Related papers: Stemmer for Serbian language
Prior work on controllable text generation has focused on learning how to control language models through trainable decoding, smart-prompt design, or fine-tuning based on a desired objective. We hypothesize that the information needed to…
Language models provide a key framework for studying linguistic theories based on prediction, but phonological analysis using large language models (LLMs) is difficult; there are few phonological benchmarks beyond English and the standard…
Scene text removal (STR) aims to erase textual elements from images. It was originally intended for removing privacy-sensitiveor undesired texts from natural scene images, but is now also appliedto typographic images. STR typically detects…
Language segmentation consists in finding the boundaries where one language ends and another language begins in a text written in more than one language. This is important for all natural language processing tasks. The problem can be solved…
We present experiments with part-of-speech tagging for Bulgarian, a Slavic language with rich inflectional and derivational morphology. Unlike most previous work, which has used a small number of grammatical categories, we work with 680…
We introduce and study natural derivatives for Christoffel and finite standard words, as well as for characteristic Sturmian words. These derivatives, which are realized as inverse images under suitable morphisms, preserve the…
Word embeddings aims to map sense of the words into a lower dimensional vector space in order to reason over them. Training embeddings on domain specific data helps express concepts more relevant to their use case but comes at a cost of…
In this paper we discuss the following issue: How do we decide whether a certain property of language is a competence property or a performance property? Our claim is that the answer to this question is not given a-priori. The answer…
The majority of contemporary computational methods for lexical semantic change (LSC) detection are based on neural embedding distributional representations. Although these models perform well on LSC benchmarks, their results are often…
The advent of contextual word embeddings -- representations of words which incorporate semantic and syntactic information from their context -- has led to tremendous improvements on a wide variety of NLP tasks. However, recent contextual…
Studies of different term extractors on a corpus of the biomedical domain revealed decreasing performances when applied to highly technical texts. The difficulty or impossibility of customising them to new domains is an additional…
Differentiating intrinsic language words from transliterable words is a key step aiding text processing tasks involving different natural languages. We consider the problem of unsupervised separation of transliterable words from native…
The first step in most empirical work in multilingual NLP is to construct maps of the correspondence between texts and their translations ({\bf bitext maps}). The Smooth Injective Map Recognizer (SIMR) algorithm presented here is a generic…
This paper describes a method for decomposing steady-state instrument data into excitation and formant filter components. The input data, taken from several series of recordings of acoustical instruments is analyzed in the frequency domain,…
Stuttering is a speech disorder during which the flow of speech is interrupted by involuntary pauses and repetition of sounds. Stuttering identification is an interesting interdisciplinary domain research problem which involves pathology,…
We describe an incremental unsupervised procedure to learn words from transcribed continuous speech. The algorithm is based on a conservative and traditional statistical model, and results of empirical tests show that it is competitive with…
Informal transliteration from other languages to English is prevalent in social media threads, instant messaging, and discussion forums. Without identifying the language of such transliterated text, users who do not speak that language…
Searching for information on the internet and digital platforms requires effective retrieval solutions. However, such solutions are not yet available for Tetun, making it difficult to find relevant documents for search queries in this…
The representation of sentences is a very important task. It can be used as a way to exchange data inter-applications. One main characteristic, that a notation must have, is a minimal size and a representative form. This can reduce the…
Word embedding is a powerful tool in natural language processing. In this paper we consider the problem of word embedding composition \--- given vector representations of two words, compute a vector for the entire phrase. We give a…