Mar 2026· arXiv.org· Vol abs/2603.18184· 0 citations· 53 references
Computer Science
TL;DR
This work proposes CWoMP (Contrastive Word-Morpheme Pretraining), which instead treats morphemes as atomic form-meaning units with learned representations with particularly strong gains in extremely low-resource settings.
Abstract
Interlinear glossed text (IGT) is a standard notation for language documentation which is linguistically rich but laborious to produce manually. Recent automated IGT methods treat glosses as character sequences, neglecting their compositional structure. We propose CWoMP (Contrastive Word-Morpheme Pretraining), which instead treats morphemes as atomic form-meaning units with learned representations. A contrastively trained encoder aligns words-in-context with their constituent morphemes in a shared embedding space; an autoregressive decoder then generates the morpheme sequence by retrieving entries from a mutable lexicon of these embeddings. Predictions are interpretable--grounded in lexicon entries--and users can improve results at inference time by expanding the lexicon without retraining. We evaluate on diverse low-resource languages, showing that CWoMP outperforms existing methods while being significantly more efficient, with particularly strong gains in extremely low-resource settings.
This work proposes an alternative approach for identifying a sentence's past, present, or future global reference interval by encoding sentences using fixed-length inventory vectors that are comprised of part-of-speech counts, dependency relation counts, and explicit futurate pattern counts.
We introduce grounded glossary generation, a structured task requiring models to recover semantically meaningful Sanskrit phrases and produce translation-grounded meanings from a sloka-translation pair, formalizing the traditional patha commentary practice as an evaluable NLP objective. We construct a benchmark of 31,3...
Manoj Balaji Jagadeeshan, Sai Pragnaan Marala, Pawan Goyal· 0 citations
This work introduces soft tags, which are under-specified representations retaining all possible morphological attributes of a word, and adopts a neural network approach in order to learn distributed representations for the soft tags and their interactions.
This work introduces soft tags, which are under-specified representations retaining all possible morphological attributes of a word, and adopts a neural network approach in order to learn distributed representations for the soft tags and their interactions.
TF-IDF provides a strong no-training lexical retrieval baseline, alongside representation analyses and generation controls for the learned models, and one narrow result remains: the decoder-only model prefers authentic word order in 107 of 112 minimal-pair comparisons, but does not reproduce held-out commentary content...
Tangut is an extinct language whose script does not explicitly mark word boundaries. We present the first systematic study of Tangut word segmentation using 2,750 expert-annotated segments (31,893 tokens), traditional lexicons, and unlabeled text. Our framework combines a reliability-calibrated lexicon-lattice represen...
Lifan Deng, Yongwei Zhang, Sen Sun et al.· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 19, 2026
An MIT and Dana-Farber Institute-led team used large language models to examine nearly 4,000 studies and hundreds of code repositories, revealing gaps in the information needed to scrutinize and reuse published research.
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.