paper-with-me

홈 › Papers

Don't Forget the Long Tail! A Comprehensive Analysis of Morphological Generalization in Bilingual Lexicon Induction

2019-09-06 · IJCNLP 2019 11 · Paula Czarnowska, Sebastian Ruder, Edouard Grave, Ryan Cotterell, Ann Copestake

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.

📄 PDF Abstract BibTeX arXiv:1909.02855

Code (0)

등록된 구현이 없습니다.

Tasks

Bilingual Lexicon InductionTranslation

Similar Papers 제목 키워드 기반

Adaptive Adapter Routing for Long-Tailed Class-Incremental Learning

2024-09-11 · Zhi-Hong Qi, Da-Wei Zhou, Yiran Yao, Han-Jia Ye 외

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 Learning

Continual Learning in Large Language Models: Methods, Challenges, and Opportunities

2026-03-13 · Hongyang Chen, Zhongwu Sun, Hongfei Ye, Kunchi Li 외 arxiv

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 Learning

Using Meta-Morph Rules to develop Morphological Analysers: A case study concerning Tamil

2019-09-01 · WS 2019 9 · Kengatharaiyer Sarveswaran, Gihan Dias, Miriam Butt

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 Analysis

GEO-Nav: a geometric dataset of voltage-gated sodium channels

2023-06-21 · Andrea Raffo, Ulderico Fugacci, Silvia Biasotti

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 Analysis

Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models

2024-02-19 · Didi Zhu, Zhongyi Sun, Zexi Li, Tao Shen 외

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