Search

Distance based knowledge graph embedding methods show promising results on link prediction task, on which two topics have been widely studied: one is the ability to handle complex relations, such as N-to-1, 1-to-N and N-to-N, the other is to encode various relation patterns, such as symmetry/antisymmetry. However, the existing methods fail to solve these two problems at the same time, which leads to unsatisfactory results. To mitigate this problem, we propose PairRE, a model with paired vectors for each relation representation. The paired vectors enable an adaptive adjustment of the margin in loss function to fit for complex relations. Besides, PairRE is capable of encoding three important relation patterns, symmetry/antisymmetry, inverse and composition. Given simple constraints on relation representations, PairRE can encode subrelation further. Experiments on link prediction benchmarks demonstrate the proposed key capabilities of PairRE. Moreover, We set a new state-of-the-art on two knowledge graph datasets of the challenging Open Graph Benchmark.

We propose a CTC alignment-based single step non-autoregressive transformer (CASS-NAT) for speech recognition. Specifically, the CTC alignment contains the information of (a) the number of tokens for decoder input, and (b) the time span of acoustics for each token. The information are used to extract acoustic representation for each token in parallel, referred to as token-level acoustic embedding which substitutes the word embedding in autoregressive transformer (AT) to achieve parallel generation in decoder. During inference, an error-based alignment sampling method is proposed to be applied to the CTC output space, reducing the WER and retaining the parallelism as well. Experimental results show that the proposed method achieves WERs of 3.8%/9.1% on Librispeech test clean/other dataset without an external LM, and a CER of 5.8% on Aishell1 Mandarin corpus, respectively1. Compared to the AT baseline, the CASS-NAT has a performance reduction on WER, but is 51.2x faster in terms of RTF. When decoding with an oracle CTC alignment, the lower bound of WER without LM reaches 2.3% on the test-clean set, indicating the potential of the proposed method., Comment: Accepted to ICASSP2021, camera ready version

We demonstrate a C-band wavelength-tunable microlaser with an Er3+ doped high quality (~1.02x10^6) lithium niobate microdisk resonator. With a 976 nm continuous-wave pump laser, lasing action can be observed at a pump power threshold as low as ~250 {\mu}W at room temperature. Furthermore, the microdisk laser wavelength can be tuned by varying the pump laser power, showing a tuning efficiency of ~-17.03 pm/mW at low pump power blow 13 mW, and 10.58 pm/mW at high pump power above 13 mW.

Numerical reasoning over texts, such as addition, subtraction, sorting and counting, is a challenging machine reading comprehension task, since it requires both natural language understanding and arithmetic computation. To address this challenge, we propose a heterogeneous graph representation for the context of the passage and question needed for such reasoning, and design a question directed graph attention network to drive multi-step numerical reasoning over this context graph. The code link is at: https://github.com/emnlp2020qdgat/QDGAT, Comment: Accepted at EMNLP 2020

In this paper, We propose a general Riemannian proximal optimization algorithm with guaranteed convergence to solve Markov decision process (MDP) problems. To model policy functions in MDP, we employ Gaussian mixture model (GMM) and formulate it as a nonconvex optimization problem in the Riemannian space of positive semidefinite matrices. For two given policy functions, we also provide its lower bound on policy improvement by using bounds derived from the Wasserstein distance of GMMs. Preliminary experiments show the efficacy of our proposed Riemannian proximal policy optimization algorithm., Comment: 12 pages, 1 figures

We report fabrication of low loss single mode waveguides on lithium niobate on insulator (LNOI) cladded by a layer of SiO2. Our technique, termed photolithography assisted chemo-mechanical etching (PLACE), relies on patterning of a chromium film into the mask shape by femtosecond laser micromachining and subsequent chemo-mechanical etching of the lithium niobate thin film. The high-index-contrast single mode waveguide is measured to have a propagation loss of 0.13 dB/cm. Furthermore, waveguide tapers are fabricated for boosting the coupling efficiency., Comment: 4 pages, 5 figures

Chinese Spelling Check (CSC) is a task to detect and correct spelling errors in Chinese natural language. Existing methods have made attempts to incorporate the similarity knowledge between Chinese characters. However, they take the similarity knowledge as either an external input resource or just heuristic rules. This paper proposes to incorporate phonological and visual similarity knowledge into language models for CSC via a specialized graph convolutional network (SpellGCN). The model builds a graph over the characters, and SpellGCN is learned to map this graph into a set of inter-dependent character classifiers. These classifiers are applied to the representations extracted by another network, such as BERT, enabling the whole network to be end-to-end trainable. Experiments (The dataset and all code for this paper are available at https://github.com/ACL2020SpellGCN/SpellGCN) are conducted on three human-annotated datasets. Our method achieves superior performance against previous models by a large margin., Comment: Accepted by ACL2020

We propose a \emph{collaborative} multi-agent reinforcement learning algorithm named variational policy propagation (VPP) to learn a \emph{joint} policy through the interactions over agents. We prove that the joint policy is a Markov Random Field under some mild conditions, which in turn reduces the policy space effectively. We integrate the variational inference as special differentiable layers in policy such that the actions can be efficiently sampled from the Markov Random Field and the overall policy is differentiable. We evaluate our algorithm on several large scale challenging tasks and demonstrate that it outperforms previous state-of-the-arts., Comment: The title of previous version was "Intention Propagation for Multi-agent Reinforcement Learning"

In the past two decades, tremendous efforts have been exerted to understand and control the delivery of ultrashort laser pulses into various types of transparent materials ranging from glass and crystal to polymer and even bio-materials. This approach opens up the route toward determinative and highly localized modification within the transparent materials, enabling three-dimensional (3D) micromachining of the materials into sophisticated structures and devices with the extreme geometrical flexibility. Owing to the linear diffraction and nonlinear self-focusing effects, the focal volume typically exhibits an asymmetric profile stretching along the longitudinal direction. This effect becomes more severe when focusing deeply into the transparent substrates for printing objects of large heights. In this work a new laser-material interaction regime is identified with the exceptional incubation effect originating from self-regulated multiple-pulse interactions with accumulated material changes. Our finding reveals a focal-volume-invariant modification deeply inside the fused silica glass, in striking contrary to the traditional believes that the geometrical shape of the laser induced modification follows the intensity distribution of the inscription laser. A macro-scale geometrically complex glass sculpture is successfully manufactured with the incubation assisted ultrashort laser inscription at uniform micrometer resolutions in all three dimensions., Comment: 16 pages, 5 figures

We achieve very efficient deep learning model deployment that designs neural network architectures to fit different hardware constraints. Given a constraint, most neural architecture search (NAS) methods either sample a set of sub-networks according to a pre-trained accuracy predictor, or adopt the evolutionary algorithm to evolve specialized networks from the supernet. Both approaches are time consuming. Here our key idea for very efficient deployment is, when searching the architecture space, constructing a table that stores the validation accuracy of all candidate blocks at all layers. For a stricter hardware constraint, the architecture of a specialized network can be very efficiently determined based on this table by picking the best candidate blocks that yield the least accuracy loss. To accomplish this idea, we propose Progressive One-shot Neural Architecture Search (PONAS) that combines advantages of progressive NAS and one-shot methods. In PONAS, we propose a two-stage training scheme, including the meta training stage and the fine-tuning stage, to make the search process efficient and stable. During search, we evaluate candidate blocks in different layers and construct the accuracy table that is to be used in deployment. Comprehensive experiments verify that PONAS is extremely flexible, and is able to find architecture of a specialized network in around 10 seconds. In ImageNet classification, 75.2% top-1 accuracy can be obtained, which is comparable with the state of the arts.

We report generation of cascaded rotational Raman scattering up to 58th orders in coherently excited CO_2 molecules. The high-order Raman scattering, which produces a quasiperiodic frequency comb with more than 600 sidebands, is obtained using an intense femtosecond laser to impulsively excite rotational coherence and the femtosecond-laser-induced N_2^+ lasing to generate cascaded Raman signals. The novel configuration allows this experiment to be performed with a single femtosecond laser beam at free-space standoff locations. It is revealed that the efficient spectral extension of Raman signals is attributed to the specific spectra-temporal structures of N_2^+ lasing, the ideal spatial overlap of femtosecond laser and N2+ lasing, and the guiding effect of molecular alignment. The Raman spectrum extending above 2000 cm^-1 naturally corresponds to a femtosecond pulse train due to the periodic revivals of molecular rotational wavepackets., Comment: 17 pages, 4 figures

Recent reports of a large anomalous Hall effect (AHE) in ferromagnetic Weyl semimetals (FM WSM) have led to a resurgence of interest in this enigmatic phenomenon. However, due to a lack of tunable materials, the interplay between the intrinsic mechanism caused by Berry curvature and extrinsic mechanisms due to scattering remains unclear in FM WSMs. In this contribution, we present a thorough investigation of both the extrinsic and intrinsic AHE in a new family of FM WSMs, PrAlGe$_{1-x}$Si$_x$, where $x$ can be tuned continuously. From DFT calculations, we show that the two end members, PrAlGe and PrAlSi, have different Fermi surfaces but similar Weyl node structures. Experimentally, we observe moderate changes in the anomalous Hall coefficient ($R_S$) but significant changes in the ordinary Hall coefficient ($R_0$) in PrAlGe$_{1-x}$Si$_x$ as a function of $x$, confirming a change of Fermi surface. By comparing the magnitude of $R_0$ and $R_S$, we identify two regimes; $|R_0|<|R_S|$ when $x\le0.5$ and $|R_0|>|R_S|$ when $x>0.5$. Through a detailed scaling analysis, we discover a universal anomalous Hall conductivity (AHC) from intrinsic contribution when $x\le0.5$. Such universal AHC is absent when $x>0.5$. Thus, we point out the significance of the extrinsic mechanisms in FM WSMs and report the first observation of a transition from intrinsic to extrinsic AHE in PrAlGe$_{1-x}$Si$_x$., Comment: 11 pages, 11 figure, 3 tables

Large-scale microfluidic microsystems with complex three-dimensional (3D) configurations are highly in demand by both fundamental research and industrial application, holding the potentials for fostering a wide range of innovative applications such as lab-on-a-chip and organ-on-a-chip as well as continuous-flow manufacturing of fine chemicals. However, freeform fabrication of such systems remains challenging for most of the current fabrication techniques in terms of fabrication resolution, flexibility, and achievable footprint size. Here, we report ultrashort pulse laser microfabrication of freeform microfluidic circuits with high aspect ratios and tunable diameters embedded in 3D printed glass objects. We achieve uniform microfluidic channel diameter by carefully distributing a string of extra access ports along the microfluidic channels for avoiding the over-etching in the thin microfluidic channels. After the chemical etching is completed, the extra access ports are sealed using carbon dioxide laser induced localized glass melting. We demonstrate a model hand of fused silica with a size of ~3 cm * 2.7 cm * 1.1 cm in which the whole blood vessel system is encapsulated., Comment: 27 pages, 5 figures

Microfluidic mixing is a fundamental functionality in most lab on a chip (LOC) systems,whereas realization of efficient mixing is challenging in microfluidic channels due to the small Reynolds numbers. Here, we design and fabricate a compact three-dimensional (3D) micromixer to enable efficient mixing at various flow rates. The performance of the fabricated micromixer was examined using blue and red inks. The extreme flexibility in fabricating microfluidic structures of arbitrary 3D geometries using femtosecond laser micromachining allows us to tackle the major disadvantageous effects for optimizing the mixing efficiency., Comment: 18 pages, 5 figures

The ability of semantic reasoning over the sentence pair is essential for many natural language understanding tasks, e.g., natural language inference and machine reading comprehension. A recent significant improvement in these tasks comes from BERT. As reported, the next sentence prediction (NSP) in BERT, which learns the contextual relationship between two sentences, is of great significance for downstream problems with sentence-pair input. Despite the effectiveness of NSP, we suggest that NSP still lacks the essential signal to distinguish between entailment and shallow correlation. To remedy this, we propose to augment the NSP task to a 3-class categorization task, which includes a category for previous sentence prediction (PSP). The involvement of PSP encourages the model to focus on the informative semantics to determine the sentence order, thereby improves the ability of semantic understanding. This simple modification yields remarkable improvement against vanilla BERT. To further incorporate the document-level information, the scope of NSP and PSP is expanded into a broader range, i.e., NSP and PSP also include close but nonsuccessive sentences, the noise of which is mitigated by the label-smoothing technique. Both qualitative and quantitative experimental results demonstrate the effectiveness of the proposed method. Our method consistently improves the performance on the NLI and MRC benchmarks, including the challenging HANS dataset \cite{hans}, suggesting that the document-level task is still promising for the pre-training., Comment: 8 pages, 3 figures, 6 tables

We demonstrate efficient tuning of a monolithically integrated lithium niobate microdisk (LN) optical frequency microcomb. Utilizing the high optical quality (Q) factor (i.e., Q~7.1*10^6) of the microdisk, the microcomb spans over a spectral bandwidth of ~200 nm at a pump power as low as 20.4 mW. Combining the large eletro-optic coefficient of LN and optimum design of the geometry of microelectrodes, we demonstrate electro-optical tuning of the comb with a spectral range of 400 pm and a tuning efficiency of ~38 pm/100V.

In this paper, we report our method for the Information Extraction task in 2019 Language and Intelligence Challenge. We incorporate BERT into the multi-head selection framework for joint entity-relation extraction. This model extends existing approaches from three perspectives. First, BERT is adopted as a feature extraction layer at the bottom of the multi-head selection framework. We further optimize BERT by introducing a semantic-enhanced task during BERT pre-training. Second, we introduce a large-scale Baidu Baike corpus for entity recognition pre-training, which is of weekly supervised learning since there is no actual named entity label. Third, soft label embedding is proposed to effectively transmit information between entity recognition and relation extraction. Combining these three contributions, we enhance the information extracting ability of the multi-head selection model and achieve F1-score 0.876 on testset-1 with a single model. By ensembling four variants of our model, we finally achieve F1 score 0.892 (1st place) on testset-1 and F1 score 0.8924 (2nd place) on testset-2., Comment: To appear at NLPCC 2019

Topological Dirac and Weyl semimetals, which support low-energy quasiparticles in condensed matter physics, are currently attracting intense interest due to exotic physical properties such as large magnetoresistance and high carrier mobilities. Transition metal diarsenides such as MoAs2 and WAs2 have been reported to harbor very high magnetoresistance suggesting the possible existence of a topological quantum state, although this conclusion remains dubious. Here, based on systematic angle-resolved photoemission spectroscopy (ARPES) measurements and parallel first-principles calculations, we investigate the electronic properties of TAs2 (T = Mo, W). Importantly, clear evidence for switching the single-Dirac cone surface state in MoAs2 with the cleaving plane is observed, whereas a Dirac state is not observed in WAs2 despite its high magnetoresistance. Our study thus reveals the key role of the terminated plane in a low-symmetry system, and provides a new perspective on how termination can drive dramatic changes in electronic structures., Comment: 8 pages, 4 figures

We report fabrication of a multifunctional photonic integrated chip on lithium niobate on insulate (LNOI), which is achieved by femtosecond laser assisted chemo-mechanical polish. We demonstrate a high extinction ratio beam splitter, a 1 * 6 optical switch, and a balanced 3 * 3 interferometer on the fabricated chip by reconfiguring the microelectrode array integrated with the multifunctional photonic circuit., Comment: 6 pages, 5 figures

We demonstrate fabrication of single-mode optical waveguides on lithium niobate on insulator (LNOI) by optical patterning combined with chemo-mechanical polishing. The fabricated LNOI waveguides have a nearly symmetric mode profile of a mode field size of ~2.5 micron (full-width at half maximum). We develop a high-precision measurement approach by which the single mode waveguides are characterized to have a propagation loss of ~0.042 dB/cm., Comment: 4 pages, 5 figures

The ambiguous annotation criteria lead to divergence of Chinese Word Segmentation (CWS) datasets in various granularities. Multi-criteria Chinese word segmentation aims to capture various annotation criteria among datasets and leverage their common underlying knowledge. In this paper, we propose a domain adaptive segmenter to exploit diverse criteria of various datasets. Our model is based on Bidirectional Encoder Representations from Transformers (BERT), which is responsible for introducing open-domain knowledge. Private and shared projection layers are proposed to capture domain-specific knowledge and common knowledge, respectively. We also optimize computational efficiency via distillation, quantization, and compiler optimization. Experiments show that our segmenter outperforms the previous state of the art (SOTA) models on 10 CWS datasets with superior efficiency., Comment: Accepted at COLING 2020