English
Related papers

Related papers: From Characters to Words to in Between: Do We Capt…

200 papers

What are the units of text that we want to model? From bytes to multi-word expressions, text can be analyzed and generated at many granularities. Until recently, most natural language processing (NLP) models operated over words, treating…

When parsing morphologically-rich languages with neural models, it is beneficial to model input at the character level, and it has been claimed that this is because character-level models learn morphology. We test these claims by comparing…

Computation and Language · Computer Science 2018-08-29 Clara Vania , Andreas Grivas , Adam Lopez

Deep transformer models have pushed performance on NLP tasks to new limits, suggesting sophisticated treatment of complex linguistic inputs, such as phrases. However, we have limited understanding of how these models handle representation…

Computation and Language · Computer Science 2020-10-15 Lang Yu , Allyson Ettinger

Character-level models have been used extensively in recent years in NLP tasks as both supplements and replacements for closed-vocabulary token-level word representations. In one popular architecture, character-level LSTMs are used to feed…

Computation and Language · Computer Science 2019-03-13 Yuval Pinter , Marc Marone , Jacob Eisenstein

Previous work combines word-level and character-level representations using concatenation or scalar weighting, which is suboptimal for high-level tasks like reading comprehension. We present a fine-grained gating mechanism to dynamically…

Computation and Language · Computer Science 2017-09-13 Zhilin Yang , Bhuwan Dhingra , Ye Yuan , Junjie Hu , William W. Cohen , Ruslan Salakhutdinov

Translation into morphologically-rich languages challenges neural machine translation (NMT) models with extremely sparse vocabularies where atomic treatment of surface forms is unrealistic. This problem is typically addressed by either…

Computation and Language · Computer Science 2020-02-28 Duygu Ataman , Wilker Aziz , Alexandra Birch

Much like sentences are composed of words, words themselves are composed of smaller units. For example, the English word questionably can be analyzed as question+able+ly. However, this structural decomposition of the word does not directly…

Computation and Language · Computer Science 2018-11-13 Ryan Cotterell , Hinrich Schütze

This paper investigates neural character-based morphological tagging for languages with complex morphology and large tag sets. We systematically explore a variety of neural architectures (DNN, CNN, CNNHighway, LSTM, BLSTM) to obtain…

Computation and Language · Computer Science 2016-06-22 Georg Heigold , Guenter Neumann , Josef van Genabith

Distributed word representations are very useful for capturing semantic information and have been successfully applied in a variety of NLP tasks, especially on English. In this work, we innovatively develop two component-enhanced Chinese…

Computation and Language · Computer Science 2015-08-28 Yanran Li , Wenjie Li , Fei Sun , Sujian Li

Large language models (LLMs) can spell out tokens character by character with high accuracy, yet they struggle with more complex character-level tasks, such as identifying compositional subcomponents within tokens. In this work, we…

Computation and Language · Computer Science 2025-06-13 Tatsuya Hiraoka , Kentaro Inui

When we speak, write or listen, we continuously make predictions based on our knowledge of a language's grammar. Remarkably, children acquire this grammatical knowledge within just a few years, enabling them to understand and generalise to…

Computation and Language · Computer Science 2024-11-26 Jaap Jumelet

Even for common NLP tasks, sufficient supervision is not available in many languages -- morphological tagging is no exception. In the work presented here, we explore a transfer learning scheme, whereby we train character-level recurrent…

Computation and Language · Computer Science 2025-04-25 Ryan Cotterell , Georg Heigold

The representation space of pretrained Language Models (LMs) encodes rich information about words and their relationships (e.g., similarity, hypernymy, polysemy) as well as abstract semantic notions (e.g., intensity). In this paper, we…

Computation and Language · Computer Science 2023-06-02 Qing Lyu , Marianna Apidianaki , Chris Callison-Burch

Systems now exist which are able to compile unification grammars into language models that can be included in a speech recognizer, but it is so far unclear whether non-trivial linguistically principled grammars can be used for this purpose.…

Computation and Language · Computer Science 2007-05-23 Manny Rayner , Beth Ann Hockey , Frankie James , Elizabeth O. Bratt , Sharon Goldwater , Mark Gawron

Most of the Chinese pre-trained models adopt characters as basic units for downstream tasks. However, these models ignore the information carried by words and thus lead to the loss of some important semantics. In this paper, we propose a…

Computation and Language · Computer Science 2022-07-14 Wenbiao Li , Rui Sun , Yunfang Wu

Learning word representations has recently seen much success in computational linguistics. However, assuming sequences of word tokens as input to linguistic analysis is often unjustified. For many languages word segmentation is a…

Computation and Language · Computer Science 2013-09-19 Grzegorz Chrupała

Representation learning is the foundation of machine reading comprehension and inference. In state-of-the-art models, character-level representations have been broadly adopted to alleviate the problem of effectively representing rare or…

Computation and Language · Computer Science 2019-06-12 Zhuosheng Zhang , Hai Zhao , Kangwei Ling , Jiangtong Li , Zuchao Li , Shexia He , Guohong Fu

A new language model for speech recognition inspired by linguistic analysis is presented. The model develops hidden hierarchical structure incrementally and uses it to extract meaningful information from the word history - thus enabling the…

Computation and Language · Computer Science 2007-05-23 Ciprian Chelba , Frederick Jelinek

Much theoretical work has described the ability of transformers to represent formal languages. However, linking theoretical results to empirical performance is not straightforward due to the complex interplay between the architecture, the…

Computation and Language · Computer Science 2024-10-07 Anej Svete , Nadav Borenstein , Mike Zhou , Isabelle Augenstein , Ryan Cotterell

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