Massey Documents by Type

Permanent URI for this communityhttps://mro.massey.ac.nz/handle/10179/294

Browse

Subject: search.filters.subject.Natural language processing

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Large language models for ingredient substitution in food recipes using supervised fine-tuning and direct preference optimization
    (Elsevier B.V., 2025-09) Senath T; Athukorala K; Costa R; Ranathunga S; Kaur R
    In this paper, we address the challenge of recipe personalization through ingredient substitution. We make use of Large Language Models (LLMs) to build an ingredient substitution system designed to predict plausible substitute ingredients within a given recipe context. Given that the use of LLMs for this task has been barely done, we carry out an extensive set of experiments to determine the best LLM, prompt, and the fine-tuning setups. We further experiment with methods such as multi-task learning, two-stage fine-tuning, and Direct Preference Optimization (DPO). The experiments are conducted using the publicly available Recipe1MSub corpus. The best results are produced by the Mistral7-Base LLM after fine-tuning and DPO. This result outperforms the strong baseline available for the same corpus with a Hit@1 score of 22.04. Although LLM results lag behind the baseline with respect to other metrics such as Hit@3 and Hit@10, we believe that this research represents a promising step towards enabling personalized and creative culinary experiences by utilizing LLM-based ingredient substitution.
  • Thumbnail Image
    Item
    SiTSE: Sinhala Text Simplification Dataset and Evaluation
    (Association for Computing Machinery, 2025-05-08) Ranathunga S; Sirithunga R; Rathnayake H; De Silva L; Aluthwala T; Peramuna S; Shekhar R; Zitouni I
    Text Simplification is a task that has been minimally explored for low-resource languages. Consequently, there are only a few manually curated datasets. In this article, we present a human-curated sentence-level text simplification dataset for the Sinhala language. Our evaluation dataset contains 1,000 complex sentences and 3,000 corresponding simplified sentences produced by three different human annotators. We model the text simplification task as a zero-shot and zero-resource sequence-to-sequence (seq-seq) task on the multilingual language models mT5 and mBART. We exploit auxiliary data from related seq-seq tasks and explore the possibility of using intermediate task transfer learning (ITTL). Our analysis shows that ITTL outperforms the previously proposed zero-resource methods for text simplification. Our findings also highlight the challenges in evaluating text simplification systems and support the calls for improved metrics for measuring the quality of automated text simplification systems that would suit low-resource languages as well. Our code and data are publicly available: https://github.com/brainsharks-fyp17/Sinhala-Text-Simplification-Dataset-andEvaluation.
  • Thumbnail Image
    Item
    The Application of Machine Learning to Consolidate Critical Success Factors of Lean Six Sigma
    (IEEE, 17/08/2021) Perera AD; Jayamaha NP; Grigg NP; Tunnicliffe M; Singh A
    Lean six sigma (LSS) is a quality improvement phenomenon that has captured the attention of the industry. Aiming at a capability level of 3.4 defects per million opportunities (Six Sigma) and efficient (lean) processes, LSS has been shown to improve business efficiency and customer satisfaction by blending the best methods from Lean and Six Sigma (SS). Many businesses have attempted to implement LSS, but not everyone has succeeded in improving the business processes to achieve expected outcomes. Hence, understanding the cause and effect relationships of the enablers of LSS, while deriving deeper insights from the functioning of the LSS strategy will be of great value for effective execution of LSS. However, there is little research on the causal mechanisms that explain how expected outcomes are caused through LSS enablers, highlighting the need for comprehensive research on this topic. LSS literature is overwhelmed by the diverse range of Critical Success Factors (CSFs) prescribed by a plethora of conceptual papers, and very few attempts have been made to harness these CSFs to a coherent theory on LSS. We fill this gap through a novel method using artificial intelligence, more specifically Natural Language Processing (NLP), with particular emphasis on cross-domain knowledge utilization to develop a parsimonious set of constructs that explain the LSS phenomenon. This model is then reconciled against published models on SS to develop a final testable model that explains how LSS elements cause quality performance, customer satisfaction, and business performance.