English
Related papers

Related papers: Hierarchical Autoregressive Transformers: Combinin…

200 papers

Language tasks involving character-level manipulations (e.g., spelling corrections, arithmetic operations, word games) are challenging for models operating on subword units. To address this, we develop a causal intervention framework to…

Computation and Language · Computer Science 2023-12-20 Jing Huang , Zhengxuan Wu , Kyle Mahowald , Christopher Potts

Tokenization is fundamental to pretrained language models (PLMs). Existing tokenization methods for Chinese PLMs typically treat each character as an indivisible token. However, they ignore the unique feature of the Chinese writing system…

Computation and Language · Computer Science 2023-02-16 Chenglei Si , Zhengyan Zhang , Yingfa Chen , Fanchao Qi , Xiaozhi Wang , Zhiyuan Liu , Yasheng Wang , Qun Liu , Maosong Sun

In Natural Language Processing (NLP), predicting linguistic structures, such as parsing and chunking, has mostly relied on manual annotations of syntactic structures. This paper introduces an unsupervised approach to chunking, a syntactic…

Computation and Language · Computer Science 2025-12-19 Zijun Wu , Anup Anand Deshmukh , Yongkang Wu , Jimmy Lin , Lili Mou

Tokenization is a hardcoded compression step which remains in the training pipeline of Large Language Models (LLMs), despite a general trend towards architectures becoming increasingly end-to-end. Prior work has shown promising results at…

Machine Learning · Computer Science 2026-02-17 Sam Dauncey , Roger Wattenhofer

Transcribing structured data into natural language descriptions has emerged as a challenging task, referred to as "data-to-text". These structures generally regroup multiple elements, as well as their attributes. Most attempts rely on…

Computation and Language · Computer Science 2019-12-23 Clément Rebuffel , Laure Soulier , Geoffrey Scoutheeten , Patrick Gallinari

Tokenization is a foundational step in the text process of Large Language Models (LLMs). Texts must be first tokenized into token IDs, which are then input to LLMs. Inefficient tokenization results in long token-ID sequences and will slow…

Computation and Language · Computer Science 2026-05-14 Chong Li , Yingzhuo Deng , Wen Yang , Jiajun Zhang , Chengqing Zong

The Transformer architecture has become increasingly popular over the past two years, owing to its impressive performance on a number of natural language processing (NLP) tasks. However, all Transformer computations occur at the level of…

Machine Learning · Computer Science 2021-04-05 David Donahue , Vladislav Lialin , Anna Rumshisky

Tokenization and sub-tokenization based models like word2vec, BERT and the GPTs are the state-of-the-art in natural language processing. Typically, these approaches have limitations with respect to their input representation. They fail to…

Computation and Language · Computer Science 2026-02-26 Felix Schneider , Maria Gogolev , Sven Sickert , Joachim Denzler

Document classification tasks were primarily tackled at word level. Recent research that works with character-level inputs shows several benefits over word-level approaches such as natural incorporation of morphemes and better handling of…

Computation and Language · Computer Science 2016-02-02 Yijun Xiao , Kyunghyun Cho

Transformers have demonstrated remarkable performance in natural language processing and related domains, as they largely focus on sequential, autoregressive next-token prediction tasks. Yet, they struggle in logical reasoning, not…

Artificial Intelligence · Computer Science 2025-10-08 Renee Ge , Qianli Liao , Tomaso Poggio

Natural Language Processing (NLP) systems commonly leverage bag-of-words co-occurrence techniques to capture semantic and syntactic word relationships. The resulting word-level distributed representations often ignore morphological…

Computation and Language · Computer Science 2015-06-12 Andrew Trask , David Gilmore , Matthew Russell

We present a new recurrent neural network topology to enhance state-of-the-art machine learning systems by incorporating a broader context. Our approach overcomes recent limitations with extended narratives through a multi-layered…

Computation and Language · Computer Science 2018-08-07 Patrick Huber , Jan Niehues , Alex Waibel

Transformer-based large language models (LLM) have been widely used in language processing applications. However, due to the memory constraints of the devices, most of them restrict the context window. Even though recurrent models in…

Computation and Language · Computer Science 2025-02-07 Zifan He , Yingqi Cao , Zongyue Qin , Neha Prakriya , Yizhou Sun , Jason Cong

The transformer has been shown to outperform recurrent neural network-based sequence-to-sequence models in various word-level NLP tasks. Yet for character-level transduction tasks, e.g. morphological inflection generation and historical…

Computation and Language · Computer Science 2021-01-29 Shijie Wu , Ryan Cotterell , Mans Hulden

Text classification algorithms investigate the intricate relationships between words or phrases and attempt to deduce the document's interpretation. In the last few years, these algorithms have progressed tremendously. Transformer…

Computation and Language · Computer Science 2022-06-28 Snehal Khandve , Vedangi Wagh , Apurva Wani , Isha Joshi , Raviraj Joshi

Many NLP applications, such as biomedical data and technical support, have 10-100 million tokens of in-domain data and limited computational resources for learning from it. How should we train a language model in this scenario? Most…

Computation and Language · Computer Science 2020-10-01 Charles Welch , Rada Mihalcea , Jonathan K. Kummerfeld

Despite their remarkable progress across diverse domains, Large Language Models (LLMs) consistently fail at simple character-level tasks, such as counting letters in words, due to a fundamental limitation: tokenization. In this work, we…

Computation and Language · Computer Science 2025-09-17 Adrian Cosma , Stefan Ruseti , Emilian Radoi , Mihai Dascalu

In this study, we provide constructive proof that Transformers can recognize and generate hierarchical language efficiently with respect to model size, even without the need for a specific positional encoding. Specifically, we show that…

Computation and Language · Computer Science 2024-10-17 Daichi Hayakawa , Issei Sato

Sequence-to-sequence transduction is the core problem in language processing applications as diverse as semantic parsing, machine translation, and instruction following. The neural network models that provide the dominant solution to these…

Computation and Language · Computer Science 2021-06-09 Ekin Akyürek , Jacob Andreas

Autoregressive (AR) models, long dominant in language generation, are increasingly applied to image synthesis but are often considered less competitive than Diffusion-based models. A primary limitation is the substantial number of image…