Related papers: vec2text with Round-Trip Translations

Semantic trajectories are high level representations of user movements where several aspects related to the movement context are represented as heterogeneous textual labels. With the objective of finding a meaningful similarity measure for…

Techniques in which words are represented as vectors have proved useful in many applications in computational linguistics, however there is currently no general semantic formalism for representing meaning in terms of vectors. We present a…

Scarcity of training data for task-oriented dialogue systems is a well known problem that is usually tackled with costly and time-consuming manual data annotation. An alternative solution is to rely on automatic text generation which,…

In the field of Natural Language Processing (NLP), we revisit the well-known word embedding algorithm word2vec. Word embeddings identify words by vectors such that the words' distributional similarity is captured. Unexpectedly, besides…

The research in machine translation community focus on translation in text space. However, humans are in fact also good at direct translation in pronunciation space. Some existing translation systems, such as simultaneous machine…

Natural Language Processing (NLP) relies heavily on training data. Transformers, as they have gotten bigger, have required massive amounts of training data. To satisfy this requirement, text augmentation should be looked at as a way to…

Temporal word embeddings have been proposed to support the analysis of word meaning shifts during time and to study the evolution of languages. Different approaches have been proposed to generate vector representations of words that embed…

In the last two decades, the landscape of text generation has undergone tremendous changes and is being reshaped by the success of deep learning. New technologies for text generation ranging from template-based methods to neural…

In this work, we take the first steps towards building a universal rewriter: a model capable of rewriting text in any language to exhibit a wide variety of attributes, including styles and languages, while preserving as much of the original…

Visual text evokes an image in a person's mind, while non-visual text fails to do so. A method to automatically detect visualness in text will enable text-to-image retrieval and generation models to augment text with relevant images. This…

Sentiments of words differ from one corpus to another. Inducing general sentiment lexicons for languages and using them cannot, in general, produce meaningful results for different domains. In this paper, we combine contextual and…

Translations capture important information about languages that can be used as implicit supervision in learning linguistic properties and semantic representations. In an information-centric view, translated texts may be considered as…

Variational autoencoders (VAEs) are essential tools in end-to-end representation learning. However, the sequential text generation common pitfall with VAEs is that the model tends to ignore latent variables with a strong auto-regressive…

In translation, a concept represented by a single word in a source language can have multiple variations in a target language. The task of lexical selection requires using context to identify which variation is most appropriate for a source…

This paper introduces a new approach to generating strongly constrained texts. We consider standardized sentence generation for the typical application of vision screening. To solve this problem, we formalize it as a discrete combinatorial…

Pretrained transformer-based models have shown high performance in natural language generation task. However, a new wave of interest has surged: automatic programming language generation. This task consists of translating natural language…

We approach the problem of generalizing pre-trained word embeddings beyond fixed-size vocabularies without using additional contextual information. We propose a subword-level word vector generation model that views words as bags of…

Large-scale language models (LMs) pretrained on massive corpora of text, such as GPT-2, are powerful open-domain text generators. However, as our systematic examination reveals, it is still challenging for such models to generate coherent…

Transformer language models can generate strikingly natural text by modeling language as a sequence of tokens, but by relying primarily on surface-level co-occurrence statistics they fail to form globally consistent latent representations…

The dominant text generation models compose the output by sequentially selecting words from a fixed vocabulary. In this paper, we formulate text generation as progressively copying text segments (e.g., words or phrases) from an existing…