Related papers: Modeling Harmony with Skip-Grams
Extracting pitch information from music recordings is a challenging but important problem in music signal processing. Frame-wise transcription or multi-pitch estimation aims for detecting the simultaneous activity of pitches in polyphonic…
Maximizing the likelihood of the next token is an established, statistically sound objective for pre-training language models. In this paper we show that we can train better models faster by pre-aggregating the corpus with a collapsed…
Naturally-occurring bracketings, such as answer fragments to natural language questions and hyperlinks on webpages, can reflect human syntactic intuition regarding phrasal boundaries. Their availability and approximate correspondence to…
A growing body of research has demonstrated the inability of NLP models to generalize compositionally and has tried to alleviate it through specialized architectures, training schemes, and data augmentation, among other approaches. In this…
The bag-of-words (BOW) model is the common approach for classifying documents, where words are used as feature for training a classifier. This generally involves a huge number of features. Some techniques, such as Latent Semantic Analysis…
Most robotic grasping systems rely on converting sensor data into explicit 3D point clouds, which is a computational step not found in biological intelligence. This paper explores a fundamentally different, neuro-inspired paradigm for 6-DoF…
Hypergraphs are increasingly utilized in both unimodal and multimodal data scenarios due to their superior ability to model and extract higher-order relationships among nodes, compared to traditional graphs. However, current hypergraph…
Sampling and quantization are standard practices in signal and image processing, but a theoretical understanding of their impact is incomplete. We consider discrete image registration when the underlying function is a one-dimensional…
In-context learning has shown great success in i.i.d semantic parsing splits, where the training and test sets are drawn from the same distribution. In this setup, models are typically prompted with demonstrations that are similar to the…
We investigate the integration of word embeddings as classification features in the setting of large scale text classification. Such representations have been used in a plethora of tasks, however their application in classification…
Sparse sequences of neural spikes are posited to underlie aspects of working memory, motor production, and learning. Discovering these sequences in an unsupervised manner is a longstanding problem in statistical neuroscience. Promising…
A deformed dielectric microcavity is used as an experimental platform for the analysis of the statistics of chaotic resonances, in the perspective of testing fractal Weyl laws at optical frequencies. In order to surmount the difficulties…
In text-to-SQL tasks -- as in much of NLP -- compositional generalization is a major challenge: neural networks struggle with compositional generalization where training and test distributions differ. However, most recent attempts to…
Cross-entropy loss has long been the standard choice for training deep neural networks, yet it suffers from interpretability limitations, unbounded weight growth, and inefficiencies that can contribute to costly training dynamics. The…
Verbal metonymy has received relatively scarce attention in the field of computational linguistics despite the fact that a model to accurately paraphrase metonymy has applications both in academia and the technology sector. The method…
In this paper, we propose an effective and robust method for acoustic scene analysis based on spatial information extracted from partially synchronized and/or closely located distributed microphones. In the proposed method, to extract…
We present Charagram embeddings, a simple approach for learning character-based compositional models to embed textual sequences. A word or sentence is represented using a character n-gram count vector, followed by a single nonlinear…
Temporal grounding is the task of locating a specific segment from an untrimmed video according to a query sentence. This task has achieved significant momentum in the computer vision community as it enables activity grounding beyond…
We provide the first extensive evaluation of how using different types of context to learn skip-gram word embeddings affects performance on a wide range of intrinsic and extrinsic NLP tasks. Our results suggest that while intrinsic tasks…
Paired image-text data with subtle variations in-between (e.g., people holding surfboards vs. people holding shovels) hold the promise of producing Vision-Language Models with proper compositional understanding. Synthesizing such training…