Related papers: Grammatical gender in Swedish is predictable using…

We empirically characterize the performance of discriminative and generative LSTM models for text classification. We find that although RNN-based generative models are more powerful than their bag-of-words ancestors (e.g., they account for…

In this paper, we describe an approach to sentence categorization which has the originality to be based on natural properties of languages with no training set dependency. The implementation is fast, small, robust and textual errors…

This study presents a novel model for invertible sentence embeddings using a residual recurrent network trained on an unsupervised encoding task. Rather than the probabilistic outputs common to neural machine translation models, our…

Recurrent neural networks (RNNs) have long been an architecture of interest for computational models of human sentence processing. The recently introduced Transformer architecture outperforms RNNs on many natural language processing tasks…

The standard recurrent neural network language model (RNNLM) generates sentences one word at a time and does not work from an explicit global sentence representation. In this work, we introduce and study an RNN-based variational autoencoder…

Natural language generation models reproduce and often amplify the biases present in their training data. Previous research explored using sequence-to-sequence rewriting models to transform biased model outputs (or original texts) into more…

Learning algorithms for natural language processing (NLP) tasks traditionally rely on manually defined relevant contextual features. On the other hand, neural network models using an only distributional representation of words have been…

In this paper, we propose TopicRNN, a recurrent neural network (RNN)-based language model designed to directly capture the global semantic meaning relating words in a document via latent topics. Because of their sequential nature, RNNs are…

The user review data have been demonstrated to be effective in solving different recommendation problems. Previous review-based recommendation methods usually employ sophisticated compositional models, such as Recurrent Neural Networks…

After a period of decrease, interest in word alignments is increasing again for their usefulness in domains such as typological research, cross-lingual annotation projection, and machine translation. Generally, alignment algorithms only use…

Content Warning: This paper contains examples of misgendering and erasure that could be offensive and potentially triggering. Gender bias in language technologies has been widely studied, but research has mostly been restricted to a binary…

We conduct a large-scale study of language models for chord prediction. Specifically, we compare N-gram models to various flavours of recurrent neural networks on a comprehensive dataset comprising all publicly available datasets of…

The compositionality of meaning extends beyond the single sentence. Just as words combine to form the meaning of sentences, so do sentences combine to form the meaning of paragraphs, dialogues and general discourse. We introduce both a…

We treat grammatical error correction (GEC) as a classification problem in this study, where for different types of errors, a target word is identified, and the classifier predicts the correct word form from a set of possible choices. We…

Generating plausible and fluent sentence with desired properties has long been a challenge. Most of the recent works use recurrent neural networks (RNNs) and their variants to predict following words given previous sequence and target…

Recurrent neural networks (RNNs) are very good at modelling the flow of text, but typically need to be trained on a far larger corpus than is available for the PAN 2015 Author Identification task. This paper describes a novel approach where…

In this paper, we explore the task of gender classification using limited network data with an application to Fotolog. We take a heuristic approach to automating gender inference based on username, followers and network structure. We test…

We implement a divide-and-concur iterative projection approach to context-free grammar inference. Unlike most state-of-the-art models of natural language processing, our method requires a relatively small number of discrete parameters,…

Neural Machine Translation (NMT) models are state-of-the-art for machine translation. However, these models are known to have various social biases, especially gender bias. Most of the work on evaluating gender bias in NMT has focused…

Recent studies have shown that word embeddings exhibit gender bias inherited from the training corpora. However, most studies to date have focused on quantifying and mitigating such bias only in English. These analyses cannot be directly…