Related papers: Modeling Event Background for If-Then Commonsense …
Context-aware neural machine translation involves leveraging information beyond sentence-level context to resolve inter-sentential discourse dependencies and improve document-level translation quality, and has given rise to a number of…
Anomaly detection with convolutional autoencoders is a popular method to search for new physics in a model-agnostic manner. These techniques are powerful, but they are still a "black box," since we do not know what high-level physical…
Computational and cognitive studies of event understanding suggest that identifying, comprehending, and predicting events depend on having structured representations of a sequence of events and on conceptualizing (abstracting) its…
While recent neural encoder-decoder models have shown great promise in modeling open-domain conversations, they often generate dull and generic responses. Unlike past work that has focused on diversifying the output of the decoder at…
Pre-trained language models have shown excellent results in few-shot learning scenarios using in-context learning. Although it is impressive, the size of language models can be prohibitive to make them usable in on-device applications, such…
In this paper, we aim to extract commonsense knowledge to improve machine reading comprehension. We propose to represent relations implicitly by situating structured knowledge in a context instead of relying on a pre-defined set of…
Commonsense temporal reasoning at scale is a core problem for cognitive systems. The correct inference of the duration for which fluents hold is required by many tasks, including natural language understanding and planning. Many AI systems…
While many production-ready and robust algorithms are available for the task of recommendation systems, many of these systems do not take the order of user's consumption into account. The order of consumption can be very useful and matters…
Data-driven societal event forecasting methods exploit relevant historical information to predict future events. These methods rely on historical labeled data and cannot accurately predict events when data are limited or of poor quality.…
We focus on the task of reasoning over paragraph effects in situation, which requires a model to understand the cause and effect described in a background paragraph, and apply the knowledge to a novel situation. Existing works ignore the…
Recent studies on transformer-based language models show that they can answer questions by reasoning over knowledge provided as part of the context (i.e., in-context reasoning). However, since the available knowledge is often not filtered…
Recently generating natural language explanations has shown very promising results in not only offering interpretable explanations but also providing additional information and supervision for prediction. However, existing approaches…
Natural Language Inference (NLI) is foundational for evaluating language understanding in AI. However, progress has plateaued, with models failing on ambiguous examples and exhibiting poor generalization. We argue that this stems from…
Commonsense reasoning is a long-standing challenge for deep learning. For example, it is difficult to use neural networks to tackle the Winograd Schema dataset (Levesque et al., 2011). In this paper, we present a simple method for…
The existence of external (``side'') semantic knowledge has been shown to result in more expressive computational event models. To enable the use of side information that may be noisy or missing, we propose a semi-supervised information…
Given a question-image input, the Visual Commonsense Reasoning (VCR) model can predict an answer with the corresponding rationale, which requires inference ability from the real world. The VCR task, which calls for exploiting the…
We introduce a neural reading comprehension model that integrates external commonsense knowledge, encoded as a key-value memory, in a cloze-style setting. Instead of relying only on document-to-question interaction or discrete features as…
Intelligent Traffic Monitoring (ITMo) technologies hold the potential for improving road safety/security and for enabling smart city infrastructure. Understanding traffic situations requires a complex fusion of perceptual information with…
In this thesis, we develop methods to enhance the interpretability of recent representation learning techniques in natural language processing (NLP) while accounting for the unavailability of annotated data. We choose to leverage…
We describe a data-driven approach for automatically explaining new, non-standard English expressions in a given sentence, building on a large dataset that includes 15 years of crowdsourced examples from UrbanDictionary.com. Unlike prior…