Related papers: When and Where Did it Happen? An Encoder-Decoder M…
In video analysis, understanding the temporal context is crucial for recognizing object interactions, event patterns, and contextual changes over time. The proposed model leverages adjacency and semantic similarities between objects from…
Driving in the dynamic, multi-agent, and complex urban environment is a difficult task requiring a complex decision policy. The learning of such a policy requires a state representation that can encode the entire environment. Mid-level…
Accurate medical symptom coding from unstructured clinical text, such as vaccine safety reports, is a critical task with applications in pharmacovigilance and safety monitoring. Symptom coding, as tailored in this study, involves…
While deep neural networks have led to human-level performance on computer vision tasks, they have yet to demonstrate similar gains for holistic scene understanding. In particular, 3D context has been shown to be an extremely important cue…
Recently, knowledge-grounded conversations in the open domain gain great attention from researchers. Existing works on retrieval-based dialogue systems have paid tremendous efforts to utilize neural networks to build a matching model, where…
Context plays an important role in visual recognition. Recent studies have shown that visual recognition networks can be fooled by placing objects in inconsistent contexts (e.g., a cow in the ocean). To model the role of contextual…
This work addresses on the following problem: given a set of unsynchronized history observations of two scenes that are correlative on their dynamic changes, the purpose is to learn a cross-scene predictor, so that with the observation of…
Current ASR systems are mainly trained and evaluated at the utterance level. Long range cross utterance context can be incorporated. A key task is to derive a suitable compact representation of the most relevant history contexts. In…
Action recognition and anticipation are key to the success of many computer vision applications. Existing methods can roughly be grouped into those that extract global, context-aware representations of the entire image or sequence, and…
Modern neural speech models benefit from having longer context, and many approaches have been proposed to increase the maximum context a model can use. However, few have attempted to measure how much context these models actually use, i.e.,…
Context plays an important role in human language understanding, thus it may also be useful for machines learning vector representations of language. In this paper, we explore an asymmetric encoder-decoder structure for unsupervised…
To understand and infer meaning in language, neural models have to learn complicated nuances. Discovering distinctive linguistic phenomena from data is not an easy task. For instance, lexical ambiguity is a fundamental feature of language…
This paper investigates contextual word representation models from the lens of similarity analysis. Given a collection of trained models, we measure the similarity of their internal representations and attention. Critically, these models…
We aim to better understand the emergence of `situational awareness' in large language models (LLMs). A model is situationally aware if it's aware that it's a model and can recognize whether it's currently in testing or deployment. Today's…
Pre-trained transformer-based models have recently shown great performance when applied to Named Entity Recognition (NER). As the complexity of their self-attention mechanism prevents them from processing long documents at once, these…
In this paper, we propose a generalizable method that systematically combines data driven MCMC samplingand inference using rule-based context knowledge for data abstraction. In particular, we demonstrate the usefulness of our method in the…
Applications like personal assistants need to be aware ofthe user's context, e.g., where they are, what they are doing, and with whom. Context information is usually inferred from sensor data, like GPS sensors and accelerometers on the…
Researchers in the political and social sciences often rely on classification models to analyze trends in information consumption by examining browsing histories of millions of webpages. Automated scalable methods are necessary due to the…
Derivational morphology is a fundamental and complex characteristic of language. In this paper we propose the new task of predicting the derivational form of a given base-form lemma that is appropriate for a given context. We present an…
Purpose - This paper presents a methodology for defining and modeling context-awareness and describing efficiently the interactions between systems, applications and their context. Also the relation of modern context-aware systems with…