10 accepted papers
Fusion-in-decoder (Fid) (Izacard and Grave, 2020) is a generative question answering (QA) model that leverages passage retrieval with a pre-trained transformer and pushed the state of the art on single-hop QA. However, the complexity of multi-hop QA hinders the effectiveness of the generative QA app…
Byte-pair encoding (BPE) is a ubiquitous algorithm in the subword tokenization process of language models as it provides multiple benefits. However, this process is solely based on pre-training data statistics, making it hard for the tokenizer to handle infrequent spellings. On the other hand, thoug…
Neural text decoding algorithms strongly influence the quality of texts generated using language models, but popular algorithms like top-k, top-p (nucleus), and temperature-based sampling may yield texts that have objectionable repetition or incoherence. Although these methods generate high-quality…
Paraphrase generation has benefited extensively from recent progress in the designing of training objectives and model architectures. However, previous explorations have largely focused on supervised methods, which require a large amount of labeled data that is costly to collect. To address this dra…
While it has not yet been proven, empirical evidence suggests that model generalization is related to local properties of the optima, which can be described via the Hessian. We connect model generalization with the local property of a solution under the PAC-Bayes paradigm. In particular, we prove th…
The convergence rate and final performance of common deep learning models have significantly benefited from recently proposed heuristics such as learning rate schedules, knowledge distillation, skip connections and normalization layers. In the absence of theoretical underpinnings, controlled experim…
End-to-end neural models have made significant progress in question answering, however recent studies show that these models implicitly assume that the answer and evidence appear close together in a single document. In this work, we propose the Coarse-grain Fine-grain Coattention Network (CFC), a ne…
In this paper, we consider the specific problem of word-level language modeling and investigate strategies for regularizing and optimizing LSTM-based models. We propose the weight-dropped LSTM, which uses DropConnect on hidden-to-hidden weights, as a form of recurrent regularization. Further, we int…
The stochastic gradient descent (SGD) method and its variants are algorithms of choice for many Deep Learning tasks. These methods operate in a small-batch regime wherein a fraction of the training data, say $32$--$512$ data points, is sampled to compute an approximation to the gradient. It has bee…
The algorithm of choice for cross-entropy training of deep neural network (DNN) acoustic models is mini-batch stochastic gradient descent (SGD). One of the important decisions for this algorithm is the learning rate strategy (also called stepsize selection). We investigate several existing schemes a…