Related papers: Natural Language to Structured Query Generation vi…

Providing plausible responses to why questions is a challenging but critical goal for language based human-machine interaction. Explanations are challenging in that they require many different forms of abstract knowledge and reasoning.…

Natural language is hypothetically the best user interface for many domains. However, general models that provide an interface between natural language and any other domain still do not exist. Providing natural language interface to…

Suggesting similar questions for a user query has many applications ranging from reducing search time of users on e-commerce websites, training of employees in companies to holistic learning for students. The use of Natural Language…

In this work, we present TGLS, a novel framework to unsupervised Text Generation by Learning from Search. We start by applying a strong search algorithm (in particular, simulated annealing) towards a heuristically defined objective that…

A major problem of machine-learning approaches in structural dynamics is the frequent lack of structural data. Inspired by the recently-emerging field of population-based structural health monitoring (PBSHM), and the use of transfer…

Meta-learning is a powerful paradigm for few-shot learning. Although with remarkable success witnessed in many applications, the existing optimization based meta-learning models with over-parameterized neural networks have been evidenced to…

Continuously-growing data volumes lead to larger generic models. Specific use-cases are usually left out, since generic models tend to perform poorly in domain-specific cases. Our work addresses this gap with a method for selecting…

Natural language understanding (NLU) and natural language generation (NLG) are both critical research topics in the NLP field. Natural language understanding is to extract the core semantic meaning from the given utterances, while natural…

Many modern NLP systems rely on word embeddings, previously trained in an unsupervised manner on large corpora, as base features. Efforts to obtain embeddings for larger chunks of text, such as sentences, have however not been so…

The rise of deep learning in natural language processing has fostered the creation of text to structured query language models composed of an encoder and a decoder. Researchers have experimented with various intermediate processing like…

Self-supervised learning has significantly improved the performance of many NLP tasks. However, how can self-supervised learning discover useful representations, and why is it better than traditional approaches such as probabilistic models…

Generating queries corresponding to natural language questions is a long standing problem. Traditional methods lack language flexibility, while newer sequence-to-sequence models require large amount of data. Schema-agnostic…

Meta-learning has been shown to have better performance than supervised learning for few-shot monolingual spoken word classification. However, the meta-learning approach remains under-explored in multilingual spoken word classification. In…

We present SkillNet-NLG, a sparsely activated approach that handles many natural language generation tasks with one model. Different from traditional dense models that always activate all the parameters, SkillNet-NLG selectively activates…

Pre-trained models are nowadays a fundamental component of machine learning research. In continual learning, they are commonly used to initialize the model before training on the stream of non-stationary data. However, pre-training is…

In self-supervised learning, a model is trained to solve a pretext task, using a data set whose annotations are created by a machine. The objective is to transfer the trained weights to perform a downstream task in the target domain. We…

Despite alarm over the reliance of machine learning systems on so-called spurious patterns, the term lacks coherent meaning in standard statistical frameworks. However, the language of causality offers clarity: spurious associations are due…

Compared to humans, machine learning models generally require significantly more training examples and fail to extrapolate from experience to solve previously unseen challenges. To help close this performance gap, we augment single-task…

The tracking-by-detection framework requires a set of positive and negative training samples to learn robust tracking models for precise localization of target objects. However, existing tracking models mostly treat different samples…

Neural natural language generation (NLG) and understanding (NLU) models are data-hungry and require massive amounts of annotated data to be competitive. Recent frameworks address this bottleneck with generative models that synthesize weak…