Do Anglian dialects of Old English have a partial pro-drop property?

2019 ◽  
pp. 53-92
Author(s):  
Kristian A. Rusten
Keyword(s):  
Old English ◽  
Random Forests ◽  
Fixed Effects ◽  
Analytical Techniques ◽  
Statistical Modelling ◽  
Descriptive Statistics ◽  
Conditional Inference ◽  
The West ◽  
Conditional Inference Trees ◽  
Logistic Regression Modelling

Chapter 3 deals with the question of whether Anglian dialects of Old English, in contrast to the West Saxon literary standard, had a partial pro-drop property. The chapter investigates this ‘dialect-split hypothesis’ by means of descriptive statistics and inferential statistical modelling. It is also noted that what has been interpreted as diatopic variation could also be representative of other types of variation, and consequently the variables of translation status, period, and genre are also investigated, in addition to dialect. The primary analytical techniques used in this chapter are generalized fixed-effects logistic regression modelling and random forests of conditional inference trees. The chapter concludes that the dialect-split hypothesis must be considered falsified.

scholarly journals Generating Tree-Level Harvest Predictions from Forest Inventories with Random Forests

Forests ◽  
2018 ◽  
Vol 10 (1) ◽  
pp. 20 ◽  
Author(s):  
Philipp Kilham ◽  
Christoph Hartebrodt ◽  
Gerald Kändler
Keyword(s):  
Random Forests ◽  
Prediction Models ◽  
Training Data ◽  
Conditional Inference ◽  
Tree Level ◽  
Data Sets ◽  
Wood Supply ◽  
Forest Inventories ◽  
Conditional Inference Trees ◽  
Harvest Decisions

Wood supply predictions from forest inventories involve two steps. First, it is predicted whether harvests occur on a plot in a given time period. Second, for plots on which harvests are predicted to occur, the harvested volume is predicted. This research addresses this second step. For forests with more than one species and/or forests with trees of varying dimensions, overall harvested volume predictions are not satisfactory and more detailed predictions are required. The study focuses on southwest Germany where diverse forest types are found. Predictions are conducted for plots on which harvests occurred in the 2002–2012 period. For each plot, harvest probabilities of sample trees are predicted and used to derive the harvested volume (m³ over bark in 10 years) per hectare. Random forests (RFs) have become popular prediction models as they define the interactions and relationships of variables in an automatized way. However, their suitability for predicting harvest probabilities for inventory sample trees is questionable and has not yet been examined. Generalized linear mixed models (GLMMs) are suitable in this context as they can account for the nested structure of tree-level data sets (trees nested in plots). It is unclear if RFs can cope with this data structure. This research aims to clarify this question by comparing two RFs—an RF based on conditional inference trees (CTree-RF), and an RF based on classification and regression trees (CART-RF)—with a GLMM. For this purpose, the models were fitted on training data and evaluated on an independent test set. Both RFs achieved better prediction results than the GLMM. Regarding plot-level harvested volumes per ha, they achieved higher variances explained (VEs) and significantly (p < 0.05) lower mean absolute residuals when compared to the GLMM. VEs were 0.38 (CTree-RF), 0.37 (CART-RF), and 0.31 (GLMM). Root means squared errors were 138.3, 139.9 and 145.5, respectively. The research demonstrates the suitability and advantages of RFs for predicting harvest decisions on the level of inventory sample trees. RFs can become important components within the generation of business-as-usual wood supply scenarios worldwide as they are able to learn and predict harvest decisions from NFIs in an automatized and self-adapting way. The applied approach is not restricted to specific forests or harvest regimes and delivers detailed species and dimension information for the harvested volumes.

scholarly journals Discourse-Pragmatic and Processing-Related Motivators of the ordering of Reason Clauses in an Academic Corpus

2018 ◽  
Vol 16 (3) ◽  
pp. 325-339
Author(s):  
Abbas A. Rezaee ◽  
Majid Nemati ◽  
Seyyed Ehsan Golparvar
Keyword(s):  
Random Forest ◽  
Applied Linguistics ◽  
Statistical Modelling ◽  
Conditional Inference ◽  
Research Articles ◽  
Relative Importance ◽  
Conditional Inference Trees

The present research is aimed at examining the relative importance of the competing motivators of the sequencing of reason clauses in a corpus of research articles of applied linguistics. All the finite reason clauses accompanied by their main clauses in this corpus were collected. Random forest of conditional inference trees is the statistical modelling in this study. The findings showed that sentence-final reason clauses outnumber sentenceinitial ones. Moreover, subordinator choice and bridging, which are discourse-pragmatic constraints on clause positioning, emerged as the two more powerful predictors of the ordering of reason clauses in this corpus. Furthermore, the complexity of the clause turned out to be a stronger processing related predictor than the length of the clause.

USING CONDITIONAL INFERENCE TREES AND RANDOM FORESTS TO PREDICT THE BIOACCUMULATION POTENTIAL OF ORGANIC CHEMICALS

2013 ◽  
Vol 32 (5) ◽  
pp. 1187-1195 ◽  
Author(s):  
Sebastian Strempel ◽  
Monika Nendza ◽  
Martin Scheringer ◽  
Konrad Hungerbühler
Keyword(s):  
Random Forests ◽  
Conditional Inference ◽  
Organic Chemicals ◽  
Conditional Inference Trees

The – switch: an empirical account of the anglicisation of a Scots variant in Scotland during the sixteenth and seventeenth centuries

2019 ◽  
Vol 24 (1) ◽  
pp. 211-236
Author(s):  
SARAH VAN EYNDHOVEN ◽  
LYNN CLARK
Keyword(s):  
Logistic Regression ◽  
Language Change ◽  
Statistical Modelling ◽  
Mixed Effects ◽  
Descriptive Statistics ◽  
Statistical Techniques ◽  
Fine Grained ◽  
Regression Modelling ◽  
Modern Methods ◽  
Logistic Regression Modelling

This article explores the anglicisation of the Scots language between the sixteenth and eighteenth centuries, focusing on the variation between the orthographic clusters <quh-> and <wh-> found in relative and interrogative clause markers. Using modern statistical techniques, we provide the most comprehensive empirical analysis of this variation so far in the Helsinki Corpus of Older Scots (Meurman-Solin 1995). By combining the techniques of Variability-Based Neighbour Clustering (Gries & Hilpert 2008, 2010, 2012) with mixed-effects logistic regression modelling (Baayen et al.2008), we uncover a different trajectory of change than that which has previously been reported for this feature (Meurman-Solin 1993, 1997). We argue that by using modern methods of data reduction and statistical modelling, we can present a picture of language change in Scots that is more fine-grained than previous studies which use only descriptive statistics.

The positioning of concessive adverbial clauses in English: assessing the importance of discourse-pragmatic and processing-based constraints

2013 ◽  
Vol 17 (1) ◽  
pp. 1-23 ◽  
Author(s):  
DANIEL WIECHMANN ◽  
ELMA KERZ
Keyword(s):  
Language Processing ◽  
Random Forests ◽  
General Type ◽  
Main Clause ◽  
Conditional Inference ◽  
Relative Importance ◽  
Multifactorial Analysis ◽  
Subordinate Clauses ◽  
Conditional Inference Trees ◽  
Adverbial Clauses

English permits adverbial subordinate clauses to be placed either before or after their associated main clause. Previous research has shown that the positioning is conditioned by various factors from the domains of semantics, discourse pragmatics and language processing. With the exception of Diessel (2008), these factors have never been investigated in concert, which makes it difficult to understand their relative importance. Diessel's study, however, discusses only temporal constructions and identifies iconicity of sequence as the strongest predictor of clause position. Since this explanation is, in principle, unavailable for other types of subordinate clauses, the generalizability of Diessel's findings is somewhat limited. The present study offers a multifactorial analysis of 2,000 concessive constructions from the written part of the BNC and assesses the variable importance of six factors for the ordering choice, showing that semantic and discourse-pragmatic factors are much stronger predictors of clause position than processing-based, weight-related ones. On a methodological note, the study proposes that random forests using conditional inference trees constitute the preferred tool for the general type of problem investigated here.

Place-name Mutation Variation in Wales and Patagonia

2020 ◽  
Vol 21 (1) ◽  
pp. 143-172
Author(s):  
Morgan Sleeper
Keyword(s):  
Random Forests ◽  
Statistical Approach ◽  
Conditional Inference ◽  
Conversational Speech ◽  
Place Names ◽  
Mutation Strategy ◽  
Significant Difference ◽  
Conditional Inference Trees ◽  
Corpus Data

This study uses corpus data of modern conversational speech to examine variation in the mutation of place-names in Welsh as spoken in both Wales and Patagonia. Specifically, it considers how speakers from both areas mutate (or do not mutate) place-names following the nasal mutation trigger yn 'in', through a two-step statistical approach of conditional inference trees and random forests. Results show no significant difference in how speakers from Wales and Patagonia mutate place-names in this environment, but that the radical initial consonant, speaker age, and place-name type – including the geographical, linguistic, and cultural 'Welshness' of the place-name – all significantly affect mutation behaviour. Furthermore, while nasal mutation is present in the data, the results also illustrate the growing use of soft mutation as an alternate mutation strategy following yn.

Variation in negation in Seto

2021 ◽  
Author(s):  
Liina Lindström ◽  
Maarja-Liisa Pilvik ◽  
Helen Plado
Keyword(s):  
Random Forests ◽  
Quantitative Methods ◽  
Conditional Inference ◽  
Double Negation ◽  
Regression Modelling ◽  
Conditional Inference Trees ◽  
Third Person ◽  
Fixed Expressions ◽  
Present Tense

Abstract Seto is an exceptional language in the Uralic family due to its systematic use of postverbal negation, although preverbal and double negation marking are also used. Postverbal negation is still the most frequent and unmarked pattern occurring in about 74% of negative clauses in Seto. This paper analyzes variation between pre- and postverbal negation in East Seto (spoken in present-day Russia), based on data gathered during fieldwork trips in 2010–2013. By applying quantitative methods that are used in variationist studies (regression modelling, conditional inference trees, and random forests), we determine the variables affecting the choice between pre- and postverbal negation. Marked preverbal negation occurs more likely with first and third person, cognition verbs, and present tense, all of which are often used in fixed expressions like I don’t know. We also found a strong structural persistence effect in the data and remarkable differences between individual speakers.

Models, forests, and trees of York English: Was/were variation as a case study for statistical practice

2012 ◽  
Vol 24 (2) ◽  
pp. 135-178 ◽  
Author(s):  
Sali A. Tagliamonte ◽  
R. Harald Baayen
Keyword(s):  
Random Forests ◽  
Linear Models ◽  
Random Effect ◽  
Mixed Effects ◽  
Conditional Inference ◽  
Mixed Effects Models ◽  
Future Research ◽  
Recent Developments ◽  
Conditional Inference Trees ◽  
Complementary Techniques

AbstractWhat is the explanation for vigorous variation between was and were in plural existential constructions, and what is the optimal tool for analyzing it? Previous studies of this phenomenon have used the variable rule program, a generalized linear model; however, recent developments in statistics have introduced new tools, including mixed-effects models, random forests, and conditional inference trees that may open additional possibilities for data exploration, analysis, and interpretation. In a step-by-step demonstration, we show how this well-known variable benefits from these complementary techniques. Mixed-effects models provide a principled way of assessing the importance of random-effect factors such as the individuals in the sample. Random forests provide information about the importance of predictors, whether factorial or continuous, and do so also for unbalanced designs with high multicollinearity, cases for which the family of linear models is less appropriate. Conditional inference trees straightforwardly visualize how multiple predictors operate in tandem. Taken together, the results confirm that polarity, distance from verb to plural element, and the nature of the DP are significant predictors. Ongoing linguistic change and social reallocation via morphologization are operational. Furthermore, the results make predictions that can be tested in future research. We conclude that variationist research can be substantially enriched by an expanded tool kit.

Phonological properties of word classes and directionality in conversion

2017 ◽  
Vol 10 (2) ◽  
pp. 204-234 ◽  
Author(s):  
Arne Lohmann
Keyword(s):  
Random Forests ◽  
Large Scale ◽  
Word Formation ◽  
Conditional Inference ◽  
Limited Attention ◽  
Word Class ◽  
Conditional Inference Trees ◽  
Word Classes ◽  
Accurate Indicator ◽  
English Noun

In the study of the word-formation process of conversion, one particularly difficult task is to determine the directionality of the process, that is, to decide which word represents the base and which the derived word. One possibility to inform this decision that has received only limited attention is to capitalize on word-class-specific phonological properties. This paper empirically investigates this option for English noun-verb conversion by building on recent findings on phonological differences between these two word classes. A large-scale study of phonological properties is carried out on CELEX data, employing the quantitative techniques of conditional inference trees and random forests. An important result of this analysis is that the accuracy of phonological cues varies widely across different subsamples in the data. Essentially this means that phonological cues can be used as a criterion to determine the directionality of words that are at least two syllables in length. When restricted to this part of the lexicon, phonological properties represent a fairly accurate indicator of source word class and are therefore a useful addition to the linguist's toolkit for determining directionality in conversion. Based on this result, the paper also discusses the relations of phonological properties to other criteria commonly employed to determine directionality.

Sign in / Sign up

Export Citation Format

Share Document