Evaluating DisCoCirc in Translation Tasks & its Limitations: A Comparative Study Between Bengali & English

TL;DR

This study evaluates the DisCoCirc formalism for translation between English and Bengali, revealing its limitations due to structural differences and highlighting areas for future enhancement in language processing frameworks.

Contribution

The paper extends DisCoCirc to Bengali, assesses its effectiveness in translation, and uncovers its limitations caused by language structural variations.

Findings

DisCoCirc performs well on many sentences but struggles with structural differences.

The framework faces limitations even with simple sentences.

Potential methods for overcoming these limitations are discussed.

Abstract

In [4], the authors present the DisCoCirc (Distributed Compositional Circuits) formalism for the English language, a grammar-based framework derived from the production rules that incorporates circuit-like representations in order to give a precise categorical theoretical structure to the language. In this paper, we extend this approach to develop a similar framework for Bengali and apply it to translation tasks between English and Bengali. A central focus of our work lies in reassessing the effectiveness of DisCoCirc in reducing language bureaucracy. Unlike the result suggested in [5], our findings indicate that although it works well for a large part of the language, it still faces limitations due to the structural variation of the two languages. We discuss the possible methods that might handle these shortcomings and show that, in practice, DisCoCirc still struggles even with relatively simple sentences. This divergence from prior claims not only highlights the framework's constraints in translation but also suggest scope for future improvement. Apart from our primary focus on English-Bengali translation, we also take a short detour to examine English conjunctions, following [1], showing a connection between conjunctions and Boolean logic.