Related papers: Eeny, meeny, miny, moe. How to choose data for mor…
We propose to cast the task of morphological inflection - mapping a lemma to an indicated inflected form - for resource-poor languages as a meta-learning problem. Treating each language as a separate task, we use data from high-resource…
Morphological inflection is a popular task in sub-word NLP with both practical and cognitive applications. For years now, state-of-the-art systems have reported high, but also highly variable, performance across data sets and languages. We…
Neural models for the various flavours of morphological inflection tasks have proven to be extremely accurate given ample labeled data -- data that may be slow and costly to obtain. In this work we aim to overcome this annotation bottleneck…
Recent years have seen exceptional strides in the task of automatic morphological inflection generation. However, for a long tail of languages the necessary resources are hard to come by, and state-of-the-art neural methods that work well…
Compute-efficient training of language models has become an important issue. We consider data pruning for data-efficient training of LLMs. In this work, we consider a data pruning method based on information entropy. We propose that the…
Recent years have brought great advances into solving morphological tasks, mostly due to powerful neural models applied to various tasks as (re)inflection and analysis. Yet, such morphological tasks cannot be considered solved, especially…
Self-supervised objectives have driven major advances in NLP by leveraging large-scale unlabeled data, but such resources are scarce for many of the world's languages. Surprisingly, they have not been explored much for character-level…
Statistical morphological inflectors are typically trained on fully supervised, type-level data. One remaining open research question is the following: How can we effectively exploit raw, token-level data to improve their performance? To…
Data augmentation techniques are widely used in low-resource automatic morphological inflection to overcome data sparsity. However, the full implications of these techniques remain poorly understood. In this study, we aim to shed light on…
With a growing focus on morphological inflection systems for languages where high-quality data is scarce, training data noise is a serious but so far largely ignored concern. We aim at closing this gap by investigating the types of noise…
This paper describes our winning systems in MRL: The 1st Shared Task on Multilingual Clause-level Morphology (EMNLP 2022 Workshop) designed by KUIS AI NLP team. We present our work for all three parts of the shared task: inflection,…
Active learning (AL) uses a data selection algorithm to select useful training samples to minimize annotation cost. This is now an essential tool for building low-resource syntactic analyzers such as part-of-speech (POS) taggers. Existing…
This study addresses a series of methodological questions that arise when modeling inflectional morphology with Linear Discriminative Learning. Taking the semi-productive German noun system as example, we illustrate how decisions made about…
The traditional approach to morphological inflection (the task of modifying a base word (lemma) to express grammatical categories) has been, for decades, to consider lexical entries of lemma-tag-form triples uniformly, lacking any…
Modern language models (LMs) increasingly require two critical resources: computational resources and data resources. Data selection techniques can effectively reduce the amount of training data required for fine-tuning LMs. However, their…
When translating into morphologically rich languages, Statistical MT approaches face the problem of data sparsity. The severity of the sparseness problem will be high when the corpus size of morphologically richer language is less. Even…
A growing number of applications users daily interact with have to operate in (near) real-time: chatbots, digital companions, knowledge work support systems -- just to name a few. To perform the services desired by the user, these systems…
Masked language modeling has become a standard pretraining objective for training encoder-based language models. In this approach, certain tokens in the input are masked, and the model learns to predict them using the surrounding context.…
Human annotation cost and time remain significant bottlenecks in Natural Language Processing (NLP), with test data annotation being particularly expensive due to the stringent requirement for low-error and high-quality labels necessary for…
Morphological analysis is an important subtask in text-to-speech conversion, hyphenation, and other language engineering tasks. The traditional approach to performing morphological analysis is to combine a morpheme lexicon, sets of…