Cross-Domain Ambiguity Detection using Linear Transformation of Word Embedding Spaces
The requirements engineering process is a crucial stage of the software development life cycle. It involves various stakeholders from different professional backgrounds, particularly in the requirements elicitation phase. Each stakeholder carries distinct domain knowledge, causing them to differently interpret certain words, leading to cross-domain ambiguity. This can result in misunderstanding amongst them and jeopardize the entire project. This paper proposes a natural language processing approach to find potentially ambiguous words for a given set of domains. The idea is to apply linear transformations on word embedding models trained on different domain corpora, to bring them into a unified embedding space. The approach then finds words with divergent embeddings as they signify a variation in the meaning across the domains. It can help a requirements analyst in preventing misunderstandings during elicitation interviews and meetings by defining a set of potentially ambiguous terms in advance. The paper also discusses certain problems with the existing approaches and discusses how the proposed approach resolves them.
Code (1)
Similar Papers 제목 키워드 기반
CRAB: Camera-Radar Fusion for Reducing Depth Ambiguity in Backward Projection based View Transformation
Recently, camera-radar fusion-based 3D object detection methods in bird's eye view (BEV) have gained attention due to the complementary characteristics and cost-effectiveness of these sensors. Previous approaches using f…
3D Object DetectionDetection, Rectification and Segmentation of Coplanar Repeated Patterns
This paper presents a novel and general method for the detection, rectification and segmentation of imaged coplanar repeated patterns. The only assumption made of the scene geometry is that repeated scene elements are ma…
Feature Transformation Enhanced Jacobi Polynomial Graph Filtering for Graph Anomaly Detection
In recent years, graph anomaly detection (GAD) based on frequency-domain filtering have achieved promising results. However, existing approaches still face three major challenges: First, they use static basic function to…
Graph Anomaly DetectionLinear Representations of Hierarchical Concepts in Language Models
We investigate how and to what extent hierarchical relations (e.g., Japan $\subset$ Eastern Asia $\subset$ Asia) are encoded in the internal representations of language models. Building on Linear Relational Concepts, we …
Domain GeneralizationSparse Neurons Carry Strong Signals of Question Ambiguity in LLMs
Ambiguity is pervasive in real-world questions, yet large language models (LLMs) often respond with confident answers rather than seeking clarification. In this work, we show that question ambiguity is linearly encoded i…