Related papers: Inside ASCENT: Exploring a Deep Commonsense Knowle…
While existing Aspect-based Sentiment Analysis (ABSA) has received extensive effort and advancement, there are still gaps in defining a more holistic research target seamlessly integrating multimodality, conversation context,…
Commonsense knowledge is essential for advancing natural language processing (NLP) by enabling models to engage in human-like reasoning, which requires a deeper understanding of context and often involves making inferences based on implicit…
A deeper understanding of video activities extends beyond recognition of underlying concepts such as actions and objects: constructing deep semantic representations requires reasoning about the semantic relationships among these concepts,…
Commonsense question answering aims to answer questions which require background knowledge that is not explicitly expressed in the question. The key challenge is how to obtain evidence from external knowledge and make predictions based on…
Language comprehension and commonsense knowledge validation by machines are challenging tasks that are still under researched and evaluated for Arabic text. In this paper, we present a benchmark Arabic dataset for commonsense explanation.…
Aspect-level sentiment classification (ASC) aims to predict the fine-grained sentiment polarity towards a given aspect mentioned in a review. Despite recent advances in ASC, enabling machines to preciously infer aspect sentiments is still…
Hypothesis testing is an important cognitive process that supports human reasoning. In this paper, we introduce a computational hypothesis testing approach based on memory augmented neural networks. Our approach involves a hypothesis…
The emergence of Generative AI is catalyzing a paradigm shift in user interfaces from command-based to intent-based outcome specification. In this paper, we explore abstract-to-detailed task transitions in the context of frontend code…
Short textual descriptions of entities provide summaries of their key attributes and have been shown to be useful sources of background knowledge for tasks such as entity linking and question answering. However, generating entity…
We publicly release a new large-scale dataset, called SearchQA, for machine comprehension, or question-answering. Unlike recently released datasets, such as DeepMind CNN/DailyMail and SQuAD, the proposed SearchQA was constructed to reflect…
Existing dense or paragraph video captioning approaches rely on holistic representations of videos, possibly coupled with learned object/action representations, to condition hierarchical language decoders. However, they fundamentally lack…
The field of deep clustering combines deep learning and clustering to learn representations that improve both the learned representation and the performance of the considered clustering method. Most existing deep clustering methods are…
Open-domain dialog involves generating search queries that help obtain relevant knowledge for holding informative conversations. However, it can be challenging to determine what information to retrieve when the user is passive and does not…
Most Reading Comprehension methods limit themselves to queries which can be answered using a single sentence, paragraph, or document. Enabling models to combine disjoint pieces of textual evidence would extend the scope of machine…
Realizing when a model is right for a wrong reason is not trivial and requires a significant effort by model developers. In some cases an input salience method, which highlights the most important parts of the input, may reveal problematic…
Unsupervised commonsense question answering is appealing since it does not rely on any labeled task data. Among existing work, a popular solution is to use pre-trained language models to score candidate choices directly conditioned on the…
Language models (LMs) increasingly drive real-world applications that require world knowledge. However, the internal processes through which models turn data into representations of knowledge and beliefs about the world, are poorly…
Conventional machine learning methods are predominantly designed to predict outcomes based on a single data type. However, practical applications may encompass data of diverse types, such as text, images, and audio. We introduce…
Structured sentences are important expressions in human writings and dialogues. Previous works on neural text generation fused semantic and structural information by encoding the entire sentence into a mixed hidden representation. However,…
Code-switching is a speech phenomenon occurring when a speaker switches language during a conversation. Despite the spontaneous nature of code-switching in conversational spoken language, most existing works collect code-switching data from…