Related papers: Generation, Implementation and Appraisal of an N-g…

This paper investigates data-driven segmentation using Re-Pair or Byte Pair Encoding-techniques. In contrast to previous work which has primarily been focused on subword units for machine translation, we are interested in the general…

Machine-translated text plays an important role in modern life by smoothing communication from various communities using different languages. However, unnatural translation may lead to misunderstanding, a detector is thus needed to avoid…

Most end-to-end speech recognition systems model text directly as a sequence of characters or sub-words. Current approaches to sub-word extraction only consider character sequence frequencies, which at times produce inferior sub-word…

We introduce a training method for both better word representation and performance, which we call GROVER (Gradual Rumination On the Vector with maskERs). The method is to gradually and iteratively add random noises to word embeddings while…

We present NN-grams, a novel, hybrid language model integrating n-grams and neural networks (NN) for speech recognition. The model takes as input both word histories as well as n-gram counts. Thus, it combines the memorization capacity and…

We propose a method for natural language generation, choosing the most representative output rather than the most likely output. By viewing the language generation process from the voting theory perspective, we define representativeness…

We propose simple and flexible training and decoding methods for influencing output style and topic in neural encoder-decoder based language generation. This capability is desirable in a variety of applications, including conversational…

Recent advancements in neural language modelling make it possible to rapidly generate vast amounts of human-sounding text. The capabilities of humans and automatic discriminators to detect machine-generated text have been a large source of…

Despite their growing capabilities, language models still frequently reproduce content from their training data, generate repetitive text, and favor common grammatical patterns and vocabulary. A possible cause is the decoding strategy: the…

The Unigram tokenization algorithm offers a probabilistic alternative to the greedy heuristics of Byte-Pair Encoding. Despite its theoretical elegance, its implementation in practice is complex, limiting its adoption to the SentencePiece…

This paper presents an overview of current research concerning knowledge extraction from technical texts. In particular, the use of empirical techniques during the identification and generation of a semantic representation is considered. A…

Potential harms of Large Language Models such as mass misinformation and plagiarism can be partially mitigated if there exists a reliable way to detect machine generated text. In this paper, we propose a new watermarking method to detect…

Transformer models have recently emerged as one of the foundational models in natural language processing, and as a byproduct, there is significant recent interest and investment in scaling these models. However, the training and inference…

Whilst there are perhaps only a few scientific methods, there seem to be almost as many artistic methods as there are artists. Artistic processes appear to inhabit the highest order of open-endedness. To begin to understand some of the…

Developing an automatic part-of-speech (POS) tagging for any new language is considered a necessary step for further computational linguistics methodology beyond tagging, like chunking and parsing, to be fully applied to the language. Many…

The popularity of automatic speech recognition (ASR) systems nowadays leads to an increasing need for improving their accessibility. Handling stuttering speech is an important feature for accessible ASR systems. To improve the accessibility…

Since long, research on machine translation has been ongoing. Still, we do not get good translations from MT engines so developed. Manual ranking of these outputs tends to be very time consuming and expensive. Identifying which one is…

The power of natural language generation models has provoked a flurry of interest in automatic methods to detect if a piece of text is human or machine-authored. The problem so far has been framed in a standard supervised way and consists…

In this paper, a novel hierarchical Persian stemming approach based on the Part-Of-Speech of the word in a sentence is presented. The implemented stemmer includes hash tables and several deterministic finite automata in its different levels…

Despite recent advances in automatic text recognition, the performance remains moderate when it comes to historical manuscripts. This is mainly because of the scarcity of available labelled data to train the data-hungry Handwritten Text…