English
Related papers

Related papers: Sent2Matrix: Folding Character Sequences in Serpen…

200 papers

This project intends to study the image representation based on attention mechanism and multimodal data. By adding multiple pattern layers to the attribute model, the semantic and hidden layers of image content are integrated. The word…

Computation and Language · Computer Science 2024-06-14 Dan Sun , Yaxin Liang , Yining Yang , Yuhan Ma , Qishi Zhan , Erdi Gao

Although deep language representations have become the dominant form of language featurization in recent years, in many settings it is important to understand a model's decision-making process. This necessitates not only an interpretable…

Computation and Language · Computer Science 2023-06-05 Victoria Lin , Louis-Philippe Morency

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

Word embedding maps words into a low-dimensional continuous embedding space by exploiting the local word collocation patterns in a small context window. On the other hand, topic modeling maps documents onto a low-dimensional topic space, by…

Computation and Language · Computer Science 2016-08-09 Shaohua Li , Tat-Seng Chua , Jun Zhu , Chunyan Miao

Unsupervised representation learning techniques, such as learning word embeddings, have had a significant impact on the field of natural language processing. Similar representation learning techniques have not yet become commonplace in the…

Computer Vision and Pattern Recognition · Computer Science 2021-02-09 Joël Bachmann , Kenneth Blomqvist , Julian Förster , Roland Siegwart

Unsupervised text embedding methods, such as Skip-gram and Paragraph Vector, have been attracting increasing attention due to their simplicity, scalability, and effectiveness. However, comparing to sophisticated deep learning architectures…

Computation and Language · Computer Science 2015-08-04 Jian Tang , Meng Qu , Qiaozhu Mei

Representing structured text from complex documents typically calls for different machine learning techniques, such as language models for paragraphs and convolutional neural networks (CNNs) for table extraction, which prohibits drawing…

Computation and Language · Computer Science 2022-02-21 Thomas Roland Barillot , Jacob Saks , Polena Lilyanova , Edward Torgas , Yachen Hu , Yuanqing Liu , Varun Balupuri , Paul Gaskell

There are two main approaches to the distributed representation of words: low-dimensional deep learning embeddings and high-dimensional distributional models, in which each dimension corresponds to a context word. In this paper, we combine…

Computation and Language · Computer Science 2014-02-19 Irina Sergienya , Hinrich Schütze

Continuous prompts have become widely adopted for augmenting performance across a wide range of natural language tasks. However, the underlying mechanism of this enhancement remains obscure. Previous studies rely on individual words for…

Computation and Language · Computer Science 2024-12-06 Qian Chen , Dongyang Li , Xiaofeng He

We propose a new type of representation learning method that models words, phrases and sentences seamlessly. Our method does not depend on word segmentation and any human-annotated resources (e.g., word dictionaries), yet it is very…

Computation and Language · Computer Science 2019-05-30 Geewook Kim , Kazuki Fukui , Hidetoshi Shimodaira

We present a novel and effective technique for performing text coherence tasks while facilitating deeper insights into the data. Despite obtaining ever-increasing task performance, modern deep-learning approaches to NLP tasks often only…

Computation and Language · Computer Science 2019-08-09 Tanner Bohn , Yining Hu , Jinhang Zhang , Charles X. Ling

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…

Computation and Language · Computer Science 2024-04-09 Yilin Wang , Xinyi Hu , Matthew R. Gormley

Models based on large-pretrained language models, such as S(entence)BERT, provide effective and efficient sentence embeddings that show high correlation to human similarity ratings, but lack interpretability. On the other hand, graph…

Computation and Language · Computer Science 2025-10-17 Juri Opitz , Anette Frank

Internal representations within deep neural architectures encode high-dimensional abstractions of linguistic structures, yet they often exhibit inefficiencies in feature distribution, limiting expressiveness and adaptability. Contextual…

Computation and Language · Computer Science 2025-03-27 Alistair Wren , Beatrice Loxley , Hamish Cadwallader , Simon Beckwith , Fabian Pargeter , James Blades

Learning sentence embeddings is a fundamental problem in natural language processing. While existing research primarily focuses on enhancing the quality of sentence embeddings, the exploration of sentence embedding dimensions is limited.…

Computation and Language · Computer Science 2023-10-25 Hongwei Wang , Hongming Zhang , Dong Yu

Neural Machine Translation (MT) has reached state-of-the-art results. However, one of the main challenges that neural MT still faces is dealing with very large vocabularies and morphologically rich languages. In this paper, we propose a…

Computation and Language · Computer Science 2016-07-01 Marta R. Costa-Jussà , José A. R. Fonollosa

We propose a direct-to-word sequence model which uses a word network to learn word embeddings from letters. The word network can be integrated seamlessly with arbitrary sequence models including Connectionist Temporal Classification and…

Computation and Language · Computer Science 2020-07-16 Ronan Collobert , Awni Hannun , Gabriel Synnaeve

The Super Characters method addresses sentiment analysis problems by first converting the input text into images and then applying 2D-CNN models to classify the sentiment. It achieves state of the art performance on many benchmark datasets.…

Computation and Language · Computer Science 2019-07-17 Baohua Sun , Lin Yang , Catherine Chi , Wenhan Zhang , Michael Lin

We consider two graph models of semantic change. The first is a time-series model that relates embedding vectors from one time period to embedding vectors of previous time periods. In the second, we construct one graph for each word: nodes…

Computation and Language · Computer Science 2017-04-11 Steffen Eger , Alexander Mehler

We provide the first exploration of sentence embeddings from text-to-text transformers (T5). Sentence embeddings are broadly useful for language processing tasks. While T5 achieves impressive performance on language tasks cast as…

Computation and Language · Computer Science 2021-12-15 Jianmo Ni , Gustavo Hernández Ábrego , Noah Constant , Ji Ma , Keith B. Hall , Daniel Cer , Yinfei Yang