Search results

Temporal point processes (TPP) are probabilistic generative models for continuous-time event sequences. Neural TPPs combine the fundamental ideas from point process literature with deep learning approaches, thus enabling construction of flexible and efficient models. The topic of neural TPPs has attracted significant attention in recent years, leading to the development of numerous new architectures and

In this paper, we present our Alexa Prize Grand Challenge 4 socialbot: Proto. Leveraging diverse sources of world knowledge, and powered by a suite of neural and rule-based natural language understanding modules, state-of-the-art neural generators, novel state-based deterministic generators, an ensemble of neural re- rankers, a robust post-processing algorithm, and an efficient overall conversation strategy

We consider the framework of non-stationary Online Convex Optimization where a learner seeks to control its dynamic regret against an arbitrary sequence of comparators. When the loss functions are strongly convex or exp-concave, we demonstrate that Strongly Adaptive (SA) algorithms can be viewed as a principled way of controlling dynamic regret in terms of path variation VT of the comparator sequence. Specifically

Natural language often contains ambiguities that can lead to misinterpretation and miscommunication. While humans can handle ambiguities effectively by asking clarifying questions and/or relying on contextual cues and commonsense knowledge, resolving ambiguities can be notoriously hard for machines. In this work, we study ambiguities that arise in text-to-image generative models. We curate the Text-to-image

Phonetic information and linguistic knowledge are an essential component of a Text-to-speech (TTS) front-end. Given a language, a lexicon can be collected offline and Grapheme-toPhoneme (G2P) relationships are usually modeled in order to predict the pronunciation for out-of-vocabulary (OOV) words. Additionally, post-lexical phonology, often defined in the form of rule-based systems, is used to correct pronunciation

Popular models for Knowledge Graph Question Answering (KGQA), including semantic parsing and End-to-End (E2E) models, decode into a constrained space of KG relations. Al-though E2E models accommodate novel entities at test-time, this constraint means they cannot access novel relations, requiring expensive and time-consuming retraining whenever a new relation is added to the KG. We propose KG-Flex, a new

Emphatic algorithms have shown great promise in stabilizing and improving reinforcement learning by selectively emphasizing the update rule. Although the emphasis fundamentally depends on an interest function which defines the intrinsic importance of each state, most approaches simply adopt a uniform interest over all states (except where a hand-designed interest is possible based on domain knowledge).

Watermark text spotting in document images can offer access to an often unexplored source of information, providing crucial evidence about a record’s scope, audience and sometimes even authenticity. Stemming from the problem of text spotting, detecting and understanding watermarks in documents inherits the same hardships - in the wild, writing can come in various fonts, sizes and forms, making generic recognition

Recent studies show that sentence-level extractive QA, i.e., based on Answer Sentence Selection (AS2), is outperformed by Generationbased QA (GenQA) models, which generate answers using the top-k answer sentences ranked by AS2 models (a la retrieval-augmented generation style). In this paper, we propose a novel training paradigm for GenQA using supervision from automatic QA evaluation models (GAVA). Specifically

Given a particular claim about a specific document, the fact checking problem is to determine if the claim is true and, if so, provide corroborating evidence. The problem is motivated by contexts where a document is too lengthy to quickly read and find an answer. This paper focuses on electronic health records, or a medical dossier, where a physician has a pointed claim to make about the record. Prior methods

Watch the recording of Marcu's live interview with Alexa evangelist Jeff Blankenburg.

This paper introduces a robust unsupervised SE(3) point cloud registration method that operates without requiring point correspondences. The method frames point clouds as functions in a reproducing kernel Hilbert space (RKHS), leveraging SE(3)-equivariant features for direct feature space registration. A novel RKHS distance metric is proposed, offering reliable performance amidst noise, outliers, and asymmetrical

To the best of our knowledge, this work introduces the first framework for clustering longitudinal data by leveraging time-dependent causal representation learning. Clustering longitudinal data has gained significant attention across various fields, yet traditional methods often overlook the causal structures underlying observed patterns. Understanding how covariates influence outcomes is critical for policymakers

Amazon Scholar Heng Ji says that deep learning could benefit from the addition of a little linguistic intuition.

We present an autonomous framework that leverages Large Language Models (LLMs) to automate end-to-end business analysis and market report generation. At its core, the system employs specialized agents - Researcher, Reviewer, Writer, and Retriever - that collaborate to analyze data and produce comprehensive reports. These agents learn from real professional consultants' presentation materials at Amazon through

Online advertisement industry aims to build a preference for a product over its competitors by making consumers aware of the product at internet scale. However, the ads that violate the applicable laws and location specific regulations can have serious business impact with legal implications. At the same time, customers are at risk of getting exposed to egregious ads resulting in a bad user experience.

FEVER (Fact Extraction and VERification) consists of 185,445 claims generated by altering sentences extracted from Wikipedia and subsequently verified without knowledge of the sentence they were derived from. The claims are classified as Supported, Refuted or NotEnoughInfo. For the first two classes, the annotators also recorded the sentence(s) forming the necessary evidence for their judgment.

Non-autoregressive models and, in particular, Connectionist Temporal Classification (CTC) models have been the most popular approaches towards mispronunciation detection and diagnosis (MDD) task. In this paper, we identify two important knowledge gaps in MDD that have not been well studied in existing MDD research. First, CTC-based MDD models often assume conditional independence in the predicted phonemes

Fashion representation learning involves the analysis and understanding of various visual elements at different granularities and the interactions among them. Existing works often learn fine-grained fashion representations at the attribute level without considering their relationships and inter-dependencies across different classes. In this work, we propose to learn an attribute and class-specific fashion

For social robots operating in home environments, identifying appropriate parking locations which are “out of the way” is a challenging and multi-faceted problem. This paper proposes a solution to one core aspect of that problem, specifically a model for estimating locations where the robot may block walking paths through narrow spaces. For generality, this model assumes no a priori knowledge about user