English
Related papers

Related papers: Representation Degeneration Problem in Training Na…

200 papers

We introduce the problem of learning distributed representations of edits. By combining a "neural editor" with an "edit encoder", our models learn to represent the salient information of an edit and can be used to apply edits to new inputs.…

Machine Learning · Computer Science 2019-02-25 Pengcheng Yin , Graham Neubig , Miltiadis Allamanis , Marc Brockschmidt , Alexander L. Gaunt

In this paper, we consider several compression techniques for the language modeling problem based on recurrent neural networks (RNNs). It is known that conventional RNNs, e.g, LSTM-based networks in language modeling, are characterized with…

Machine Learning · Statistics 2019-04-09 Artem M. Grachev , Dmitry I. Ignatov , Andrey V. Savchenko

To what extent can neural network models learn generalizations about language structure, and how do we find out what they have learned? We explore these questions by training neural models for a range of natural language processing tasks on…

Computation and Language · Computer Science 2023-01-20 Robert Östling , Murathan Kurfalı

This paper proposes a novel Recurrent Neural Network (RNN) language model that takes advantage of character information. We focus on character n-grams based on research in the field of word embedding construction (Wieting et al. 2016). Our…

Computation and Language · Computer Science 2019-06-14 Sho Takase , Jun Suzuki , Masaaki Nagata

Large Language Models (LLMs) have made substantial strides in structured tasks through Reinforcement Learning (RL), demonstrating proficiency in mathematical reasoning and code generation. However, applying RL in broader domains like…

Computation and Language · Computer Science 2025-02-10 Hao Sun , Yunyi Shen , Jean-Francois Ton , Mihaela van der Schaar

Diffusion-based large language models offer a non-autoregressive alternative for text generation, but enabling them to perform complex reasoning remains challenging. Reinforcement learning has recently emerged as an effective post-training…

Artificial Intelligence · Computer Science 2026-04-14 Shaoan Xie , Lingjing Kong , Xiangchen Song , Xinshuai Dong , Guangyi Chen , Eric P. Xing , Kun Zhang

A review of Word Embedding Models through a deconstructive approach reveals their several shortcomings and inconsistencies. These include instability of the vector representations, a distorted analogical reasoning, geometric incompatibility…

Computation and Language · Computer Science 2019-02-05 Koushik Varma Kalidindi

We present a family of neural-network--inspired models for computing continuous word representations, specifically designed to exploit both monolingual and multilingual text. This framework allows us to perform unsupervised training of…

Computation and Language · Computer Science 2016-12-15 Radu Soricut , Nan Ding

Recurrent neural language models are the state-of-the-art models for language modeling. When the vocabulary size is large, the space taken to store the model parameters becomes the bottleneck for the use of recurrent neural language models.…

Computation and Language · Computer Science 2017-12-25 Zhongliang Li , Raymond Kulhanek , Shaojun Wang , Yunxin Zhao , Shuang Wu

Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised…

Computation and Language · Computer Science 2023-02-17 Danilo S. Carvalho , Giangiacomo Mercatali , Yingji Zhang , Andre Freitas

Network representation learning (NRL) methods aim to map each vertex into a low dimensional space by preserving the local and global structure of a given network, and in recent years they have received a significant attention thanks to…

Machine Learning · Computer Science 2018-10-17 Abdulkadir Çelikkanat , Fragkiskos D. Malliaros

Recent works on word representations mostly rely on predictive models. Distributed word representations (aka word embeddings) are trained to optimally predict the contexts in which the corresponding words tend to appear. Such models have…

Computation and Language · Computer Science 2015-04-10 Rémi Lebret , Ronan Collobert

Metalearning of deep neural network (DNN) architectures and hyperparameters has become an increasingly important area of research. At the same time, network regularization has been recognized as a crucial dimension to effective training of…

Neural and Evolutionary Computing · Computer Science 2021-07-22 Jason Liang , Santiago Gonzalez , Hormoz Shahrzad , Risto Miikkulainen

Word embeddings predict a word from its neighbours by learning small, dense embedding vectors. In practice, this prediction corresponds to a semantic score given to the predicted word (or term weight). We present a novel model that, given a…

Information Retrieval · Computer Science 2019-06-04 Casper Hansen , Christian Hansen , Stephen Alstrup , Jakob Grue Simonsen , Christina Lioma

Recent works using artificial neural networks based on word distributed representation greatly boost the performance of various natural language learning tasks, especially question answering. Though, they also carry along with some…

Computation and Language · Computer Science 2016-12-23 Lingxun Meng , Yan Li , Mengyi Liu , Peng Shu

Models trained on a new task typically degrade on prior tasks, a phenomenon known as forgetting. Traditionally, mitigating forgetting has required replaying stored exemplars from prior tasks, which is often impractical. By contrast,…

Machine Learning · Computer Science 2026-05-26 Martin Marek , Dongkyu Cho , Shikai Qiu , Rumi Chunara , Pavel Izmailov , Andrew Gordon Wilson

Pre-trained word embeddings improve the performance of a neural model at the cost of increasing the model size. We propose to benefit from this resource without paying the cost by operating strictly at the sub-lexical level. Our approach is…

Computation and Language · Computer Science 2017-07-24 Karl Stratos

Weight space learning is an emerging paradigm in the deep learning community. The primary goal of weight space learning is to extract informative features from a set of parameters using specially designed neural networks, often referred to…

Machine Learning · Computer Science 2025-03-13 Taesun Yeom , Jaeho Lee

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

After just a few hundred training updates, a standard probabilistic model for language generation has likely not yet learnt many semantic or syntactic rules of natural language, making it difficult to estimate the probability distribution…

Computation and Language · Computer Science 2023-06-26 Clara Meister , Wojciech Stokowiec , Tiago Pimentel , Lei Yu , Laura Rimell , Adhiguna Kuncoro