Related papers: Helping the Weak Makes You Strong: Simple Multi-Ta…
Neural Algorithmic Reasoning (NAR) trains neural networks to simulate classical algorithms, enabling structured and interpretable reasoning over complex data. While prior research has predominantly focused on learning exact algorithms for…
We introduce negative space learning machine translation (NSL-MT), a training method for underresourced languages, that augments limited parallel data with synthetically generated violations of the target language's grammar and explicitly…
As language models continue to rapidly improve, we can expect their actions and reasoning to become difficult or impossible for weaker agents and humans to follow, undermining interpretability and oversight. With an eye on long-term…
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…
Non-autoregressive approaches aim to improve the inference speed of translation models, particularly those that generate output in a one-pass forward manner. However, these approaches often suffer from a significant drop in translation…
Multi-task learning is to improve the performance of the model by transferring and exploiting common knowledge among tasks. Existing MTL works mainly focus on the scenario where label sets among multiple tasks (MTs) are usually the same,…
Latent tree learning(LTL) methods learn to parse sentences using only indirect supervision from a downstream task. Recent advances in latent tree learning have made it possible to recover moderately high quality tree structures by training…
As large Pre-trained Language Models (PLMs) trained on large amounts of data in an unsupervised manner become more ubiquitous, identifying various types of bias in the text has come into sharp focus. Existing "Stereotype Detection" datasets…
In this paper, we investigate whether multilingual neural translation models learn stronger semantic abstractions of sentences than bilingual ones. We test this hypotheses by measuring the perplexity of such models when applied to…
Neural machine translation is known to require large numbers of parallel training sentences, which generally prevent it from excelling on low-resource language pairs. This thesis explores the use of cross-lingual transfer learning on neural…
The development of neural audio codecs (NACs) has largely promoted applications of language models (LMs) to speech processing and understanding. However, there lacks the verification on the effectiveness of autoregressive (AR) LMbased…
Through the development of neural machine translation, the quality of machine translation systems has been improved significantly. By exploiting advancements in deep learning, systems are now able to better approximate the complex mapping…
In this paper, we present our first attempts in building a multilingual Neural Machine Translation framework under a unified approach. We are then able to employ attention-based NMT for many-to-many multilingual translation tasks. Our…
Practical natural language processing (NLP) tasks are commonly long-tailed with noisy labels. Those problems challenge the generalization and robustness of complex models such as Deep Neural Networks (DNNs). Some commonly used resampling…
Common intermediate language representation in neural machine translation can be used to extend bilingual to multilingual systems by incremental training. In this paper, we propose a new architecture based on introducing an interlingual…
Recent advances have made non-autoregressive (NAT) translation comparable to autoregressive methods (AT). However, their evaluation using BLEU has been shown to weakly correlate with human annotations. Limited research compares…
End-to-end automatic speech recognition (ASR) systems are increasingly popular due to their relative architectural simplicity and competitive performance. However, even though the average accuracy of these systems may be high, the…
Understanding the neural implementation of complex human behaviors is one of the major goals in neuroscience. To this end, it is crucial to find a true representation of the neural data, which is challenging due to the high complexity of…
Model-agnostic meta-learning (MAML) is a meta-learning technique to train a model on a multitude of learning tasks in a way that primes the model for few-shot learning of new tasks. The MAML algorithm performs well on few-shot learning…
Neural network pretraining is gaining attention due to its outstanding performance in natural language processing applications. However, pretraining usually leverages predefined task sequences to learn general linguistic clues. The lack of…