Deep Learning for Prominence Detection in Children s Read Speech

Expressive reading, considered the defining attribute of oral readingfluency, comprises the prosodic realization of phrasing and prominence . We consider a labeled dataset of children’s readingrecordings for the speaker-independent detection of prominent words using acoustic-prosodic and lexico-syntactic features . Deeplearning is applied to obtain word-level features from low-level acousticcontours of fundamental frequency, intensity and spectral shape in anend-to-end fashion .…

Characterization of Decomposition of Matrix Multiplication Tensors

The canonical polyadic (CP) decomposition of tensors thatcorresponds to matrix multiplications is studied . Finding the rank of thesetensors and computing the decompositions is a fundamental problem of algebraiccomplexity theory . In this paper, we present a novel decomposition . of the tensormultiplication of matrices of the size 3×3 with 3×6 with rank 40 .…

Feedback Vertex Set on Hamiltonian Graphs

We study the computational complexity of Feedback Vertex Set on subclasses ofHamiltonian graphs . In particular, we consider Hamiltonian graphs that areregular or are planar and regular . We also study the less known class of $p$-Hamiltonian-ordered graphs, which admit for any $ p$-tupleof vertices a Hamiltonian cycle visiting them in the order given by the tuples of vertices .…

Consequence aware Sequential Counterfactual Generation

Counterfactuals have become a popular technique nowadays for interacting with black-box machine learning models and understanding how to change a particularinstance to obtain a desired outcome . Most existing approaches assume instant materialization of these changes, ignoring that they may require effort and a specific order of application .…

QZNs Quantum Z numbers

Z-numbers lack the ability to process the quantum information in quantum environment . The results show that, with the help of quantum computation, the proposed algorithm can make diagnoses correctly and efficiently . Based on QZNs, a novel quantummulti-attributes decision making (MADM) algorithm is proposed and applied in medical diagnosis.…

Self Training with Weak Supervision

State-of-the-art deep neural networks require large-scale labeled training data that is often expensive to obtain or not available for many tasks . In this work, we develop a weak supervision framework (ASTRA) that leveragesall the available data for a given task .…

Updater Extractor Architecture for Inductive World State Representations

Developing NLP models traditionally involves two stages – training andapplication . Retention of information acquired after training (at applicationtime) is limited by the size of the model’s context window . In this paper, we propose a noveltransformer-based Updater-Extractor architecture and a training procedure that can work with sequences of arbitrary length and refine its knowledge about the world based on linguistic inputs .…

Synthesis of Frame Field Aligned Multi Laminar Structures

Homogenization approach can represent microstructural design at a much finer length-scale than the computational grid . The optimal microstructure for asingle load case is an orthogonal rank-3 laminate . We propose a method for generating multi-laminar structures from framefields. We provide two methods for generating structures from stream surface collections.…

On Unifying Misinformation Detection

UnifiedM2 is a general-purpose misinformation model that jointly models multiple domains of misinformation with a single, unified setup . The model is trained to handle four tasks: detecting news bias, clickbait, fake news, and verifying rumors . By grouping these tasks together, the model learns a richer representation of misinformation, which leads to comparable performance across all tasks .…

Boltzmann Tuning of Generative Models

Boltzmann Tuning ofGenerative Models (BTGM) applies to a wide range of applications . It coversconditional generative modelling as a particular case, and offers an affordable alternative to rejection sampling . The merits of the approach are demonstrated on a real-world application, in the context of robust design for energypolicies, showing the ability of BTGM to sample the extreme regions of the considered criteria .…

An Approach to Symbolic Regression Using Feyn

The QLattice is a supervised machine learning tool inspired by Richard Feynman’spath integral formulation, that explores many potential models that solves agiven problem . It formulates these models as graphs that can be interpreted as equations . We show how it differs from traditional machine learning approaches, what it has in common with them .…

Backtranslation Feedback Improves User Confidence in MT Not Quality

Backward translation feedback has a mixed effect on the whole process: itincreases user confidence in the produced translation, but not the objective quality . Backward translations are three modules: backward translation, quality estimation (with alignment) and sourceparaphrasing . We examine the effects of each proposed feedback module and further focus on how the quality of machine translationsystems influence these findings and the user perception of success .…

Building Mental Models through Preview of Autopilot Behaviors

Autopilot behavior can help to ensuresmoothhuman-vehicle collaboration during the initial exploration stagewith thevehicle . AutoPreview framework can provide a deeperunderstanding of autopilot behavior compared to direct interaction with the vehicle . We conducted acase study on humans-vehicles collaboration and built a prototype of our framework with theCARLA simulator .…

Adversarial Open Domain Adaption for Sketch to Photo Synthesis

The open-domain sketch-to-photo translation is challenging due to the lack of training supervision and the large geometrydistortion between the freehand sketch and photo domains . We propose a framework that jointlylearns sketch to photo and photo-to sketch generation . We validate our method on the Scribble and SketchyCOCO datasets.…

LearningCity Knowledge Generation for Smart Cities

LearningCity aims to create knowledge creation in smart cities through anomaly detection and dataannotation, supported in both an automated and crowdsourced manner . The solution has been validated over an existing smart city deployment in Santander, and the OrganiCityexperimentation-as-a-service ecosystem .…

Semantic Frame Forecast

This paper introduces semantic frame forecast, a task that predicts thesemantic frames that will occur in the next 10, 100, or even 1,000 sentences in a running story . We represent a storyblock using the term frequencies (TF) of semantic frames in it, normalized by each frame’s inverse document frequency (IDF) We conduct semantic frameforecast experiments on 4,794 books from the Bookcorpus and 7,962 scientificabstracts from CODA-19 .…

Macro Average Rare Types Are Important Too

Traditional corpus-level evaluation metrics for machine translation (MT) correlate well with fluency but struggle to reflect adequacy . We explore the simple type-based classifiermetric, MacroF1, and study its applicability to MT evaluation . We find thatMacroF1 is competitive on direct assessment, and outperforms others in indicating downstream cross-lingual information retrieval task performance .…

Investigating Methods to Improve Language Model Integration for Attention based Encoder Decoder ASR Models

Attention-based encoder-decoder (AED) models learn an implicit internallanguage model (ILM) from the training transcriptions . Bayesian interpretation as in the hybrid autoregressivetransducer (HAT) suggests dividing by the prior of the discriminative acoustic model, which corresponds to this implicit LM . We propose several novel methods to estimate the ILM directly from the AED model .…

StylePTB A Compositional Benchmark for Fine grained Controllable Text Style Transfer

Text style transfer aims to controllably generate text with targetedstylistic changes while maintaining core meaning from the source sentenceconstant . Many existing style transfer benchmarks do not offer fine-grained control on sentence structure, emphasis, and content of the sentence . We introduce a large-scale benchmark, StylePTB, with pairedsentences undergoing 21 stylistic changes spanning atomic lexical,syntactic, semantic, and thematic transfers of text .…

Fine Tuning Transformers for Identifying Self Reporting Potential Cases and Symptoms of COVID 19 in Tweets

We describe our straight-forward approach for Tasks 5 and 6 of 2021 SocialMedia Mining for Health Applications (SMM4H) shared tasks . We explore how much fine-tuning is necessary for classifying tweets as containing self-reported COVID-19 symptoms (Task 5) or whether a tweet related to the virus is self-reporting, non-personalreporting, or a literature/news mention of the virus (Task 6)…

Accelerating science with human versus alien artificial intelligences

Data-driven artificial intelligence models fed with published scientific findings have been used to create powerful prediction engines for scientific and technological advance . These models succeed by predicting human predictions and the scientists who will make them . By tuning AI to avoid the crowd, however, itgenerates scientifically promising “alien” hypotheses unlikely to be imagined or pursued without intervention, not only accelerating but punctuatingscientific advance .…

Joint Universal Syntactic and Semantic Parsing

While numerous attempts have been made to jointly parse syntax and semantics, high performance in one domain typically comes at the price of performance inthe other . This trade-off contradicts a large body of research focusing on the rich interactions at the syntax-semantics interface .…

Interpretable Methods for Identifying Product Variants

For e-commerce companies, organization andgrouping of products in meaningful ways is important for creating great customer shopping experiences . One important way of grouping products is to identify a family of product variants,where the variants are mostly the same with slight and yet distinct differences(e.g.…

Unsupervised Lane Change Identification for On Ramp Merge Analysis in Naturalistic Driving Data

Connected and Automated Vehicles (CAVs) are envisioned to transform the future industrial and private transportation sectors . Functional verification and validation of safety aspects are essential before the technology merges into the public domain . This work addresses this problem and proposes aframework for on-ramp scenario identification that also enables for scenariocategorization and assessment .…

A Scalable Algorithm for Decentralized Actor Termination Detection

Automatic garbage collection (GC) prevents certain kinds of bugs and reducesprogramming overhead . GC techniques for sequential programs are based onreachability analysis . However, testing reachability from a root set is inadequate for determining whether an actor is garbage . We present a low-overhead reference listing technique (called DRL) fortermination detection in actor systems .…

Combining exogenous and endogenous signals with a semi supervised co attention network for early detection of COVID 19 fake tweets

Fake tweets are observed to be ever-increasing, demanding immediatecountermeasures to combat their spread . During COVID-19, tweets withmisinformation should be flagged and neutralized in their early stages tomitigate the damages . ENDEMIC leverages exogenous and endogenous signals related to tweets, while learning on limited labeled data .…