---
title: "Constructing a Regional Slang Lexicon for Electricity Demands via Soft-Label Bidirectional Anchoring and Active Learning"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.04231v1"
permalink: "https://feed.astralor.com/items/itm_902957343c0c74b61e7629cd"
published: "2026-11-03T03:11:35.000Z"
score: 60
channel: "tech"
tags: ["LLM","RAG","多模态","Constructing","Regional Slang Lexicon","Electricity Demands","Soft-Label Bidirectional Anchoring","Active Learning Power-grid"]
---

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

## At a glance

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, sem…

## Key points

- 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.

## Full text

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 $κ$. 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 ($n=46$) yields $κ_{\text{dialect}}=1.0$ and $κ_{\text{power}}=0.85$. The resulting 25--33-term lexicon, 4--5 of which are power-relevant, provides a preliminary resource for dialect-aware power-grid service NLP.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_902957343c0c74b61e7629cd