Yukio Tono
Linguistic feature extraction and evaluation using machine learning to identify “criterial” grammar constructions for the CEFR levels
L2 learner profile
English Profile – CEFR for Englsih
Criterial features: Hawkins & Filipovic 2012
CEFR-J RLD Project: aim prepare list of vocabulary and grammar item to be taught and assessed at each CEFR level
CEFR Coursebook Corpus
Weka format 3.6.12
158 features
Attribute selection
Lynne Flowerdew
Language learning theories underpinning corpus-based pedagogy
The noticing hypothesis (Schmidt)
Attention consciously drawn
Noticing linked to frequency counts
Implicit vs explicit learning
Constructivist learning
Learners engage in discovery learning
Inductive learning
Cognitive skills, problem solving to understand new data
Widmann et al. 2011: the more possible starting points for exploitation, the more likely for different learners- SACODEYL project.
Sociocultural theory
What about language learning outside the classroom and incidental learning?
Learner corpus research: a fast-growing interdisciplinary field
Sylviane Granger
LCR IS an interdisciplinary research
Design: learner and taks variables to control
Not only English language
Method: CIA (Granger, 1996) and computer-aided error analysis
Wider spectrum of linguistic analysis
Interpretation: focus on transfer but this is changing; growing integration of SLA theory
Applications: few up-and-running resources but great potential
Version 3 (2016 or 2017) around 30 L1s as opposed to 11 L1s in Version 1
Learner corpora is a powerful heuristic resource
Corpus techniques make it possible to uncover new dimensions of learner language and lead to the formulation of new research questions: the L2 phrasicon (word combinations).
Prof. Granger brings up Leech’s preface to Learner English on Computer (1998)
Gradual change from mute corpora to sound aligned corpora
POS tagging has improved so much
Error-tagging: wide range of error tagging systems: multi-layer annotation systems
Parsing of learner data (90% accuracy Geertzen et al. 2014)
Static learner corpora vs monito corpora
CMC learner corpus (Marchand 2015)
Granger (2009) paper on the learner research field:
Granger, Sylviane. “The contribution of learner corpora to second language acquisition and foreign language teaching.” Corpora and language teaching 33 (2009): 13.
CIA V2 Granger (2015): a new model
SLA researchers are more interested in corpus data and corpus linguists are more familiar with SLA grounding
Implications are much more numerous than applications
Links with NLP: spell and gramar checking, learner feedback, native language id, etc.
Multiple perspectives on the same resource: richer insights and more powerful tools
Phraseology
Louvain English for Academic Purposes Dictionary (LEAD)
web-based
corpus based
descriptions of cross-disciplinary academic vocabulary
1200 lexical times around 18 functions (contrast, illustrate, quote, refer, etc.)
A really exciting application
Corpus Linguistics 2015, University of Lancaster, 21-24 July
Yu Yuan:
“Exploring the variation in world Learner Englishes: A multidimensional analysis of L2 written corpora”
109 features included in the analysis
RQ:
Can Biber’s model be extended?
How do features co-occur in learner English?
Data
ICLE 1.0 (Granger, 2002)
SWEECL 2.0 (Wen & Wang, 2008)
Tools
MA tagger Nini (2014) Manual here. Software (Windows) here.
Stanford Corenlp
R
Pythin scripts
Method
Kaisser’s criteria + Scree test for Factor Analysis
Results
10 dimensions stand out
Dimensions are largely epistemological, rhetorical and syntactical.
Through the corpora list & Prof. Mark Davies
::::::::::::::::::::::::::::::::::::
We are pleased to announce the release of the 1.6 billion word Hansard Corpus . The corpus is part of the SAMUELS project and has been funded by the AHRC (UK).
The Hansard Corpus contains 1.6 billion words from 7.6 million speeches in the British Parliament from 1803-2005. The corpus is semantically tagged, which allows for powerful meaning-based searches. In addition, users can create “virtual corpora” by speaker, time period, House of Parliament, and party in power, and compare across these corpora.
As with all of the other BYU corpora, the corpus allows queries by part of speech, lemma, synonym, customized word lists, and by section of the corpus (e.g. which words or phrases appear in one time period much more than in another). In terms of visualization, it allows users to view frequency listings (matching words and phrases), chart displays (overall frequency by time period), collocates (including comparisons between collocates of contrasting node words), and re-sortable concordance lines.
The end result is a corpus that will be of value not only to linguists (as the largest structured corpus of historical British English from the 1800s-1900s), but hopefully to historians, political scientists, and others as well.
http://www.hansard-corpus.org
============================================
Mark Davies
Professor of Linguistics / Brigham Young University
http://davies-linguistics.byu.edu/
Through the Corpora List
:::::::::::::::::::::::::::::::::::::
The “Language Science Press” has just published the following open access book in their series “Translation and Multilingual NLP”:
“NEW DIRECTIONS IN CORPUS-BASED TRANSLATION STUDIES” by Claudio Fantinuoli & Federico Zanettin (eds.)
Please download your free copy from http://langsci-press.org/catalog/book/76
ABSTRACT
Corpus-based translation studies has become a major paradigm and research methodology and has investigated a wide variety of topics in the last two decades. The contributions to this volume add to the range of corpus-based studies by providing examples of some less explored applications of corpus analysis methods to translation research. They show that the area keeps evolving as it constantly opens up to different frameworks and approaches, from appraisal theory to process-oriented analysis, and encompasses multiple translation settings, including (indirect) literary translation, machine(-assisted) translation and the practical work of professional legal translators. The studies included in the volume also expand the range of application of corpus applications in terms of the tools used to accomplish the research tasks outlined.