Related papers: Automatic Rule Generation for Time Expression Norm…
Taking the continuum limit is essential for extracting physical observables from quantum simulations of lattice gauge theories. Achieving the correct continuum limit requires careful control of all systematic uncertainties, including those…
We present a self-supervised approach for learning video representations using temporal video alignment as a pretext task, while exploiting both frame-level and video-level information. We leverage a novel combination of temporal alignment…
Recent experiments by Springer and Kenyon have shown that a deep neural network can be trained to predict the action of $t$ steps of Conway's Game of Life automaton given millions of examples of this action on random initial states.…
Automated predictions require explanations to be interpretable by humans. One type of explanation is a rationale, i.e., a selection of input features such as relevant text snippets from which the model computes the outcome. However, a…
The rapid development of generative technology opens up possibility for higher level of automation, and artificial intelligence (AI) embodiment in robotic systems is imminent. However, due to the blackbox nature of the generative…
Neural style transfer is a powerful computer vision technique that can incorporate the artistic "style" of one image to the "content" of another. The underlying theory behind the approach relies on the assumption that the style of an image…
Normalization and scaling are fundamental preprocessing steps in time series modeling, yet their role in Transformer-based models remains underexplored from a theoretical perspective. In this work, we present the first formal analysis of…
Automatic term extraction (ATE) is a Natural Language Processing (NLP) task that eases the effort of manually identifying terms from domain-specific corpora by providing a list of candidate terms. As units of knowledge in a specific field…
We explore training an automatic modality tagger. Modality is the attitude that a speaker might have toward an event or state. One of the main hurdles for training a linguistic tagger is gathering training data. This is particularly…
Normalization techniques play an important role in supporting efficient and often more effective training of deep neural networks. While conventional methods explicitly normalize the activations, we suggest to add a loss term instead. This…
We characterize normalization by evaluation as the composition of a self-interpreter with a self-reducer using a special representation scheme, in the sense of Mogensen (1992). We do so by deriving in a systematic way an untyped…
Most algorithms for representation learning and link prediction on relational data are designed for static data. However, the data to which they are applied typically evolves over time, including online social networks or interactions…
Recent advances in large language model (LLM) training have highlighted the need for diverse, high-quality instruction data. Recently, many works are exploring synthetic data generation using LLMs. However, they primarily focus on prompt…
Optimizing compilers, as well as other translator systems, often work by rewriting expressions according to equivalence preserving rules. Given an input expression and its optimized form, finding the sequence of rules that were applied is a…
We present a model of pragmatic language understanding, where utterances are produced and understood by searching for regularized equilibria of signaling games. In this model (which we call ReCo, for Regularized Conventions), speakers and…
We present a novel counterexample-guided, sketch-based method for the synthesis of symbolic distributed protocols in TLA+. Our method's chief novelty lies in a new search space reduction technique called interpretation reduction, which…
Self-supervised methods such as Contrastive predictive Coding (CPC) have greatly improved the quality of the unsupervised representations. These representations significantly reduce the amount of labeled data needed for downstream task…
Broadcasts and timelines are the primary mechanism of information exchange in online social platforms today. Services like Facebook, Twitter and Instagram have enabled ordinary people to reach large audiences spanning cultures and…
Self-normalized processes arise naturally in statistical applications. Being unit free, they are not affected by scale changes. Moreover, self-normalization often eliminates or weakens moment assumptions. In this paper we present several…
Modern conversational AI systems support natural language understanding for a wide variety of capabilities. While a majority of these tasks can be accomplished using a simple and flat representation of intents and slots, more sophisticated…