scholarly journals A Graph-based Lattice Dependency Parser for Joint Morphological Segmentation and Syntactic Analysis

2015 ◽  
Vol 3 ◽  
pp. 359-373 ◽  
Author(s):  
Wolfgang Seeker ◽  
Özlem Çetinoğlu
Keyword(s):  
Morphological Analysis ◽  
Syntactic Analysis ◽  
Data Sets ◽  
Syntactic Structures ◽  
Morphological Segmentation ◽  
Joint Task ◽  
Dependency Tree ◽  
First Results ◽  
Input Sentence ◽  
Dependency Parser

Space-delimited words in Turkish and Hebrew text can be further segmented into meaningful units, but syntactic and semantic context is necessary to predict segmentation. At the same time, predicting correct syntactic structures relies on correct segmentation. We present a graph-based lattice dependency parser that operates on morphological lattices to represent different segmentations and morphological analyses for a given input sentence. The lattice parser predicts a dependency tree over a path in the lattice and thus solves the joint task of segmentation, morphological analysis, and syntactic parsing. We conduct experiments on the Turkish and the Hebrew treebank and show that the joint model outperforms three state-of-the-art pipeline systems on both data sets. Our work corroborates findings from constituency lattice parsing for Hebrew and presents the first results for full lattice parsing on Turkish.

scholarly journals The S2 Baseband Processing System for Phase-coherent Pulsar Observations

1996 ◽  
Vol 160 ◽  
pp. 21-22
Author(s):  
R. Wietfeldt ◽  
W. Van Straten ◽  
D. Del Rizzo ◽  
N. Bartel ◽  
W. Cannon ◽  
...  
Keyword(s):  
High Speed ◽  
Processing System ◽  
High Time Resolution ◽  
Data Sets ◽  
Future Developments ◽  
Huge Data ◽  
Pulse Timing ◽  
First Results ◽  
Vela Pulsar ◽  
Baseband Processing

AbstractThe phase-coherent recording of pulsar data and subsequent software dispersion removal provide a flexible way to reach the limits of high time resolution, useful for more precise pulse timing and the study of fast signal fluctuations within a pulse. Because of the huge data rate and lack of adequate recording and computing capabilities, this technique has been used mostly only for small pulsar data sets. In recent years, however, the development of very capable, reasonably inexpensive high-speed recording systems and computers has made feasible the notion of pulsar baseband recording and subsequent processing with a workstation/computer. In this paper we discuss the development of a phase-coherent baseband processing system for radio pulsar observations. This system is based on the S2 VLBI recorder developed at ISTS/York University in Toronto, Canada. We present preliminary first results for data from the Vela pulsar, obtained at Parkes, Australia, and processed at ISTS/York University, and discuss plans for future developments.

scholarly journals Anatomical variation of the distal femur - a CT data analysis of 24,042 knees

2018 ◽  
Vol 6 (4_suppl2) ◽  
pp. 2325967118S0003
Author(s):  
Cornelia Merz ◽  
Andre Steinert ◽  
Wiliam Kurtz ◽  
Franz Xaver Köck ◽  
Johannes Beckmann
Keyword(s):  
Distal Femur ◽  
External Rotation ◽  
Anatomical Variation ◽  
Data Sets ◽  
Medial Condyle ◽  
First Results ◽  
The Difference ◽  
Ct Data ◽  
The Individual ◽  
Femoral Size

Based on a large quantity of CT data, variations in distal femoral geometry was examined and evaluated for TKA. A retrospective study was performed on 24,042 data sets generated during the process of designing individual knee implants. Following parameters were recorded for the distal femur: Femoral absolute anterior-posterior (AP) and medial-lateral (ML) extent, lateral and medial condyle and trochlea size, distal condylar offset (DCO) between lateral and medial condyle, and the difference between medial and lateral posterior condylar offset (PCO) measured in AP direction. Variable patient geometry was found with analysis of the AP and ML extent. Approximately one-third of the patients would experience size conflicts of +/- 3 mm with standard arthroplasty systems. 62% of the knees had a DCO> 1 mm. 83% of the distal femur had a mediolateral difference in PCO> 2 mm, which corresponds to about 3° external rotation and does not correlate with the femoral size. There is a distinct variability of femoral AP and ML extent as well as offsets / asymmetries. Medial and lateral PCOs are different and do not correlate with femoral size. This first results in mismatches between size of implant and individual knee anatomy and secondly in possible softtissue release and different femoral external rotations to adapt systems with fixed distal geometry to the individual situation.

scholarly journals Syntax-Aware Neural Semantic Role Labeling

2019 ◽  
Vol 33 ◽  
pp. 7305-7313 ◽  
Author(s):  
Qingrong Xia ◽  
Zhenghua Li ◽  
Min Zhang ◽  
Meishan Zhang ◽  
Guohong Fu ◽  
...  
Keyword(s):  
Close Correlation ◽  
Semantic Role ◽  
Semantic Role Labeling ◽  
Semantic Parsing ◽  
Single Model ◽  
Improve Performance ◽  
Syntactic Structures ◽  
Word Sequence ◽  
Input Sentence ◽  
Feature Based

Semantic role labeling (SRL), also known as shallow semantic parsing, is an important yet challenging task in NLP. Motivated by the close correlation between syntactic and semantic structures, traditional discrete-feature-based SRL approaches make heavy use of syntactic features. In contrast, deep-neural-network-based approaches usually encode the input sentence as a word sequence without considering the syntactic structures. In this work, we investigate several previous approaches for encoding syntactic trees, and make a thorough study on whether extra syntax-aware representations are beneficial for neural SRL models. Experiments on the benchmark CoNLL-2005 dataset show that syntax-aware SRL approaches can effectively improve performance over a strong baseline with external word representations from ELMo. With the extra syntax-aware representations, our approaches achieve new state-of-the-art 85.6 F1 (single model) and 86.6 F1 (ensemble) on the test data, outperforming the corresponding strong baselines with ELMo by 0.8 and 1.0, respectively. Detailed error analysis are conducted to gain more insights on the investigated approaches.

3D-Modeling of the Distribution of Welding Aerosol Nano- and Microparticles in the Working Area

2017 ◽  
Vol 13 ◽  
pp. 232-238 ◽  
Author(s):  
Konstantin Yu. Kirichenko ◽  
Vladimir A. Drozd ◽  
Alexander V. Gridasov ◽  
Sergei P. Kobylyakov ◽  
A.S. Kholodov ◽  
...  
Keyword(s):  
Disperse System ◽  
3D Modeling ◽  
Morphological Analysis ◽  
3D Model ◽  
Maximum Density ◽  
Welding Fumes ◽  
Aerosol Cloud ◽  
Gaseous Component ◽  
First Results ◽  
Long Time

The first results of the research of the distribution of welding aerosol nano- and microparticles in the working area based on substance and morphological analysis are presented in the paper. A 3D-model of the welding aerosol cloud demonstrating the distribution of nano- and microparticles in the working area of the welder was created using the granulometric data of the samples. The most dangerous area with maximum density of nano- and microparticles of welding fumes was singled out: 1.3 m in height and 5 meters in all directions.Welding aerosol is a disperse system in which the solid component of the welding aerosol (SCWA) acts as the phase, and the mixture of gases (gaseous component of welding aerosol, or GCWA) – as the medium. SCWA stays suspended in the air for a long time spreading far beyond the working area of a welder [1].The aim of this work was to create a 3D-model of a welding aerosol cloud, demonstrating the spread of nano- and microparticles of welding aerosol in the working area of a welder. The 3D model was created using granulometric data of samples collected by the author’s method.

scholarly journals AGAT-Syntax as component of computer-based Ukrainian grammar

2020 ◽  
pp. 82-102
Author(s):  
Nataliia Darchuk ◽  
Keyword(s):  
Full Range ◽  
Syntactic Analysis ◽  
Main Element ◽  
Sentence Structure ◽  
Subordinate Clauses ◽  
Dependency Tree ◽  
Letter Code ◽  
Computer Based ◽  
Functional Features ◽  
Syntactic Relations

Abstract: The article describes functional features of the syntactic module of computer-based Ukrainian grammar AGAT. This is a linguistic type of computer-aided syntactic analysis, which provides full information about syntactic units and categories, in particular, predicativity, coordinate and subordinate clauses, the categories of subject and predicate etc. The developed linguistic software provides syntactic analysis of a whole sentence in the form of a dependency tree and indicates the types of syntactic relations and links. The AGAT-syntax task is to identify all varieties of compatibility – predicative, subordinate, and coordinate – of each word in the text. The grammatical characteristics of the phrase directly depend on which part of the language its keyword belongs to. The lexical and grammatical nature of the word determines its compatibility to the other words. Accordingly, phrases can be divided into substantive, adjective, pronouns, numeral, verbal and adverbial. Computer sub-grammars of valencies of the said parts of the language are built by us on a single principle: a lexema is indicated, preposition that participates in government and a case of a substantive word form in the shape of a two-letter code. In theory, according to their composition words combinations (phrases) are divided into simple, complex and combined. Dependency tree is built from two elements – nodes and connections. Nodes are wordforms and connections are relationships between the main element (“master”) and dependent element (“slave”). It enables to describe a configuration, a form, external parameters of a sentence but this is not sufficient to describe a sentence structure. Thus, the syntactic analysis has two levels: the first one attributes to each binary pair a type of syntactic relationships on the level of morphological way of expression of a “master”; the second level attributes to the connection a type of syntactic relationships, which include: subjective, objective, attributive, adverbial, completive and appositive modifying.. In such a way, the cycle of automated syntactic analysis of Ukrainian texts is completed by determining the syntactic word-combination, identifying a type of syntactic link and a type of relationship. It provides full range of characteristics that can be used for systemic study of semantic and syntactic problems. Keywords: automated syntactic analysis, dependency tree, syntactic relations, syntactic links.

scholarly journals Towards a dependency treebank for Spanish Sign Language (LSE)

2020 ◽  
Vol 22 ◽  
pp. 111-143
Author(s):  
José M. García ◽  
Carmen Cabeza
Keyword(s):  
Sign Language ◽  
Syntactic Analysis ◽  
Visual Modality ◽  
Sign Languages ◽  
First Results ◽  
Dependency Syntax

This paper presents the foundations, procedures, tests and first results of a dependency treebank of the Spanish Sign Language (LSE). Dependency syntax offers many advantages over other alternatives for the systematic and exhaustive syntactic analysis of a corpus. Nevertheless, the visual modality that is characteristic of sign languages poses unique challenges for their syntactic analysis, among which the most prominent is the simultaneity of expression: both hands, face and other non-manual components. Taking into account these and other particularities of sign languages, the paper explores the main difficulties faced when one tries to apply some usual categories and relations from the syntactic analysis of spoken and written languages to LSE.

scholarly journals An Algorithm for Morphological Segmentation of Esperanto Words

2016 ◽  
Vol 105 (1) ◽  
pp. 63-76
Author(s):  
Theresa Guinard
Keyword(s):  
Natural Language Processing ◽  
Language Processing ◽  
Morphological Analysis ◽  
Compound Words ◽  
Part Of Speech ◽  
Semantic Classes ◽  
Morphological Segmentation ◽  
Segmentation Accuracy ◽  
N Gram ◽  
Speech Information

Abstract Morphological analysis (finding the component morphemes of a word and tagging morphemes with part-of-speech information) is a useful preprocessing step in many natural language processing applications, especially for synthetic languages. Compound words from the constructed language Esperanto are formed by straightforward agglutination, but for many words, there is more than one possible sequence of component morphemes. However, one segmentation is usually more semantically probable than the others. This paper presents a modified n-gram Markov model that finds the most probable segmentation of any Esperanto word, where the model’s states represent morpheme part-of-speech and semantic classes. The overall segmentation accuracy was over 98% for a set of presegmented dictionary words.

scholarly journals Deverbal and deadjectival nominalization in Dan: Not as different as one might think. A reply to Baker & Gondo (2020)

2021 ◽  
Vol 6 (1) ◽  
Author(s):  
Valentin Feodosievich Vydrin
Keyword(s):  
Syntactic Analysis ◽  
Syntactic Structures ◽  
Intransitive Verb ◽  
Possessive Constructions

The paper (Baker & Gondo 2020) studies several issues in Dan morphosyntax: the formal differences between verbs, nouns and adjectives; two types of possessive constructions (with alienable and inalienable head nouns) and their syntactic structures; the derivation of nouns from verbs and adjectives; low and high nominalization; and possessive constructions with deverbal and deadjectival nouns. As it turns out, Baker & Gondo’s analyses are incorrect in some major points: the key formal differences between verbs, adjectives and nouns have been left unnoticed due to disregard for Dan tonal morphology, and for the same reason, the tonal marking of the high nominalization has also been ignored. Baker & Gondo’s syntactic analysis of the possessive construction with alienable nouns as analogous to the Saxon genitive (king’s house) cannot be accepted; in fact, it can be compared with the genitive construction seen in English the house of the king. Possessive constructions with deverbal and deadjectival nouns are not as radically opposed as one may think after reading Baker & Gondo’s paper; in fact, a noun derived from an intransitive verb can sometimes appear as an alienable noun with respect to its theme, and, conversely, a deadjectival noun can appear as a relational noun with respect to the modified noun.

scholarly journals The Linguistic Atlas of the East of Guilan on the Basis of Morphological Analysis (Lexical - Inflectional)

2016 ◽  
Vol 7 (1) ◽  
pp. 1166-1171
Author(s):  
Maryam Mahlouji Afshar ◽  
Iran Kalbassi
Keyword(s):  
Caspian Sea ◽  
Morphological Analysis ◽  
Field Method ◽  
Syntactic Analysis ◽  
The Caspian Sea ◽  
Principal Role ◽  
Language Varieties ◽  
Eastern Border ◽  
Morphological Differences ◽  
Guilan Province

This article, in line with “The National Project of the Dialectology”, aims to provide a linguistic atlas in the East of Guilan province. Due to the large number of speakers in the southern edge of the Caspian Sea and many differences between dialects and accents, this area has great importance linguistically and providing the linguistic atlas in representation and introduction of dialects in this land can be an important achievement to access the indigenous, cultural, social and historical studies among linguistics and persons who are interested in culture. In order to achieve this principal issue, there has been investigated the morphological differences and similarities (lexical - inflectional) of language varieties in the East of Guilan province with the standard Persian- even more than phonetic and syntactic analysis- and they can have the principal role in providing the linguistic atlas. So in this article, through presenting the morphological evidences (lexical - inflectional) and comparing them with standard Persian, there has been marked a dialect with different accents- the Guilaki dialect from the East of Guilan province and it has been depicted for linguistic atlas. The study was conducted by library and field method and by collecting data from a questionnaire consisting of 100 words and sampling from 20 villages in the East of Guilan province- from Astaneh Ashrafieh to the end of the eastern border of Guilan province (Chaboksar). The data obtained by each village has been considered in the tables related to each word and has been moved on the map of region after comparing with the standard Persian and finally the linguistic atlas has been made. To achieve genuine accents, the speakers of middle-aged who spent much of their life in the area have been helped and villages have been considered with more phonetic differences in accent.

scholarly journals Towards a dependency treebank for Spanish Sign Language (LSE)

2020 ◽  
Vol 23 ◽  
pp. 111-143
Author(s):  
José M. García ◽  
Carmen Cabeza
Keyword(s):  
Sign Language ◽  
Syntactic Analysis ◽  
Visual Modality ◽  
Sign Languages ◽  
First Results ◽  
Dependency Syntax

This paper presents the foundations, procedures, tests and first results of a dependency treebank of the Spanish Sign Language (LSE). Dependency syntax offers many advantages over other alternatives for the systematic and exhaustive syntactic analysis of a corpus. Nevertheless, the visual modality that is characteristic of sign languages poses unique challenges for their syntactic analysis, among which the most prominent is the simultaneity of expression: both hands, face and other non-manual components. Taking into account these and other particularities of sign languages, the paper explores the main difficulties faced when one tries to apply some usual categories and relations from the syntactic analysis of spoken and written languages to LSE.

Sign in / Sign up

Export Citation Format

Share Document