Related papers: Span Pointer Networks for Non-Autoregressive Task-…
Despite the growing interest in unsupervised learning, extracting meaningful knowledge from unlabelled audio remains an open challenge. To take a step in this direction, we recently proposed a problem-agnostic speech encoder (PASE), that…
We propose Seq2Edits, an open-vocabulary approach to sequence editing for natural language processing (NLP) tasks with a high degree of overlap between input and output texts. In this approach, each sequence-to-sequence transduction is…
We propose LaserTagger - a sequence tagging approach that casts text generation as a text editing task. Target texts are reconstructed from the inputs using three main edit operations: keeping a token, deleting it, and adding a phrase…
Neural sequence-to-sequence networks with attention have achieved remarkable performance for machine translation. One of the reasons for their effectiveness is their ability to capture relevant source-side contextual information at each…
This paper describes a neural semantic parser that maps natural language utterances onto logical forms which can be executed against a task-specific environment, such as a knowledge base or a database, to produce a response. The parser…
Sequence prediction on temporal data requires the ability to understand compositional structures of multi-level semantics beyond individual and contextual properties. The task of temporal action segmentation, which aims at translating an…
Most machine translation systems generate text autoregressively from left to right. We, instead, use a masked language modeling objective to train a model to predict any subset of the target words, conditioned on both the input text and a…
Learning latent representations from long text sequences is an important first step in many natural language processing applications. Recurrent Neural Networks (RNNs) have become a cornerstone for this challenging task. However, the quality…
In this paper, we propose a new differentiable neural network alignment mechanism for text-dependent speaker verification which uses alignment models to produce a supervector representation of an utterance. Unlike previous works with…
Autoregressive (AR) Transformer-based sequence models are known to have difficulty generalizing to sequences longer than those seen during training. When applied to text-to-speech (TTS), these models tend to drop or repeat words or produce…
Recent advances in text recognition led to a paradigm shift for page-level recognition, from multi-step segmentation-based approaches to end-to-end attention-based ones. However, the na\"ive character-level autoregressive decoding process…
The autoregressive (AR) models, such as attention-based encoder-decoder models and RNN-Transducer, have achieved great success in speech recognition. They predict the output sequence conditioned on the previous tokens and acoustic encoded…
With parallelizable attention networks, the neural Transformer is very fast to train. However, due to the auto-regressive architecture and self-attention in the decoder, the decoding procedure becomes slow. To alleviate this issue, we…
Sentence embedding is one of the most fundamental tasks in Natural Language Processing and plays an important role in various tasks. The recent breakthrough in sentence embedding is achieved by pre-trained language models (PLMs). Despite…
Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to…
We describe a data-driven approach for automatically explaining new, non-standard English expressions in a given sentence, building on a large dataset that includes 15 years of crowdsourced examples from UrbanDictionary.com. Unlike prior…
It is encouraged to see that progress has been made to bridge videos and natural language. However, mainstream video captioning methods suffer from slow inference speed due to the sequential manner of autoregressive decoding, and prefer…
Attention-based sequence-to-sequence modeling provides a powerful and elegant solution for applications that need to map one sequence to a different sequence. Its success heavily relies on the availability of large amounts of training data.…
Standard decoders for neural machine translation autoregressively generate a single target token per time step, which slows inference especially for long outputs. While architectural advances such as the Transformer fully parallelize the…
Non-autoregressive approaches aim to improve the inference speed of translation models by only requiring a single forward pass to generate the output sequence instead of iteratively producing each predicted token. Consequently, their…