Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision 		Previous revision
course:esslli2021:start [2021/08/04 19:30]
schtepf [Organizational information] 		course:esslli2021:start [2022/08/11 12:26]
schtepf [Hands-on Distributional Semantics (ESSLLI 2021 / 2022)]
Line 1: Line 1:
-====== Hands-on Distributional Semantics (ESSLLI 2021)  ======+====== Hands-on Distributional Semantics (ESSLLI 2021 / 2022)  ======
  
 **Hands-on Distributional Semantics – From first steps to interdisciplinary applications** **Hands-on Distributional Semantics – From first steps to interdisciplinary applications**
 +[[https://2022.esslli.eu/|{{ :course:esslli2021:esslli2022_logo.png?150|ESSLLI 2022 (Galway)}}]]
 [[https://esslli2021.unibz.it/|{{ :course:esslli2021:esslli21.png?250|ESSLLI 2021 (online)}}]] [[https://esslli2021.unibz.it/|{{ :course:esslli2021:esslli21.png?250|ESSLLI 2021 (online)}}]]
 \\ \\
 //Foundational course at [[https://esslli2021.unibz.it/page/course/hands_on_distributional_semantics_from_first_steps_to_interdisciplinary_applications_introductory_course/|ESSLLI 2021]], online, August 9–13, 2021// //Foundational course at [[https://esslli2021.unibz.it/page/course/hands_on_distributional_semantics_from_first_steps_to_interdisciplinary_applications_introductory_course/|ESSLLI 2021]], online, August 9–13, 2021//
 +\\
 +
 +**Hands-on Distributional Semantics for Linguistics using R**
 +\\
 +//Foundational course at [[https://2022.esslli.eu/courses-workshops-accepted/week-1-and-2-schedule.html#W1|ESSLLI 2022]], Galway, Ireland, August 8–12, 2022//
 +\\
 +
  
   * [[course:material|Software & data sets]]   * [[course:material|Software & data sets]]
Line 10: Line 18:
  
 {{:icon_star.png?24 }} {{:icon_star.png?24 }}
-  * check this page for updates and instructions by **Friday, August 6th, 2021** (late afternoon CEST) +  * update of all materials for the 2022 edition of the course has been completed 
-  * please install software and download data sets on the weekend before the course (i.e. on August 7th or 8th) as we may be making changes or uploading new versions until then+  * //Thanks for attending our course! It's a pleasure working with you.//
  
 ===== Course description ===== ===== Course description =====
  
-Distributional semantic models (DSM) are based on the assumption that the meaning of a word can (at least to a certain extent) be inferred from its usage, i.e. its distribution in text. Therefore, these models dynamically build semantic representations through a statistical analysis of the contexts in which words occur. DSMs are a promising technique for solving the lexical acquisition bottleneck by unsupervised learning, and their distributed representation provides a cognitively plausible, robust and flexible architecture for the organisation and processing of semantic information.+Distributional semantic models (DSM) – also known as “word space”, “distributional similarity”, or more recently “word embeddings” – are based on the assumption that the meaning of a word can (at least to a certain extent) be inferred from its usage, i.e. its distribution in text. Therefore, these models dynamically build semantic representations – in the form of high-dimensional vector spaces – through a statistical analysis of the contexts in which words occur. DSMs are a promising technique for solving the lexical acquisition bottleneck by unsupervised learning, and their distributed representation provides a cognitively plausible, robust and flexible architecture for the organisation and processing of semantic information.
  
-In this introductory course we will highlight the interdisciplinary potential of DSM beyond standard semantic similarity tasks, with applications in cognitive modeling and theoretical linguistics. This course aims to equip participants with the background knowledge and skills needed to build different kinds of DSM representations and apply them to a wide range of tasks. There will be a particular focus on practical exercises with the user-friendly [[http://www.r-project.org/|R]] software package [[http://wordspace.r-forge.r-project.org/|wordspace]] and various pre-built models.+In this introductory course we will highlight the interdisciplinary potential of DSM beyond standard semantic similarity tasks, with applications in cognitive modeling and theoretical linguistics. This course aims to equip participants with the background knowledge and skills needed to build different kinds of DSM representations – from traditional “count” models to neural word embeddings – and apply them to a wide range of tasks. The hands-on sessions will be conducted in [[http://www.r-project.org/|R]] with the user-friendly [[http://wordspace.r-forge.r-project.org/|wordspace]] package and various pre-built models.
  
-**Lecturers:** [[http://www.stefan-evert.de/|Stefan Evert]] (FAU Erlangen-Nürnberg) & [[https://www.ims.uni-stuttgart.de/en/institute/team/Lapesa/|Gabriella Lapesa]] (IMS, U Stuttgart)+ 
 +**Lecturers:** [[https://www.stephanie-evert.de/|Stephanie Evert]] (FAU Erlangen-Nürnberg) & [[https://www.ims.uni-stuttgart.de/en/institute/team/Lapesa/|Gabriella Lapesa]] (IMS, U Stuttgart)
  
 ===== Organizational information ===== ===== Organizational information =====
  
-Please make sure you have up-to-date versions of **[[https://www.r-project.org/|R]]** and **[[https://rstudio.org|RStudio]]** to participate in the hands-on exercises.+Please make sure you have up-to-date versions of **[[https://www.r-project.org/|R]]** and **[[https://rstudio.org|RStudio]]** to participate in the hands-on exercises.  Follow the detailed [[course:material|set-up instructions]] and download (some of) the data sets and precompiled DSMs. 
 +Additional instructions will be given in the first session on Monday. In particular, you will be asked to download and install the ''wordspaceEval'' package using a password provided in the course.
  
-We will answer questions during lectures and in the afternoon via the course's [[https://esslli21.slack.com/archives/C028KS92G3Z|Slack channel]]. Registered participants of ESSLLI 2021 should have access to this channel.+/* We will answer questions during lectures and in the afternoon via the course's [[https://esslli21.slack.com/archives/C028KS92G3Z|Slack channel]]. Registered participants of ESSLLI 2021 should have access to this channel. */
  
  
-{{:under_construction.png?48 |Under Construction}} 
- 
-\\ 
-**Further information on required software packages and data sets will be provided by Saturday, August 7th, 2021.**   
-\\ 
-\\ 
  
  
 ===== Schedule & handouts ===== ===== Schedule & handouts =====
- 
-{{:under_construction.png?48 |Under Construction}} 
- 
-\\ 
-**Handouts and other materials will be made available along with the course.**   
-\\ 
-\\ 
- 
- 
-<!-- 
  
 === Day 1: Introduction === === Day 1: Introduction ===
  
-{{:course:esslli2018:dsm_tutorial_part1.slides.pdf|Presentation slides}} (PDF, 1.1 MB) – {{:course:esslli2018:dsm_tutorial_part1.handout.pdf|handout}} (PDF, 0.9 MB) – {{:course:esslli2018:part1_examples.R|R code}} +[[http://wordspace.collocations.de/lib/exe/fetch.php/course:esslli2021:esslli2022_part1.slides.pdf|presentation slides]] (PDF, 2.1 MB) – [[http://wordspace.collocations.de/lib/exe/fetch.php/course:esslli2021:esslli2022_part1.handout.pdf|handout]] (PDF, 1.7 MB) – R code: [[http://wordspace.collocations.de/lib/exe/fetch.php/course:esslli2021:hands_on_day1.R|hands_on_day1.R]]
- +
-  * motivation and brief history of distributional semantics +
-  * common DSM architectures & prototypical applications +
-  * first practical exercises with the ''wordspace'' package +
- +
- +
-=== Day 2: The parameters of a DSM === +
- +
-{{:course:esslli2018:dsm_tutorial_part2.slides.pdf|Presentation slides}} (PDF, 1.3 MB) – {{:course:esslli2018:dsm_tutorial_part2.handout.pdf|handout}} (PDF, 1.0 MB) – {{:course:esslli2018:part2_examples.R|R code}} – {{:course:esslli2018:part2_input_formats.R|practice: input formats}} – {{:course:esslli2018:part2_exercise.R|exercise (DSM parameters)}}+
  
 +  * motivation and geometric intuition
 +  * distributional vs. semantic similarity
 +  * outline of the course
 +  * practice: //software setup, first steps with the ''wordspace'' package//
  
-  * taxonomy of DSM parameters: context representation, feature scaling, normalization and standardization, distance/similarity measures, dimensionality reduction +=== Day 2: Building a DSM ===
-  * overview of common parameter settings & best-practice recommendations +
-  * practical exercises: building DSMs and exploring their parameters+
  
 +[[http://wordspace.collocations.de/lib/exe/fetch.php/course:esslli2021:esslli2022_part2.slides.pdf|presentation slides]] (PDF, 1.6 MB) –
 +[[http://wordspace.collocations.de/lib/exe/fetch.php/course:esslli2021:esslli2022_part2.handout.pdf|handout]] (PDF, 1.2 MB) –
 +R code: [[http://wordspace.collocations.de/lib/exe/fetch.php/course:esslli2021:hands_on_day2.R|hands_on_day2.R]] –
 +bonus material: [[http://wordspace.collocations.de/lib/exe/fetch.php/course:esslli2021:hands_on_day2_input_formats.R|hands_on_day2_input_formats.R]]
  
-=== Day 3: Applications and evaluation ===+  * formal definition of a DSM, taxonomy of parameters 
 +  * collecting co-occurrence data: what counts as a context? 
 +  * mathematical operations on DSM vectors 
 +  * computing distances/similarities 
 +  * practice: //building DSMs and exploring different parameter settings//
  
-{{:course:esslli2018:dsm_tutorial_part3.slides.pdf|Presentation slides}} (PDF, 2.0 MB) – {{:course:esslli2018:dsm_tutorial_part3.handout.pdf|handout}} (PDF, 1.8 MB) – {{:course:esslli2018:part3_examples.R|R code}} – {{:course:esslli2018:part3_exercise.R|exercise (evaluation)}}+=== Day 3: Which aspects of meaning does a DSM capture? ===
  
-  * attributional and relational similarity, clustering and semantic categorization, multiple-choice tasks +[[http://wordspace.collocations.de/lib/exe/fetch.php/course:esslli2021:esslli2022_part3.slides.pdf|presentation slides]] (PDF, 3.2 MB) – 
-/*  * supervised & unsupervised classification based on DSM vectors */ +[[http://wordspace.collocations.de/lib/exe/fetch.php/course:esslli2021:esslli2022_part3.handout.pdf|handout]] (PDF, 2.9 MB) – 
-  * insights from recent parameter evaluation studies +R code: [[http://wordspace.collocations.de/lib/exe/fetch.php/course:esslli2021:hands_on_day3_exercise_1.R|hands_on_day3_exercise_1.R]], [[http://wordspace.collocations.de/lib/exe/fetch.php/course:esslli2021:hands_on_day3_exercise_2.R|hands_on_day3_exercise_2.R]]
-  * practical exercises: implementation and evaluation of selected tasks+
  
 +  * evaluation: conceptual coordinates
 +  * standard evaluation tasks (multiple choice, correlation, clustering)
 +  * narrowing down similarity: classifying semantic relations
 +  * practice: //evaluation of selected tasks//
  
-=== Day 4: Elements of matrix algebra ===+=== Day 4: DS beyond NLP – Linguistic theory ===
  
-{{:course:esslli2018:dsm_tutorial_part4.slides.pdf|Presentation slides}} (PDF, 0.7 MB) – {{:course:esslli2018:dsm_tutorial_part4.handout.pdf|handout}} (PDF, 0.6 MB) – {{:course:esslli2018:part4_examples.R|R code}} – {{:course:esslli2018:schuetze1998.R|bonus practice: Schütze-style WSD}} – {{:course:esslli2018:part4_exercise.R|exercise (roll your own DSM)}}+[[http://wordspace.collocations.de/lib/exe/fetch.php/course:esslli2021:esslli2022_part4.slides.pdf|presentation slides]] (PDF, 3.6 MB) – 
 +[[http://wordspace.collocations.de/lib/exe/fetch.php/course:esslli2021:esslli2022_part4.handout.pdf|handout]] (PDF, 3.5 MB) – 
 +R code: [[http://wordspace.collocations.de/lib/exe/fetch.php/course:esslli2021:hands_on_day4.R|hands_on_day4.R]] – 
 +bonus material: [[http://www.collocations.de/data/esslli2021/schuetze1998.R|schuetze1998.R]]
  
-  * basic matrix and vector operations, orthogonal projection & dimensionality reduction 
-  * singular value decomposition (SVD) 
-  * practical exercises: roll your own DSM with matrix operations 
  
 +  * linguistic exploitation of DSM representations
 +  * a textbook challenge for DSMs: polysemy
 +  * success stories: semantic compositionality, morphological transparency, argument structure
 +  * issues: not all words have a distributional meaning
 +  * practice: //different exercises with linguistic data sets//
  
-=== Day 5: Making sense of DSMs ===+=== Day 5: DS beyond NLP – Cognitive modelling ===
  
-  * mathematical properties of and relations between different types of DSM +[[http://wordspace.collocations.de/lib/exe/fetch.php/course:esslli2021:esslli2022_part5.slides.pdf|presentation slides]] (PDF, 1.6 MB) – 
-  * singular value decomposition (SVD) as a latent class model +[[http://wordspace.collocations.de/lib/exe/fetch.php/course:esslli2021:esslli2022_part5.handout.pdf|handout]] (PDF, 1.4 MB) – 
-  * comparison with neural vector embeddings+R code: [[http://wordspace.collocations.de/lib/exe/fetch.php/course:esslli2021:hands_on_day5.R|hands_on_day5.R]] – 
 +bonus task: [[http://www.collocations.de/data/CogALex4.rda|CogALex4.rda]] (0.2 MB) – 
 +bonus material: [[http://wordspace.collocations.de/lib/exe/fetch.php/course:esslli2021:hands_on_day5_matrix_factorization.R|hands_on_day5_matrix_factorization.R]] 
  
--->+  * DSMs for cognitive modelling 
 +  * free association norms as a window into the mental lexicon 
 +  * predicting free associations with DSMs 
 +  * practice: //combining DSMs with first-order co-occurrence for the FAST task//
  

You are here: start » course » esslli2021