Inspicio: Open-Vocabulary, LLM-Based Sense Retrieval for Historical Languages

• URL: http://arxiv.org/abs/2609.00998v1
• Date: Tue, 01 Sep 2026 09:46:38 GMT
• Title: Inspicio: Open-Vocabulary, LLM-Based Sense Retrieval for Historical Languages
• Abstract summary: We present Inspicio, an open-vocabulary retrieval pipeline that links tokens in context to synsets of the Open English WordNet.<n>For each occurrence, an instruction-tuned LLM produces two English translations, a small set of candidate dictionary-style definitions, and a few candidate English lemmas.<n>We evaluate the pipeline across a 6x6 grid of LLMs and sentence-embedding models on a new bilingual set of manually annotated Latin and Ancient Greek perception verbs.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Word Sense Disambiguation has advanced rapidly for English and a handful of well-resourced modern languages, but it continues to assume the existence of a sense inventory and a word-to-sense mapping in the source language (Navigli, 2026). These assumptions break down for most historical and low-resource languages, whose dedicated WordNets are either incomplete or still under construction. We present Inspicio, an open-vocabulary retrieval pipeline that links tokens in context to synsets of the Open English WordNet (McCrae et al., 2020) without requiring any source-language inventory or mapping. For each occurrence, an instruction-tuned LLM produces two English translations of the surrounding sentence, a small set of candidate dictionary-style definitions, and a few candidate English lemmas. These outputs drive a hybrid retrieval step that combines dense definition-synset similarity, sparse lemma matching, and Maximal Marginal Relevance re-ranking. We evaluate the pipeline across a 6x6 grid of LLMs and sentence-embedding models on a new bilingual set of manually annotated Latin and Ancient Greek perception verbs, on a subset of PREMOVE dataset (Farina, 2025), and on a diachronic sample of Italian. The best configuration reaches 96% Recall@50 on the perception-verb test set, with each component contributing measurable gains, and remains competitive in the out-of-domain and cross-lingual settings.

Related papers

• Syntax as a Rosetta Stone: Universal Dependencies for In-Context Coptic Translation [6.070010259231488]
  This paper proposes a novel in-context learning approach to support low-resource machine translation of the Coptic language to English.<n>Our results show that while syntactic information alone is not as useful as dictionary-based glosses, combining retrieved dictionary items with syntactic information achieves significant gains across model sizes.
  arXiv  Detail & Related papers  (2026-04-20T19:07:32Z)
• Generating Concept Lexicalizations via Dictionary-Based Cross-Lingual Sense Projection [11.136711217530157]
  We generate senses by associating target-language lemmas with existing lexical concepts via semantic projection.<n>Our method projects English synsets onto aligned target-language tokens and assigns the corresponding lemmas to those synsets.<n>We evaluate the method on multiple languages, comparing it to prior methods, as well as dictionary-based and large language model baselines.
  arXiv  Detail & Related papers  (2026-04-15T20:27:26Z)
• MINERS: Multilingual Language Models as Semantic Retrievers [23.686762008696547]
  This paper introduces the MINERS, a benchmark designed to evaluate the ability of multilingual language models in semantic retrieval tasks. We create a comprehensive framework to assess the robustness of LMs in retrieving samples across over 200 diverse languages. Our results demonstrate that by solely retrieving semantically similar embeddings yields performance competitive with state-of-the-art approaches.
  arXiv  Detail & Related papers  (2024-06-11T16:26:18Z)
• A Novel Cartography-Based Curriculum Learning Method Applied on RoNLI: The First Romanian Natural Language Inference Corpus [71.77214818319054]
  Natural language inference is a proxy for natural language understanding. There is no publicly available NLI corpus for the Romanian language. We introduce the first Romanian NLI corpus (RoNLI) comprising 58K training sentence pairs.
  arXiv  Detail & Related papers  (2024-05-20T08:41:15Z)
• Always Keep your Target in Mind: Studying Semantics and Improving Performance of Neural Lexical Substitution [124.99894592871385]
  We present a large-scale comparative study of lexical substitution methods employing both old and most recent language models. We show that already competitive results achieved by SOTA LMs/MLMs can be further substantially improved if information about the target word is injected properly.
  arXiv  Detail & Related papers  (2022-06-07T16:16:19Z)
• Retrieval-Augmented Multilingual Keyphrase Generation with Retriever-Generator Iterative Training [66.64843711515341]
  Keyphrase generation is the task of automatically predicting keyphrases given a piece of long text. We call attention to a new setting named multilingual keyphrase generation. We propose a retrieval-augmented method for multilingual keyphrase generation to mitigate the data shortage problem in non-English languages.
  arXiv  Detail & Related papers  (2022-05-21T00:45:21Z)
• Learning Contextualised Cross-lingual Word Embeddings and Alignments for Extremely Low-Resource Languages Using Parallel Corpora [63.5286019659504]
  We propose a new approach for learning contextualised cross-lingual word embeddings based on a small parallel corpus. Our method obtains word embeddings via an LSTM encoder-decoder model that simultaneously translates and reconstructs an input sentence.
  arXiv  Detail & Related papers  (2020-10-27T22:24:01Z)
• Discovering Bilingual Lexicons in Polyglot Word Embeddings [32.53342453685406]
  In this work, we utilize a single Skip-gram model trained on a multilingual corpus yielding polyglot word embeddings. We present a novel finding that a surprisingly simple constrained nearest-neighbor sampling technique can retrieve bilingual lexicons. Across three European language pairs, we observe that polyglot word embeddings indeed learn a rich semantic representation of words.
  arXiv  Detail & Related papers  (2020-08-31T03:57:50Z)
• A Multi-Perspective Architecture for Semantic Code Search [58.73778219645548]
  We propose a novel multi-perspective cross-lingual neural framework for code--text matching. Our experiments on the CoNaLa dataset show that our proposed model yields better performance than previous approaches.
  arXiv  Detail & Related papers  (2020-05-06T04:46:11Z)
• Multi-SimLex: A Large-Scale Evaluation of Multilingual and Cross-Lingual Lexical Semantic Similarity [67.36239720463657]
  Multi-SimLex is a large-scale lexical resource and evaluation benchmark covering datasets for 12 diverse languages. Each language dataset is annotated for the lexical relation of semantic similarity and contains 1,888 semantically aligned concept pairs. Owing to the alignment of concepts across languages, we provide a suite of 66 cross-lingual semantic similarity datasets.
  arXiv  Detail & Related papers  (2020-03-10T17:17:01Z)

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.