Related papers: Using Multiple Sources of Information for Constrai…
Tokenization shapes how language models perceive morphology and meaning in NLP, yet widely used frequency-driven subword tokenizers (e.g., Byte Pair Encoding and WordPiece) can fragment morphologically rich and agglutinative languages in…
This paper presents an approach to spelling correction in agglutinative languages that is based on two-level morphology and a dynamic programming based search algorithm. Spelling correction in agglutinative languages is significantly…
Neural machine translation (NMT) has achieved impressive performance on machine translation task in recent years. However, in consideration of efficiency, a limited-size vocabulary that only contains the top-N highest frequency words are…
Morphologically rich languages accentuate two properties of distributional vector space models: 1) the difficulty of inducing accurate representations for low-frequency word forms; and 2) insensitivity to distinct lexical relations that…
In this paper, we build morphological chains for agglutinative languages by using a log-linear model for the morphological segmentation task. The model is based on the unsupervised morphological segmentation system called MorphoChains. We…
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…
Inflection is an essential part of every human language's morphology, yet little effort has been made to unify linguistic theory and computational methods in recent years. Methods of string manipulation are used to infer inflectional…
Transformers have achieved state-of-the-art performance in morphological inflection tasks, yet their ability to generalize across languages and morphological rules remains limited. One possible explanation for this behavior can be the…
All natural language processing systems (such as parsers, generators, taggers) need to have access to a lexicon about the words in the language. This thesis presents a lexicon architecture for natural language processing in Turkish. Given a…
Lexical ambiguity makes it difficult to compute various useful statistics of a corpus. A given word form might represent any of several morphological feature bundles. One can, however, use unsupervised learning (as in EM) to fit a model…
Tokenization is a pivotal design choice for neural language modeling in morphologically rich languages (MRLs) such as Turkish, where productive agglutination challenges both vocabulary efficiency and morphological fidelity. Prior studies…
Lexical ambiguity, a challenging phenomenon in all natural languages, is particularly prevalent for languages with diacritics that tend to be omitted in writing, such as Arabic. Omitting diacritics leads to an increase in the number of…
In this thesis, I address the problem of automatically acquiring lexical semantic knowledge, especially that of case frame patterns, from large corpus data and using the acquired knowledge in structural disambiguation. The approach I adopt…
Large Language Models (LLMs) have shown significant progress on various multilingual benchmarks and are increasingly used to generate and evaluate text in non-English languages. However, while they may produce fluent outputs, it remains…
This paper describes a computational, declarative approach to prosodic morphology that uses inviolable constraints to denote small finite candidate sets which are filtered by a restrictive incremental optimization mechanism. The new…
The lack or absence of parallel and comparable corpora makes bilingual lexicon extraction a difficult task for low-resource languages. The pivot language and cognate recognition approaches have been proven useful for inducing bilingual…
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…
We address the problem of clustering words (or constructing a thesaurus) based on co-occurrence data, and using the acquired word classes to improve the accuracy of syntactic disambiguation. We view this problem as that of estimating a…
Memorization in large language models has been studied almost exclusively through prefix-conditioned extraction, a natural choice for autoregressive models. However, diffusion language models (DLMs) can denoise masked tokens at arbitrary…
Error-tolerant recognition enables the recognition of strings that deviate mildly from any string in the regular set recognized by the underlying finite state recognizer. Such recognition has applications in error-tolerant morphological…