Similarity between Units of Natural Language: The Transition from Coarse to Fine Estimation
This work addresses the need for more accurate and interpretable similarity measures in critical applications, though it appears incremental as it builds on existing regression and adversarial methods.
The paper tackles the problem of computing similarity between natural language units more precisely, especially for sensitive domains like legal or medical affairs, by developing a regression model that combines attack testing with adversarial training to catch loopholes and provide explanations, achieving state-of-the-art performance in handling edge cases.
Capturing the similarities between human language units is crucial for explaining how humans associate different objects, and therefore its computation has received extensive attention, research, and applications. With the ever-increasing amount of information around us, calculating similarity becomes increasingly complex, especially in many cases, such as legal or medical affairs, measuring similarity requires extra care and precision, as small acts within a language unit can have significant real-world effects. My research goal in this thesis is to develop regression models that account for similarities between language units in a more refined way. Computation of similarity has come a long way, but approaches to debugging the measures are often based on continually fitting human judgment values. To this end, my goal is to develop an algorithm that precisely catches loopholes in a similarity calculation. Furthermore, most methods have vague definitions of the similarities they compute and are often difficult to interpret. The proposed framework addresses both shortcomings. It constantly improves the model through catching different loopholes. In addition, every refinement of the model provides a reasonable explanation. The regression model introduced in this thesis is called progressively refined similarity computation, which combines attack testing with adversarial training. The similarity regression model of this thesis achieves state-of-the-art performance in handling edge cases.