Asia-Pacific Chapter of the Association for Computational Linguistics (AACL)
10th International Joint Conference on Natural Language Processing (IJCNLP)
Taipei, Taiwan, November 20, 2022
Online and NTUH International Convention Center, Taipei
https://sites.google.com/view/cogalexvii2022
https://www.aacl2022.org/Program/workshops
Words are important for many tasks: communication, information access (search), and even thinking (brainstorming). This being so, one may wonder how to build tools supporting their learning and usage (access/navigation). Alas, the answer depends on a number of factors that are not always really simple: the user's background (age, expertise), the task (production/reception), the momentary cognitive state (information available at the onset of the search), the material support, etc. Words in books, computers, and the human brain are not the same. Being aware of this, different communities (linguists, lexicographers, psychologists) have focused on different issues —representation and organization of words; time course of retrieving a word; indexing, creation of navigational tools (dictionaries), etc.— yet, their views and respective goals have changed considerably over time.
Rather than considering the lexicon as a static entity, where discrete units (words) are organized alphabetically (database view), dictionaries are now viewed dynamically, i.e., as lexical graphs, whose entities are linked in various ways (topical relations; associations) and whose link weights may vary over time. While lexicographers view words as products, i.e., holistic entities, psychologists and neuroscientists view them as processes. Words are decomposed, and their synthesis requires various steps leading from some input (more or less clear idea, concept) to an output (word form).
Computational linguists have their own ways to look at words, which also have changed quite a bit over the years. Discrete count-based vector representations have successively been replaced by continuous vectors (i.e., word embeddings), and then by language-model-based contextualized representations which outperform the static models (including word embeddings) in a broad range of tasks.
As one can see, different communities look at words from different angles, which can be an asset and a problem. It is an asset, as complementary views may help us to broaden and deepen our understanding of this fundamental cognitive resource. Yet, this diversity of perspectives can also be a problem, in particular in a dynamic field like ours that is so rapidly moving on. Hence, it becomes harder and harder for everyone, including experts, to remain fully informed about the latest changes (state of the art). This is one of the reasons why we organize this workshop. More precisely, our goal is not only to keep people informed without getting them crushed by the information glut, but also to help them to perceive clearly what is new, relevant, and hence important. Last, but not least, we would like to connect people from different communities in the hope that this may help them to gain new insights or inspiration.
2 Scope and Topics
This workshop is about possible enhancements of lexical resources (representation, organization of the data, etc.). To allow for this, we invite researchers to submit their contributions. The idea is to discuss the limitations of existing resources and to explore possible enhancements that take into account new developments, the users’ and the engineers' needs (computational aspects).
For this workshop, we solicit papers including but not limited to the following topics, each of which can be considered from various points of view: linguistics (lexicography, computational- or corpus linguistics), neuro- or psycholinguistics (tip-of-the-tongue problem, word associations), network-related sciences (vector-based approaches, graph theory, small-world problem), and so on.
Micro- and macrostructure of the lexicon;
Indexical categories (taxonomies, thesaurus-like topical structures, etc.);
Map of the lexicon (topology) and relations between words (word associations).
Lexical representation (holistic, decomposed);
Meaning representation (concept-based, primitives);
Distributional semantics (count models, neural embeddings, etc.)
What information do language producers typically provide when looking for a word (terms, relations)?
What kind of relational information do they give: typed or untyped relations?
Which relations are typically used?
Manual, automatic, or collaborative building of dictionaries and indexes (crowdsourcing, serious games, etc.);
Extraction of associations from corpora to build semantic networks supporting navigation;
Automatic, or semi-automatic induction of the link type (e.g., synonym, hypernym, meronym, association, collocation, ...).
Concept dictionary;
Dictionary of larger segments than words (clauses, phrasal elements);
Dictionary of patterns or concept patterns;
Merging of various resources (dictionaries, thesauri, encyclopedia, episodic knowledge, i.e., shared and more or less recent news);
Dictionary of syllables.
Search based on sound (rhymes), meaning, or contextually related words (associations);
Determination of appropriate search space based on the user’s cognitive state (information available at the onset) and meta-knowledge (knowledge concerning the relationship between the input and the target word), ...
Identification of typical word access strategies (navigational patterns) used by people;
Interface problems, data visualization.
Submission page: https://softconf.com/aacl2022/CogALex-VII/user/scmd.cgi?scmd=submitPaperCustom&pageid=0
Other relevant information: https://www.aacl2022.org/Submission/paper#h.c6zwy6syj5r8
Submission Deadline: September 02, 2022
Workshop Date: November 20, 2022
https://sites.google.com/view/cogalexvii2022/home/important-dates
5 In case of questions
cogalex2022@gmail.com, or michael.zock@lis-lab.fr, Skype: mikazock