Related papers: Breaking Character: Are Subwords Good Enough for M…

Most pre-trained language models (PLMs) construct word representations at subword level with Byte-Pair Encoding (BPE) or its variations, by which OOV (out-of-vocab) words are almost avoidable. However, those methods split a word into…

Subword tokenization is an essential part of modern large language models (LLMs), yet its specific contributions to training efficiency and model performance remain poorly understood. In this work, we decouple the effects of subword…

Recent years have witnessed the burgeoning of pretrained language models (LMs) for text-based natural language (NL) understanding tasks. Such models are typically trained on free-form NL text, hence may not be suitable for tasks like…

Pretrained language models (PLMs) have shown marvelous improvements across various NLP tasks. Most Chinese PLMs simply treat an input text as a sequence of characters, and completely ignore word information. Although Whole Word Masking can…

How does the input segmentation of pretrained language models (PLMs) affect their interpretations of complex words? We present the first study investigating this question, taking BERT as the example PLM and focusing on its semantic…

Pre-trained language models (PLMs) have shown remarkable successes in acquiring a wide range of linguistic knowledge, relying solely on self-supervised training on text streams. Nevertheless, the effectiveness of this language-agnostic…

Semitic morphologically-rich languages (MRLs) are characterized by extreme word ambiguity. Because most vowels are omitted in standard texts, many of the words are homographs with multiple possible analyses, each with a different…

Despite the development of pre-trained language models (PLMs) significantly raise the performances of various Chinese natural language processing (NLP) tasks, the vocabulary for these Chinese PLMs remain to be the one provided by Google…

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…

Pre-trained language models such as BERT have exhibited remarkable performances in many tasks in natural language understanding (NLU). The tokens in the models are usually fine-grained in the sense that for languages like English they are…

Pre-trained language models (PLMs) that use subword tokenization schemes can succeed at a variety of language tasks that require character-level information, despite lacking explicit access to the character composition of tokens. Here,…

In the era of high performing Large Language Models, researchers have widely acknowledged that contextual word representations are one of the key drivers in achieving top performances in downstream tasks. In this work, we investigate the…

While pretrained language models (PLMs) primarily serve as general-purpose text encoders that can be fine-tuned for a wide variety of downstream tasks, recent work has shown that they can also be rewired to produce high-quality word…

Pre-trained models are widely used in the tasks of natural language processing nowadays. However, in the specific field of text simplification, the research on improving pre-trained models is still blank. In this work, we propose a…

Pre-trained language models (PLMs) aim to learn universal language representations by conducting self-supervised training tasks on large-scale corpora. Since PLMs capture word semantics in different contexts, the quality of word…

Masked Language Modeling (MLM) is widely used to pretrain language models. The standard random masking strategy in MLM causes the pre-trained language models (PLMs) to be biased toward high-frequency tokens. Representation learning of rare…

Standard pretrained language models operate on sequences of subword tokens without direct access to the characters that compose each token's string representation. We probe the embedding layer of pretrained language models and show that…

We present VBART, the first Turkish sequence-to-sequence Large Language Models (LLMs) pre-trained on a large corpus from scratch. VBART are compact LLMs based on good ideas leveraged from BART and mBART models and come in two sizes, Large…

Most pretrained language models rely on subword tokenization, which processes text as a sequence of subword tokens. However, different granularities of text, such as characters, subwords, and words, can contain different kinds of…

Multilingual Pre-trained Language models (multiPLMs), trained on the Masked Language Modelling (MLM) objective are commonly being used for cross-lingual tasks such as bitext mining. However, the performance of these models is still…