arXiv subjects

Kevin Huang

Publications and source records attributed to Kevin Huang.

At least 55 records · Page 3Linked to original sources

arXiv2020

Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling

Document-level relation extraction (RE) poses new challenges compared to its sentence-level counterpart. One document commonly contains multiple entity pairs, and one entity pair occurs multiple times in the document associated with multiple possible relations. In this paper, we propose two novel techniques, adaptive thresholding and localized context pooling, to solve the multi-label and multi-entity problems. The adaptive thresholding replaces the global threshold for multi-label classification in the prior work with a learnable entities-dependent threshold. The localized context pooling directly transfers attention from pre-trained language models to locate relevant context that is useful to decide the relation. We experiment on three document-level RE benchmark datasets: DocRED, a recently released large-scale RE dataset, and two datasets CDRand GDA in the biomedical domain. Our ATLOP (Adaptive Thresholding and Localized cOntext Pooling) model achieves an F1 score of 63.4, and also significantly outperforms existing models on both CDR and GDA.

cs.CL↗

arXiv2020

Accelerating Road Sign Ground Truth Construction with Knowledge Graph and Machine Learning

Having a comprehensive, high-quality dataset of road sign annotation is critical to the success of AI-based Road Sign Recognition (RSR) systems. In practice, annotators often face difficulties in learning road sign systems of different countries; hence, the tasks are often time-consuming and produce poor results. We propose a novel approach using knowledge graphs and a machine learning algorithm - variational prototyping-encoder (VPE) - to assist human annotators in classifying road signs effectively. Annotators can query the Road Sign Knowledge Graph using visual attributes and receive closest matching candidates suggested by the VPE model. The VPE model uses the candidates from the knowledge graph and a real sign image patch as inputs. We show that our knowledge graph approach can reduce sign search space by 98.9%. Furthermore, with VPE, our system can propose the correct single candidate for 75% of signs in the tested datasets, eliminating the human search effort entirely in those cases.

cs.AI↗

arXiv2020

Entity and Evidence Guided Relation Extraction for DocRED

Document-level relation extraction is a challenging task which requires reasoning over multiple sentences in order to predict relations in a document. In this paper, we pro-pose a joint training frameworkE2GRE(Entity and Evidence Guided Relation Extraction)for this task. First, we introduce entity-guided sequences as inputs to a pre-trained language model (e.g. BERT, RoBERTa). These entity-guided sequences help a pre-trained language model (LM) to focus on areas of the document related to the entity. Secondly, we guide the fine-tuning of the pre-trained language model by using its internal attention probabilities as additional features for evidence prediction.Our new approach encourages the pre-trained language model to focus on the entities and supporting/evidence sentences. We evaluate our E2GRE approach on DocRED, a recently released large-scale dataset for relation extraction. Our approach is able to achieve state-of-the-art results on the public leaderboard across all metrics, showing that our E2GRE is both effective and synergistic on relation extraction and evidence prediction.

cs.CL↗

arXiv2020

Cubic Regularized Newton Method for Saddle Point Models: a Global and Local Convergence Analysis

In this paper, we propose a cubic regularized Newton (CRN) method for solving convex-concave saddle point problems (SPP). At each iteration, a cubic regularized saddle point subproblem is constructed and solved, which provides a search direction for the iterate. With properly chosen stepsizes, the method is shown to converge to the saddle point with global linear and local superlinear convergence rates, if the saddle point function is gradient Lipschitz and strongly-convex-strongly-concave. In the case that the function is merely convex-concave, we propose a homotopy continuation (or path-following) method. Under a Lipschitz-type error bound condition, we present an iteration complexity bound of $\mathcal{O}\left(\ln \left(1/ε\right)\right)$ to reach an $ε$-solution through a homotopy continuation approach, and the iteration complexity bound becomes $\mathcal{O}\left(\left(1/ε\right)^{\frac{1-θ}{θ^2}}\right)$ under a Hölderian-type error bound condition involving a parameter $θ$ ($0<θ<1$).

math.OC↗

arXiv2020

Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documents

Interpretable multi-hop reading comprehension (RC) over multiple documents is a challenging problem because it demands reasoning over multiple information sources and explaining the answer prediction by providing supporting evidences. In this paper, we propose an effective and interpretable Select, Answer and Explain (SAE) system to solve the multi-document RC problem. Our system first filters out answer-unrelated documents and thus reduce the amount of distraction information. This is achieved by a document classifier trained with a novel pairwise learning-to-rank loss. The selected answer-related documents are then input to a model to jointly predict the answer and supporting sentences. The model is optimized with a multi-task learning objective on both token level for answer prediction and sentence level for supporting sentences prediction, together with an attention-based interaction between these two tasks. Evaluated on HotpotQA, a challenging multi-hop RC data set, the proposed SAE system achieves top competitive performance in distractor setting compared to other existing systems on the leaderboard.

cs.CL↗

arXiv2019

Relation Module for Non-answerable Prediction on Question Answering

Machine reading comprehension(MRC) has attracted significant amounts of research attention recently, due to an increase of challenging reading comprehension datasets. In this paper, we aim to improve a MRC model's ability to determine whether a question has an answer in a given context (e.g. the recently proposed SQuAD 2.0 task). Our solution is a relation module that is adaptable to any MRC model. The relation module consists of both semantic extraction and relational information. We first extract high level semantics as objects from both question and context with multi-head self-attentive pooling. These semantic objects are then passed to a relation network, which generates relationship scores for each object pair in a sentence. These scores are used to determine whether a question is non-answerable. We test the relation module on the SQuAD 2.0 dataset using both BiDAF and BERT models as baseline readers. We obtain 1.8% gain of F1 on top of the BiDAF reader, and 1.0% on top of the BERT base model. These results show the effectiveness of our relation module on MRC

cs.CL↗

arXiv2019

Charge-stripe order, antiferromagnetism, and spin dynamics in the cuprate-analog nickelate La$_4$Ni$_3$O$_8$

We report a muon spin rotation ($μ$SR) study of the cuprate-analog nickelate La$_4$Ni$_3$O$_8$, which undergoes a transition at 105 K to a low-temperature phase with charge-stripe and antiferromagnetic (AFM) order on square planar NiO$_2$ layers. Zero-field $μ$SR shows that this transition is abrupt and that the AFM configuration is commensurate. Comparison of observed muon precession frequencies with Ni dipolar field calculations yields Ni moments $\lesssim 0.5μ_B$. Dynamic muon spin relaxation above 105 K suggests critical slowing of Ni spin fluctuations, but is inconsistent with corresponding $^{139}$La NMR results. Critical slowing and an abrupt transition are also observed in the planar cuprate AFM La$_2$CuO$_{4+δ}$, where they are evidence for weakly interplanar-coupled two-dimensional AFM spin fluctuations, but our $μ$SR data do not agree quantitatively with theoretical predictions for this scenario.

cond-mat.mtrl-sci↗

arXiv2019

The Materials Science Procedural Text Corpus: Annotating Materials Synthesis Procedures with Shallow Semantic Structures

Materials science literature contains millions of materials synthesis procedures described in unstructured natural language text. Large-scale analysis of these synthesis procedures would facilitate deeper scientific understanding of materials synthesis and enable automated synthesis planning. Such analysis requires extracting structured representations of synthesis procedures from the raw text as a first step. To facilitate the training and evaluation of synthesis extraction models, we introduce a dataset of 230 synthesis procedures annotated by domain experts with labeled graphs that express the semantics of the synthesis sentences. The nodes in this graph are synthesis operations and their typed arguments, and labeled edges specify relations between the nodes. We describe this new resource in detail and highlight some specific challenges to annotating scientific text with shallow semantic structure. We make the corpus available to the community to promote further research and development of scientific information extraction systems.

cs.CL↗

arXiv2019

Inorganic Materials Synthesis Planning with Literature-Trained Neural Networks

Leveraging new data sources is a key step in accelerating the pace of materials design and discovery. To complement the strides in synthesis planning driven by historical, experimental, and computed data, we present an automated method for connecting scientific literature to synthesis insights. Starting from natural language text, we apply word embeddings from language models, which are fed into a named entity recognition model, upon which a conditional variational autoencoder is trained to generate syntheses for arbitrary materials. We show the potential of this technique by predicting precursors for two perovskite materials, using only training data published over a decade prior to their first reported syntheses. We demonstrate that the model learns representations of materials corresponding to synthesis-related properties, and that the model's behavior complements existing thermodynamic knowledge. Finally, we apply the model to perform synthesizability screening for proposed novel perovskite compounds.

cond-mat.mtrl-sci↗

arXiv2019

Renormalizations in unconventional superconducting states of Ce$_{1-x}$Yb$_{x}$CoIn$_{5}$

We have measured the superconducting penetration depth~$Λ(T)$ in the heavy-fermion/intermediate-valent superconducting alloy series~Ce$_{1-x}$Yb$_x$CoIn$_5$ using transverse-field muon spin relaxation, to study the effect of intermediate-valent Yb doping on Fermi-liquid renormalization. From $Λ(T)$ we determine the superfluid density $ρ_s(T)$, and find that it decreases continuously with increasing nominal Yb concentration~$x$, i.e., with increasing intermediate valence. The temperature-dependent renormalization of the "normal" fluid density~$ρ_N(T) = ρ_s(0) - ρ_s(T)$ in both the heavy-fermion and intermediate valence limits is proportional to the temperature-dependent renormalization of the specific heat. This indicates that the temperature-dependent Fermi-liquid Landau parameters of the superconducting quasiparticles entering the two different physical quantities are the same. These results represent an important advance in understanding of both intermediate valence and heavy-fermion phenomena in superconductors.

cond-mat.str-el↗

arXiv2019

Broken time-reversal symmetry in superconducting Pr$_{1-x}$La$_{x}$Pt$_{4}$Ge$_{12}$

The superconducting state of the filled skutterudite alloy series Pr$_{1-x}$La$_{x}$Pt$_{4}$Ge$_{12}$ has been systematically studied by specific heat, zero-field muon spin relaxation ($μ$SR), and superconducting critical field measurements. An additional inhomogeneous local magnetic field, indicative of broken time-reversal symmetry (TRS), is observed in the superconducting states of the alloys. For $x \lesssim 0.5$ the broken-TRS phase sets in below a temperature $T_m$ distinctly lower than the superconducting transition temperature $T_c$. For $x \gtrsim 0.5$ $T_m \approx T_c$. The local field strength decreases as $x \to 1$, where LaPt$_{4}$Ge$_{12}$ is characterized by conventional pairing. The lower critical field $H_{c1}(T)$ of PrPt$_{4}$Ge$_{12}$ shows the onset of a second quadratic temperature region below $T_q \sim T_m$. Upper critical field $H_{c2}(T)$ measurements suggest multiband superconductivity, and point gap nodes are consistent with the specific heat data. In Pr$_{1-x}$La$_{x}$Pt$_{4}$Ge$_{12}$ only a single specific heat discontinuity is observed at $T_c$, in contrast to the second jump seen in PrOs$_{4}$Sb$_{12}$ below $T_c$. These results suggest that superconductivity in PrPt$_{4}$Ge$_{12}$ is characterized by a complex order parameter.

cond-mat.supr-con↗

arXiv2019

Quasiparticle Relaxation Dynamics in URu$_{2-x}$Fe$_{x}$Si$_{2}$ Single Crystals

We investigate quasiparticle relaxation dynamics in URu$_{2-x}$Fe$_{x}$Si$_{2}$ single crystals using ultrafast optical-pump optical-probe (OPOP) spectroscopy as a function of temperature ($T$) and Fe substitution ($x$), crossing from the hidden order (HO) phase ($x$ = 0) to the large moment antiferromagnet (LMAFM) phase ($x$ = 0.12). At low $T$, the dynamics for $x$ = 0 and $x$ = 0.12 are consistent with the low energy electronic structure of the HO and LMAFM phases that emerge from the high $T$ paramagnetic (PM) phase. In contrast, for $x$ = 0.1, two transitions occur over a narrow $T$ range (from ~15.5 - 17.5 K). A PM to HO transition occurs at an intermediate $T$ followed by a transition to the LMAFM phase at lower $T$. While the data at low $T$ are consistent with the expected coexistence of LMAFM and HO, the data in the intermediate $T$ phase are not, and instead suggest the possibility of an unexpected coexistence of HO and PM. Additionally, the dynamics in the PM phase reflect the presence of a hybridization gap as well as strongly interacting spin and charge degrees of freedom. OPOP yields insights into meV-scale electrodynamics with sub-Kelvin $T$ resolution, providing a complementary approach to study low energy electronic structure in quantum materials.

cond-mat.str-el↗

arXiv2018

ParaNet - Using Dense Blocks for Early Inference

DenseNets have been shown to be a competitive model among recent convolutional network architectures. These networks utilize Dense Blocks, which are groups of densely connected layers where the output of a hidden layer is fed in as the input of every other layer following it. In this paper, we aim to improve certain aspects of DenseNet, especially when it comes to practicality. We introduce ParaNet, a new architecture that constructs three pipelines which allow for early inference. We additionally introduce a cascading mechanism such that different pipelines are able to share parameters, as well as logit matching between the outputs of the pipelines. We separately evaluate each of the newly introduced mechanisms of ParaNet, then evaluate our proposed architecture on CIFAR-100.

cs.CV↗

arXiv2018

Anomalous quantum-critical spin dynamics in YFe2Al10

We report results of a muon spin relaxation ($μ$SR) study of YFe$_2$Al$_{10}$, a quasi-2D nearly-ferromagnetic metal in which unconventional quantum critical behavior is observed. No static Fe$^{2+}$ magnetism, with or without long-range order, is found down to 19~mK\@. The dynamic muon spin relaxation rate~$λ$ exhibits power-law divergences in temperature and magnetic field, the latter for fields that are too weak to affect the electronic spin dynamics directly. We attribute this to the proportionality of $λ(ω_μ,T)$ to the dynamic structure factor~$S(ω_μ,T)$, where $ω_μ\approx 10^5$--$10^7~\mathrm{s}^{-1}$ is the muon Zeeman frequency. These results suggest critical divergences of $S(ω_μ,T)$ in both temperature and frequency. Power-law scaling and a 2D dissipative quantum XY (2D-DQXY) model both yield forms for $S(ω,T)$ that agree with neutron scattering data ($ω\approx 10^{12}~\mathrm{s}^{-1}$). Extrapolation to $μ$SR frequencies agrees semi-quantitatively with the observed temperature dependence of $λ(ω_μ,T)$, but predicts frequency independence for $ω_μ\ll T$ in extreme disagreement with experiment. We conclude that the quantum critical spin dynamics of YFe$_2$Al$_{10}$ are not well understood at low frequencies.

cond-mat.str-el↗

arXiv2018

Nodal superconductivity coexists with low-moment static magnetism in single-crystalline tetragonal FeS: A muon spin relaxation and rotation study

We report muon spin relaxation and rotation ($μ$SR) measurements on hydrothermally-grown single crystals of the tetragonal superconductor~FeS, which help to clarify the controversial magnetic state and superconducting gap symmetry of this compound. $μ$SR time spectra were obtained from 280~K down to 0.025~K in zero field (ZF) and applied fields up to 20 mT. In ZF the observed loss of initial asymmetry (signal amplitude) and increase of depolarization rate~$Λ_\mathrm{ZF}$ below 10~K indicate the onset of static magnetism, which coexists with superconductivity below $T_c$. Transverse-field $μ$SR yields a muon depolarization rate $σ_\mathrm{sc} \propto λ_{ab}^{-2}$ that clearly shows a linear dependence at low temperature, consistent with nodal superconductivity. The $s{+}d$-wave model gives the best fit to the observed temperature and field dependencies. The normalized superfluid densities versus normalized temperature for different fields collapse onto the same curve, indicating the superconducting gap structure is independent of field. The $T=0$ in-plane penetration depth $λ_{ab}$(0) = 198(3) nm.

cond-mat.supr-con↗

arXiv2017

Stretching Epitaxial La0.6Sr0.4CoO3-δ for Fast Oxygen Reduction

The slow kinetics of the oxygen reduction reaction (ORR) is one of the key challenges in developing high performance energy devices, such as solid oxide fuel cells. Straining a film by growing on a lattice-mismatched substrate has been a conventional approach to enhance the ORR activity. However, due to the limited choice of electrolyte substrates to alter the degree of strain, a systematic study in various materials has been a challenge. Here, we explore the strain modulation of the ORR kinetics by growing epitaxial La0.6Sr0.4CoO3-δ (LSCO) films on yttria-stabilized zirconia substrates with the film thickness below and above the critical thickness for strain relaxation. Two orders of magnitude higher ORR kinetics is achieved in an ultra-thin film with ~0.8% tensile strain as compared to unstrained films. Time-of-flight secondary ion mass spectrometry depth profiling confirms that the Sr surface segregation is not responsible for the enhanced ORR in strained films. We attribute this enhancement of ORR kinetics to the increase in oxygen vacancy concentration in the tensile-strained LSCO film owing to the reduced activation barrier for oxygen surface exchange kinetics. Density functional theory calculations reveal an upshift of the oxygen 2p-band center relative to the Fermi level by tensile strain, indicating the origin of the enhanced ORR kinetics.

cond-mat.mtrl-sci↗

arXiv2017

Automatically Extracting Action Graphs from Materials Science Synthesis Procedures

Computational synthesis planning approaches have achieved recent success in organic chemistry, where tabulated synthesis procedures are readily available for supervised learning. The syntheses of inorganic materials, however, exist primarily as natural language narratives contained within scientific journal articles. This synthesis information must first be extracted from the text in order to enable analogous synthesis planning methods for inorganic materials. In this work, we present a system for automatically extracting structured representations of synthesis procedures from the texts of materials science journal articles that describe explicit, experimental syntheses of inorganic compounds. We define the structured representation as a set of linked events made up of extracted scientific entities and evaluate two unsupervised approaches for extracting these structures on expert-annotated articles: a strong heuristic baseline and a generative model of procedural text. We also evaluate a variety of supervised models for extracting scientific entities. Our results provide insight into the nature of the data and directions for further work in this exciting new area of research.

cs.CL↗

arXiv2017

Investigation of the complex magnetism in the breathing pyrochlore LiIn(Cr$_{1-x}$Rh$_x$)$_4$O$_8$

We have performed a detailed investigation of the new `breathing' pyrochlore compound LiInCr$_4$O$_8$ through Rh substitution with measurements of magnetic susceptibility, specific heat, and x-ray powder diffraction. The antiferromagnetic phase of LiInCr$_4$O$_8$ is found to be slowly suppressed with increasing Rh, up to the critical concentration of $x$ = 0.1 where the antiferromagnetic phase is still observed with the peak in specific heat $T_p$ = 12.5 K, slightly lower than $T_p$ = 14.3 K for the $x$ = 0 compound. From the measurements of magnetization we also uncover evidence that substitution increases the amount of frustration. Comparisons are made with the LiGa$_y$In$_{1-y}$Cr$_4$O$_8$ system as well as other frustrated pyrochlore-related materials and find comparable amounts of frustration. The results of this work shows that engineered breathing pyrochlores presents an important method to further understand the complex magnetism in frustrated systems.

cond-mat.str-el↗