DYNNETLAC

"Dynamic Networks for Lexical Access: Design, Navigation and Interface."

 Partecipanti

Mappa

 Word cloud

Esplora la "nuvola delle parole (Word Cloud) per avere un'idea di massima del progetto.

 Obiettivo del progetto (Objective)

'.Lexical insertion is a very important process in the production of language, whether verbal or written. It is often metaphorically stated that words are stored in a mental dictionary, called lexicon. The general belief is that the more entries in the lexicon, the better. But having a large number of stored data is not useful if we do not have the right tools to access the information we need. We know also from experience that the lexical choice is not always easy, and sometimes we fail to reach that precise word to express a certain idea, even though we know it exists. Psycholinguists call this fact the tip-of-the-tongue phenomenon or, more technically, dysnomia or anomia. Access to data from the lexicon depends on two factors: a) how words are organized, and b) which mechanisms exist to access the data. Complex Network theory (Newman, 2003) can help to both tasks: organization and navigation of the lexicon. Words can be organized by means of two-layer networks with a double dimension: syntagmatic and paradigmatic. Methods taken from DNA regulatory networks can help to design efficient and affordable navigation mechanisms capable to change the configuration while walked, in order to adjust to the necessities of the user. Therefore, this proposal aims using mildly bio-inspired dynamic complex networks to develop a computational implementation of computer-assisted writing to help users in cases of lexical access disorder, or dysnomia. The topic is related to complex network theory and semantics of natural languages. But the project also affects psychology and psycholinguistics, provided that it deals with a language disorder; cognitive modeling, when trying to simulate the organization of memory; natural language production, because we want to model an interactive mechanism to assist it, as well as biologically inspired theoretical computer science, when we take the model of genetic regulation to improve navigation.'

Introduzione (Teaser)

A person's vocabulary is known as their lexicon, a mental dictionary of sorts. EU-funded research addressed the problem that emerges when accessing this dictionary proves troublesome.

Descrizione progetto (Article)

The project 'Dynamic networks for lexical access: Design, navigation and interface' (DYNNETLAC) was set up to tackle the tip-of-the-tongue phenomenon, a kind of anomia. The research took as its starting point Newman's complex network theory (which can help in both organising and navigating the lexicon) and semantics of natural languages. The overall goal was to create dynamic networks that can help users overcome momentary blocks to accessing a desired word.

To this end, the team set and achieved several sub-goals. The first entailed building lexical networks capable of simulating humans when associating words. Using Wikipedia abstracts and the British National Corpus as corpora, graphs were designed containing only verbs, nouns and adjectives, and considering only immediate 'neighbours'.

The team built on research initiated by WordNet to design lexical networks that approximate the mental lexicon. DYNNETLAC also evaluated the potential for modelling navigation in complex networks using methods from DNA regulatory networks. Investigations considered how methodological interactions between biology and mathematical systems can be tailored to a linguistic model.

A lesser developed objective was the design of a man-machine interaction system for searching the graphs for clues. Work did not progress in this area primarily for reasons of poor technical compatibility when trying to integrate the chosen programming language (Python) in the dynamic web page design. This is a known issue that other (non-project) researchers are addressing.

DYNNETLAC tested its system by comparing its best-ranked words with primary responses retrieved by humans in the Edinburgh Association Thesaurus (EAT). Although the results were positive, the team acknowledges it would be better if the system matched their first word with the one given by the EAT.

Project activities also involved a training component relevant to the research topic, new research methodologies, and developing skills relevant to computational implementation of formal and mathematical linguistic theories. Other efforts included initiating interactions and collaboration with the Natural Language Processing community.

Overall, project results open a new line of research: the use of automatically generated non-annotated resources to simulate human cognitive capabilities. Although more research is needed, DYNNETLAC demonstrated that very simple techniques can be used to describe major processes of natural language generation.