Resource-Lean Lexicon Induction for German Dialects

• URL: http://arxiv.org/abs/2604.23824v1
• Date: Sun, 26 Apr 2026 18:09:56 GMT
• Title: Resource-Lean Lexicon Induction for German Dialects
• Abstract summary: We show that statistical models trained on string similarity features are surprisingly effective for inducing German dialect lexicons.<n>They outperform large language models, enable cross-dialect transfer, and offer a lightweight data-driven alternative.<n>Motivated by the resource scarcity in dialects, we further investigate the extent to which models transfer across different German dialects.
• Score: 42.23792930877588
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Automatic induction of high-quality dictionaries is essential for building lexical resources, yet low-resource languages and dialects pose several challenges: limited access to annotators, high degree of spelling variations, and poor performance of large language models (LLMs). We empirically show that statistical models (random forests) trained on string similarity features are surprisingly effective for inducing German dialect lexicons. They outperform LLMs, enable cross-dialect transfer, and offer a lightweight data-driven alternative. We evaluate our models intrinsically on bilingual lexicon induction (BLI) and extrinsically on dialect information retrieval (IR). On BLI, random forests outperform Mistral-123b while being more resource-lean. On dialect IR with BM25, using our dialect dictionaries for query expansion yields relative improvements of up to 28.9% in nDCG@10 and 50.7% in Recall@100. Motivated by the resource scarcity in dialects, we further investigate the extent to which models transfer across different German dialects, and their performance under varying amounts of training data.

Related papers

• Sometin Beta Pass Notin (SBPN): Improving Multilingual ASR for Nigerian Languages via Knowledge Distillation [1.9346797099839141]
  Nigerian languages present unique modelling hurdles, including acute data scarcity, inconsistent orthography, tonal diacritics, diverse accents, frequent code-switching, and localized named entities.<n>To address these challenges, we developed a multilingual ASR framework utilizing a two-stage distillation process.<n>We introduce Sometin Beta Pass Notin (SBPN), a foundational multilingual ASR model covering Yorb, Hausa, Igbo, Nigerian Pidgin, and Nigerian English.
  arXiv  Detail & Related papers  (2026-05-18T00:22:18Z)
• Low-Resource Dialect Adaptation of Large Language Models: A French Dialect Case-Study [0.043496401697112684]
  We study the use of continual pre-training (CPT) for dialect learning under tight data and compute budgets.<n>We adapt three large language models to the Qu'ebec French dialect using a very small dataset and benchmark them on the COLE suite.<n>Our experiments demonstrate an improvement on the minority dialect benchmarks with minimal regression on the prestige language benchmarks with under 1% of model parameters updated.
  arXiv  Detail & Related papers  (2025-10-26T16:49:06Z)
• Make Every Letter Count: Building Dialect Variation Dictionaries from Monolingual Corpora [38.54622638611305]
  We use Bavarian as a case study and investigate the lexical dialect understanding capability of Large Language Models (LLMs)<n>We use DiaLemma, a novel annotation framework for creating dialect variation dictionaries from monolingual data only.<n>We evaluate how well nine state-of-the-art LLMs can judge Bavarian terms as dialect translations, inflected variants, or unrelated forms of a given German lemma.
  arXiv  Detail & Related papers  (2025-09-22T14:49:08Z)
• Leveraging LLM and Self-Supervised Training Models for Speech Recognition in Chinese Dialects: A Comparative Analysis [4.774607166378613]
  Self-supervised pre-training, combined with large language models (LLM), can effectively enhance ASR performance in low-resource scenarios.<n>We pre-train a Data2vec2 model on 300,000 hours of unlabeled dialect and accented speech data and do alignment training on a supervised dataset of 40,000 hours.
  arXiv  Detail & Related papers  (2025-05-27T12:50:55Z)
• Cross-Dialect Information Retrieval: Information Access in Low-Resource and High-Variance Languages [23.947119147068925]
  A large amount of local and culture-specific knowledge can only be found in documents written in dialects.<n>We introduce the first German dialect retrieval dataset, dubbed WikiDIR, which consists of seven German dialects extracted from Wikipedia.<n>We show that commonly used zero-shot cross-lingual transfer approach with multilingual encoders do not transfer well to extremely low-resource setups.
  arXiv  Detail & Related papers  (2024-12-17T11:21:09Z)
• The Belebele Benchmark: a Parallel Reading Comprehension Dataset in 122 Language Variants [80.4837840962273]
  We present Belebele, a dataset spanning 122 language variants. This dataset enables the evaluation of text models in high-, medium-, and low-resource languages.
  arXiv  Detail & Related papers  (2023-08-31T17:43:08Z)
• Chain-of-Dictionary Prompting Elicits Translation in Large Language Models [100.47154959254937]
  Large language models (LLMs) have shown surprisingly good performance in multilingual neural machine translation (MNMT) We present a novel method, CoD, which augments LLMs with prior knowledge with the chains of multilingual dictionaries for a subset of input words to elicit translation abilities.
  arXiv  Detail & Related papers  (2023-05-11T05:19:47Z)
• High-resource Language-specific Training for Multilingual Neural Machine Translation [109.31892935605192]
  We propose the multilingual translation model with the high-resource language-specific training (HLT-MT) to alleviate the negative interference. Specifically, we first train the multilingual model only with the high-resource pairs and select the language-specific modules at the top of the decoder. HLT-MT is further trained on all available corpora to transfer knowledge from high-resource languages to low-resource languages.
  arXiv  Detail & Related papers  (2022-07-11T14:33:13Z)
• UNKs Everywhere: Adapting Multilingual Language Models to New Scripts [103.79021395138423]
  Massively multilingual language models such as multilingual BERT (mBERT) and XLM-R offer state-of-the-art cross-lingual transfer performance on a range of NLP tasks. Due to their limited capacity and large differences in pretraining data, there is a profound performance gap between resource-rich and resource-poor target languages. We propose novel data-efficient methods that enable quick and effective adaptation of pretrained multilingual models to such low-resource languages and unseen scripts.
  arXiv  Detail & Related papers  (2020-12-31T11:37:28Z)
• XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning [68.57658225995966]
  Cross-lingual Choice of Plausible Alternatives (XCOPA) is a typologically diverse multilingual dataset for causal commonsense reasoning in 11 languages. We evaluate a range of state-of-the-art models on this novel dataset, revealing that the performance of current methods falls short compared to translation-based transfer.
  arXiv  Detail & Related papers  (2020-05-01T12:22:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.