical properties which are specifically targeted at morphological analysis. It also specifies morphological, syntactic and semantic features (such as gender or number), which can be used by parser and assessment system. Also we explain the ascendant approach design of parser and we give an idea on the experimentation of the realized system and its integration in e-learning environment.

Design and Construction of Distributed JavaScript Parsing System

With the rapid development of the Internet technology, JS (short for JavaScript), as one of the representative of script languages, which is very powerful, is becoming more and more popular to the developers and users. But JS programming is more complex than usual static technology. In the field of search engine and information acquisition, it's very difficult to get the information hidden in script code. In this paper, the authors design a distributed system for parsing the JS code embedded in HTML file and retrieving the underling information. the authors describe how to extract JS codes from HTML file and parse them. Also, they introduce a task scheduling algorithm for the JS parsing system by employing Hadoop distributed computing technology. The experimental results indicate that the proposed algorithm and system can achieve a reasonable task scheduling efficiency and parse JS codes rapidly.

한국어 의존 관계 분석과 자질 집합 분할을 이용한 기계학습의 성능 개선

최근에 한국어 의존 관계에 대한 파싱 시스템과 관련된 연구가 소프트웨어 공학자들이나 언어학자들에 의해 다양하게 연구되고 있으며, 시스템 구현은 주로 기계 학습이나 기호 주의를 사용하고 있다. 기계 학습을 사용한 방법은 한국어 문장 데이터가 매우 크기 때문에 시스템 특성상 매우 긴 학습시간을 가지며, 데이터 자체가 가지는 오류로 인하여 한정된 인식율을 가진다. 본 연구에서는 기계학습을 이용한 시스템에 대하여 학습 시간을 줄일 수 있도록 특징들을 자질 집합 모듈로 분할하여 처리하는 방법을 제안하고, 문장수와 반복횟수에 따른 인식율을 분석하였다. 설계된 시스템은 분리된 모듈과 이진 검색을 위한 정렬 기법이 사용되었다. 데이터는 세종 말뭉치로부터 추출한 후 정제된 36,090문장을 사용하였다. 학습 시간은 약 3 시간으로 줄었으며, 인식율은 10,000 문장을 50회 학습하였을 때 84.54%로 가장 높았다. 모든 학습 문장(32,481)을 10회 학습하였을 때 인식율은 82.99%이다. 결과적으로 정제된 데이터를 이용하여 시스템이 안정화될 때까지 반복하는 것이 더 효율적이었다.

LFG parse disambiguation for Wolof

This paper presents several techniques for managing ambiguity in LFG parsing of Wolof, a less-resourced Niger-Congo language. Ambiguity is pervasive in Wolof and This raises a number of theoretical and practical issues for managing ambiguity associated with different objectives. From a theoretical perspective, the main aim is to design a large-scale grammar for Wolof that is able to make linguistically motivated disambiguation decisions, and to find appropriate ways of controlling ambiguity at important interface representations. The practical aim is to develop disambiguation strategies to improve the performance of the grammar in terms of efficiency, robustness and coverage.To achieve these goals, different avenues are explored to manage ambiguity in the Wolof grammar, including the formal encoding of noun class indeterminacy, lexical specifications, the use of Constraint Grammar models (Karlsson 1990) for morphological disambiguation, the application of the c-structure pruning mechanism (Cahill et al. 2007, 2008; Crouch et al. 2013), and the use of optimality marks for preferences (Frank et al. 1998, 2001). The parsing system is further controlled by packing ambiguities. In addition, discriminant-based techniques for parse disambiguation (Rosén et al. 2007) are applied for treebanking purposes.