Don't Forget the Long Tail! A Comprehensive Analysis of Morphological Generalization in Bilingual Lexicon Induction
Human translators routinely have to translate rare inflections of words - due to the Zipfian distribution of words in a language. When translating from Spanish, a good translator would have no problem identifying the proper translation of a statistically rare inflection such as habl\'aramos. Note the lexeme itself, hablar, is relatively common. In this work, we investigate whether state-of-the-art bilingual lexicon inducers are capable of learning this kind of generalization. We introduce 40 morphologically complete dictionaries in 10 languages and evaluate three of the state-of-the-art models on the task of translation of less frequent morphological forms. We demonstrate that the performance of state-of-the-art models drops considerably when evaluated on infrequent morphological inflections and then show that adding a simple morphological constraint at training time improves the performance, proving that the bilingual lexicon inducers can benefit from better encoding of morphology.
Code (0)
등록된 구현이 없습니다.
Tasks
Bilingual Lexicon InductionTranslationSimilar Papers 제목 키워드 기반
Adaptive Adapter Routing for Long-Tailed Class-Incremental Learning
In our ever-evolving world, new data exhibits a long-tailed distribution, such as e-commerce platform reviews. This necessitates continuous model learning imbalanced data without forgetting, addressing the challenge of l…
class-incremental learningClass Incremental LearningExemplar-FreeIncremental LearningContinual Learning in Large Language Models: Methods, Challenges, and Opportunities
Continual learning (CL) has emerged as a pivotal paradigm to enable large language models (LLMs) to dynamically adapt to evolving knowledge and sequential tasks while mitigating catastrophic forgetting-a critical limitat…
Continual LearningUsing Meta-Morph Rules to develop Morphological Analysers: A case study concerning Tamil
This paper describes a new and larger coverage Finite-State Morphological Analyser (FSM) and Generator for the Dravidian language Tamil. The FSM has been developed in the context of computational grammar engineering, adh…
MORPHMorphological AnalysisGEO-Nav: a geometric dataset of voltage-gated sodium channels
Voltage-gated sodium (Nav) channels constitute a prime target for drug design and discovery, given their implication in various diseases such as epilepsy, migraine and ataxia to name a few. In this regard, performing mor…
Drug DesignMorphological AnalysisModel Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models
Catastrophic forgetting emerges as a critical challenge when fine-tuning multi-modal large language models (MLLMs), where improving performance on unseen tasks often leads to a significant performance drop on the origina…
Image CaptioningQuestion AnsweringVisual Question Answering