Related papers: Smoothing and Shrinking the Sparse Seq2Seq Search …

Metaphors play a significant role in our everyday communication, yet detecting them presents a challenge. Traditional methods often struggle with improper application of language rules and a tendency to overlook data sparsity. To address…

Cross-lingual transfer of word embeddings aims to establish the semantic mappings among words in different languages by learning the transformation functions over the corresponding word embedding spaces. Successfully solving this problem…

Language diversity presents a significant challenge in speech-to-text (S2T) tasks, such as automatic speech recognition and translation. Traditional multi-lingual multi-task training approaches aim to address this by jointly optimising…

Long samples of text from neural language models can be of poor quality. Truncation sampling algorithms--like top-$p$ or top-$k$ -- address this by setting some words' probabilities to zero at each step. This work provides framing for the…

Language models (LMs) are often used as zero-shot or few-shot classifiers by scoring label words, but they remain fragile to adversarial prompts. Prior work typically optimizes task- or model-specific triggers, making results difficult to…

Sequence-to-sequence transduction is the core problem in language processing applications as diverse as semantic parsing, machine translation, and instruction following. The neural network models that provide the dominant solution to these…

Neural language models often struggle with low-resource languages due to the limited availability of training data, making tokens from these languages rare in the training set. This paper addresses a specific challenge during training: rare…

Making decent multi-lingual sentence representations is critical to achieve high performances in cross-lingual downstream tasks. In this work, we propose a novel method to align multi-lingual embeddings based on the similarity of sentences…

Sentence simplification is the task of rewriting texts so they are easier to understand. Recent research has applied sequence-to-sequence (Seq2Seq) models to this task, focusing largely on training-time improvements via reinforcement…

Despite recent advances in neural text generation, encoding the rich diversity in human language remains elusive. We argue that the sub-optimal text generation is mainly attributable to the imbalanced token distribution, which particularly…

To encourage intra-class compactness and inter-class separability among trainable feature vectors, large-margin softmax methods are developed and widely applied in the face recognition community. The introduction of the large-margin concept…

Techniques for multi-lingual and cross-lingual speech recognition can help in low resource scenarios, to bootstrap systems and enable analysis of new languages and domains. End-to-end approaches, in particular sequence-based techniques, are…

We propose CatchPhrase, a novel audio-to-image generation framework designed to mitigate semantic misalignment between audio inputs and generated images. While recent advances in multi-modal encoders have enabled progress in cross-modal…

We formulate language modeling as a matrix factorization problem, and show that the expressiveness of Softmax-based models (including the majority of neural language models) is limited by a Softmax bottleneck. Given that natural language is…

We simplify sentences with an attentive neural network sequence to sequence model, dubbed S4. The model includes a novel word-copy mechanism and loss function to exploit linguistic similarities between the original and simplified sentences.…

The Sparsespeech model is an unsupervised acoustic model that can generate discrete pseudo-labels for untranscribed speech. We extend the Sparsespeech model to allow for sampling over a random discrete variable, yielding…

Unsupervised sentence embeddings task aims to convert sentences to semantic vector representations. Most previous works directly use the sentence representations derived from pretrained language models. However, due to the token bias in…

The recently proposed Sequence-to-Sequence (seq2seq) framework advocates replacing complex data processing pipelines, such as an entire automatic speech recognition system, with a single neural network trained in an end-to-end fashion. In…

This paper studies compressing pre-trained language models, like BERT (Devlin et al.,2019), via teacher-student knowledge distillation. Previous works usually force the student model to strictly mimic the smoothed labels predicted by the…

The softmax function is widely used in artificial neural networks for the multiclass classification problems, where the softmax transformation enforces the output to be positive and sum to one, and the corresponding loss function allows to…