cs.CLNov 3, 2026

Constructing a Regional Slang Lexicon for Electricity Demands via Soft-Label Bidirectional Anchoring and Active Learning

Authors: Rong Chang, Lijing Shi, Zhaoxiang Zang

Organizations: Yuxi Power Supply Bureau, Yunnan Power Grid Co., Ltd., Yuxi, 653100, China. · Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, 650504, China. · Key Laboratory of Artificial Intelligence in Yunnan Province, Kunming University of Science and Technology, Kunming, 650504, China.

Abstract

Power-grid customer service increasingly relies on community social media, where customers describe outages, billing, and equipment faults in informal regional dialect. Such messages exhibit non-standard morphology, semantic drift, and out-of-vocabulary expressions that make manual lexicon construction costly and degrade conventional NLP tools. We propose a weak-supervision framework constructing a regional slang lexicon from curated dialect anchors and power-domain seed terms. Candidates are generated via Pointwise Mutual Information with soft-label bidirectional anchoring, retaining dialect-anchored terms while recording power-domain relevance as separate metadata, and are scored by combining Sentence-BERT semantic similarity with a jieba-based wordhood measure. Uncertainty-aware active learning with rule-based and retrieval-augmented LLM oracles is applied under three query strategies, and the resulting lexicon is evaluated by a higher-capability LLM calibrated against human expert annotations via Cohen's κκ. On 11,177 real WeChat messages from Yuxi (Yunnan, China), the framework achieves an evaluator-estimated dialect precision of DP~==~1.0 with zero false positives. An ablation shows that soft-label layering retains 751% more candidates than strict power-gating at identical precision, expanding the candidate pool from 41 to 349 terms. Human calibration (n=46n=46) yields κdialect=1.0κ_{\text{dialect}}=1.0 and κpower=0.85κ_{\text{power}}=0.85. The resulting 25--33-term lexicon, 4--5 of which are power-relevant, provides a preliminary resource for dialect-aware power-grid service NLP.

Figures & tables

Explore similar work

CardsList
  1. slang.gr as a Large-Scale Crowdsourced Resource for Non-Standard Greek

    Jul 23, 2026Panagiotis Papadakos, Katerina Papantoniou, Dimitris PlexousakisComputational Social Science

  2. Community-Specific Slang and Entity Detection via Semantic Shift in Fine-Tuned Language Models

    Apr 19, 2026Julia Kruk, Sanchita Porwal, Amitrajit Bhattacharjee +1Social Media AnalysisWord Embeddings

  3. Resource-Lean Lexicon Induction for German Dialects

    Apr 26, 2026Robert Litschko, Barbara Plank, Diego FrassinelliLow-Resource Language Processing