Related papers: Unsupervised Morphological Paradigm Completion

Probing the multilingual knowledge of linguistic structure in LLMs, often characterized as sequence labeling, faces challenges with maintaining output templates in current text-to-text prompting strategies. To solve this, we introduce a…

We present a semi-supervised way of training a character-based encoder-decoder recurrent neural network for morphological reinflection, the task of generating one inflected word form from another. This is achieved by using unlabeled tokens…

Computational morphology handles the language processing at the word level. It is one of the foundational tasks in the NLP pipeline for the development of higher level NLP applications. It mainly deals with the processing of words and word…

This paper presents a constraint-based morphological disambiguation approach that is applicable languages with complex morphology--specifically agglutinative languages with productive inflectional and derivational morphological phenomena.…

Although Large Language Models (LLMs) excel at addressing straightforward reasoning tasks, they frequently struggle with difficulties when confronted by more complex multi-step reasoning due to a range of factors. Firstly, natural language…

We present a system for bottom-up cumulative learning of myriad concepts corresponding to meaningful character strings, and their part-related and prediction edges. The learning is self-supervised in that the concepts discovered are used as…

We quantify the linguistic complexity of different languages' morphological systems. We verify that there is an empirical trade-off between paradigm size and irregularity: a language's inflectional paradigms may be either large in size or…

The first morphological learner based upon the theory of Whole Word Morphology Ford et al. (1997) is outlined, and preliminary evaluation results are presented. The program, Whole Word Morphologizer, takes a POS-tagged lexicon as input,…

In this paper we present a lexicon-based approach to the problem of morphological processing. Full-form words, lemmas and grammatical tags are interconnected in a DAWG. Thus, the process of analysis/synthesis is reduced to a search in the…

In this paper, we address unsupervised pose-guided person image generation, which is known challenging due to non-rigid deformation. Unlike previous methods learning a rock-hard direct mapping between human bodies, we propose a new pathway…

We propose an unsupervised method to obtain cross-lingual embeddings without any parallel data or pre-trained word embeddings. The proposed model, which we call multilingual neural language models, takes sentences of multiple languages as…

We propose a new unsupervised method for lexical substitution using pre-trained language models. Compared to previous approaches that use the generative capability of language models to predict substitutes, our method retrieves substitutes…

We present a novel incremental learning approach for unsupervised word segmentation that combines features from probabilistic modeling and model selection. This includes super-additive penalties for addressing the cognitive burden imposed…

We present a compact, single-model approach to multilingual inflection, the task of generating inflected word forms from base lemmas to express grammatical categories. Our model, trained jointly on data from 73 languages, is lightweight,…

Despite recent success in machine reading comprehension (MRC), learning high-quality MRC models still requires large-scale labeled training data, even using strong pre-trained language models (PLMs). The pre-training tasks for PLMs are not…

Conditional text generation often requires lexical constraints, i.e., which words should or shouldn't be included in the output text. While the dominant recipe for conditional text generation has been large-scale pretrained language models…

Neural state-of-the-art sequence-to-sequence (seq2seq) models often do not perform well for small training sets. We address paradigm completion, the morphological task of, given a partial paradigm, generating all missing forms. We propose…

Prompting inputs with natural language task descriptions has emerged as a popular mechanism to elicit reasonably accurate outputs from large-scale generative language models with little to no in-context supervision. This also helps gain…

Despite an ever growing number of word representation models introduced for a large number of languages, there is a lack of a standardized technique to provide insights into what is captured by these models. Such insights would help the…

Representation learning is the foundation of natural language processing (NLP). This work presents new methods to employ visual information as assistant signals to general NLP tasks. For each sentence, we first retrieve a flexible number of…