Linguistic Semantics, Text Organization and NLP




Greetings!!


This site was constructed as part of a Fellowship funded by the

Cultural Heritage Informatics initiative (CHI)

administered by the

Department of Anthropology

in partnership with the

Lab for Educational Advancement in Digital Research

at Michigan State University.


This site does Five primary things.


  1. Teaches a bit about Natural Language Semantics
  2. Teaches a bit about how that work relates to Natural Language Processing
  3. Serves as a tutorial on a few NLP techniques
  4. Demonstrates how the organizational structure of a text can be hinted at using Semantic information
  5. Shows how this all relates to Cultural Heritage research via a novel research project



A few words on the project


Linguistic Semantics, Text Organization and NLP is a project with three specific goals. First, it aims to educate those engaged in Cultural Heritage work and the Digital Humanities about the tools and techniques employed by Linguists in the area of Natural Language Semantics, i.e. what linguists say about exploring meaning. Secondly, it introduces some NLP techniques which this group of researchers may wish to use to begin a text analysis project of their own. Third, it demonstrates how these techniques have been used by the author in a novel research project. The project seeks to improve the methodology by which we can use NLP to help us organize textual sources (documents) of an unknown structure. The information on all of these topics is presented in somewhat independent modules and therefore, the site can be explored by a user to investigate in whatever manner that they would like.

There are two primary ideas that have motivated the creation of this site. First, researchers who are engaging in Cultural Heritage and Digital Humanities (CHDH) projects often do not have formal Linguistic training. However, they do have a high degree of proficiency in “thinking” about language in a variety of ways and frequently hail from fields where language work of some type is key. That is, they are Philosophers, Poets, Anthropologists, Archaeologists, Historians, Literary Scholars, Librarians, etc. This group is well prepared to learn a little bit about Semantic research and then run with it. Secondly, there is an overall need to incorporate more insights from Linguistics into NLP research. A primary area that everyone needs to think more about is the Semantics and Pragmatics of Natural Languages. What this entails is fundamentally different (not better or worse) from what “Semantics” often means in the NLP community. Overall, the goal here is to provide enough of an introduction to Natural Language Semantics that researchers can begin to think more about it in their research design and also, in the interest of creating the most vibrant research possible, allow for more clarity regarding how we discuss the phenomena that we are interested in. That is, we need to improve the vocabulary that we use to share our ideas and our approaches. This site will teach everyone some ways to do just that.