Amirhossein Layegh

Amirhossein Layegh

PhD Student

Publications

Zero-shot relation extraction (RE) presents the challenge of identifying entity relationships from text without training on those specific relations. Despite significant advancements in natural language processing by applying large language models (LLMs), their application to zero-shot RE remains less effective compared to traditional models that fine-tune smaller pre-trained language models. This limitation is attributed to insufficient prompting strategies that fail to leverage the full capabilities of LLMs for zero-shot RE, considering the intrinsic complexities of the RE task. A compelling question is whether LLMs can address complex tasks, such as RE, by decomposing them into more straightforward, distinct tasks that are easier to manage and solve individually. We propose the Refine-Estimate-Answer (REA) approach to answer this question. This multi-stage prompting strategy of REA decomposes the RE task into more manageable subtasks and applies iterative refinement to guide LLMs through the complex reasoning required for accurate RE. Our research validates the effectiveness of REA through comprehensive testing across multiple public RE datasets, demonstrating marked improvements over existing LLM-based frameworks. Experimental results on the FewRel, Wiki-ZSL, and TACRED datasets show that our proposed approach significantly boosts the vanilla prompting F1 scores by 31.57, 19.52, and 15.39, respectively, thereby outperforming the performance of state-of-the-art LLM-based methods.

Prompt-tuning and instruction-tuning of language models have exhibited significant results in few-shot Natural Language Processing (NLP) tasks, such as Relation Extraction (RE), which involves identifying relationships between entities within a sentence. However, the effectiveness of these methods relies heavily on the design of the prompts. A compelling question is whether incorporating external knowledge can enhance the language model’s understanding of NLP tasks. In this paper, we introduce wiki-based prompt construction that leverages Wikidata as a source of information to craft more informative prompts for both prompt-tuning and instruction-tuning of language models in RE. Our experiments show that using wiki-based prompts enhances cutting-edge language models in RE, emphasizing their potential for improving RE tasks.

Prompt-based language models have produced encouraging results in numerous applications, including Named Entity Recognition (NER) tasks. NER aims to identify entities in a sentence and provide their types. However, the strong performance of most available NER approaches is heavily dependent on the design of discrete prompts and a verbalizer to map the model-predicted outputs to entity categories, which are complicated undertakings. To address these challenges, we present ConstrastNER, a prompt-based NER framework that employs both discrete and continuous tokens in prompts and uses a contrastive learning approach to learn the continuous prompts and forecast entity types. The experimental results demonstrate that ContrastNER obtains competitive performance to the state-of-the-art NER methods in high-resource settings and outperforms the state-of-the-art models in low-resource circumstances without requiring extensive manual prompt engineering and verbalizer design.

This paper presents a survey of existing tools for Big Data pipeline orchestration based on a comparative framework developed in the DataCloud project. We propose criteria for evaluating the tools to support reusability, flexible pipeline communication modes, and separation of concerns in Big Data pipeline descriptions. This survey aims to identify research and technological gaps and to recommend approaches for filling them. Further work in the DataCloud project is oriented towards the design, implementation, and practical evaluation of the recommended approaches.