相关论文: Team Ryu's Submission to SIGMORPHON 2024 Shared Ta…

While model architecture and training objectives are well-studied, tokenization, particularly in multilingual contexts, remains a relatively neglected aspect of Large Language Model (LLM) development. Existing tokenizers often exhibit high…

The best performing transformer-based language models use subword tokenization techniques, such as Byte-Pair-Encoding (BPE). However, these approaches often overlook linguistic principles, such as morphological segmentation, which we…

We investigate segmenting and clustering speech into low-bitrate phone-like sequences without supervision. We specifically constrain pretrained self-supervised vector-quantized (VQ) neural networks so that blocks of contiguous feature…

Given the lack of word delimiters in written Japanese, word segmentation is generally considered a crucial first step in processing Japanese texts. Typical Japanese segmentation algorithms rely either on a lexicon and syntactic analysis or…

Modern language models mostly take sub-words as input, a design that balances the trade-off between vocabulary size, number of parameters, and performance. However, sub-word tokenization still has disadvantages like not being robust to…

We present in this paper a novel framework for morpheme segmentation which uses the morpho-syntactic regularities preserved by word representations, in addition to orthographic features, to segment words into morphemes. This framework is…

This paper evaluates the performance of several modern subword segmentation methods in a low-resource neural machine translation setting. We compare segmentations produced by applying BPE at the token or sentence level with…

Recent advances in methods focused on the grounding problem have resulted in techniques that can be used to construct a symbolic language associated with a specific domain. Inspired by how humans communicate complex ideas through language,…

Language models typically tokenize text into subwords, using a deterministic, hand-engineered heuristic of combining characters into longer surface-level strings such as 'ing' or whole words. Recent literature has repeatedly shown the…

Morphological segmentation for polysynthetic languages is challenging, because a word may consist of many individual morphemes and training data can be extremely scarce. Since neural sequence-to-sequence (seq2seq) models define the state of…

We explore threshold vocabulary trimming in Byte-Pair Encoding subword tokenization, a postprocessing step that replaces rare subwords with their component subwords. The technique is available in popular tokenization libraries but has not…

While tokenization is a key step in language modeling, with effects on model training and performance, it remains unclear how to effectively evaluate tokenizer quality. One proposed dimension of tokenizer quality is the extent to which…

Sensor fusion is a fundamental process in robotic systems as it extends the perceptual range and increases robustness in real-world operations. Current multi-sensor deep learning based semantic segmentation approaches do not provide…

This paper presents the submission by the CMU-01 team to the SIGMORPHON 2019 task 2 of Morphological Analysis and Lemmatization in Context. This task requires us to produce the lemma and morpho-syntactic description of each token in a…

We describe and analyze a simple and effective algorithm for sequence segmentation applied to speech processing tasks. We propose a neural architecture that is composed of two modules trained jointly: a recurrent neural network (RNN) module…

Canonical morphological segmentation is the process of analyzing words into the standard (aka underlying) forms of their constituent morphemes. This is a core task in language documentation, and NLP systems have the potential to…

This paper presents a new unified approach to semantic segmentation in both images and videos by using language modeling to output the masks as sequences of discrete tokens. We use run length encoding (RLE) to discretize the segmentation…

Data-driven segmentation of words into subword units has been used in various natural language processing applications such as automatic speech recognition and statistical machine translation for almost 20 years. Recently it has became more…

Language models typically tokenize raw text into sequences of subword identifiers from a predefined vocabulary, a process inherently sensitive to typographical errors, length variations, and largely oblivious to the internal structure of…

Subword segmentation is typically applied in preprocessing and stays fixed during training. Alternatively, it can be learned during training to optimise the training objective. In this paper we study the learning dynamics of subword…