arXiv subjects

Dong Yu

Publications and source records attributed to Dong Yu.

At least 397 records · Page 22Linked to original sources

arXiv2019

Improving Machine Reading Comprehension with General Reading Strategies

Reading strategies have been shown to improve comprehension levels, especially for readers lacking adequate prior knowledge. Just as the process of knowledge accumulation is time-consuming for human readers, it is resource-demanding to impart rich general domain knowledge into a deep language model via pre-training. Inspired by reading strategies identified in cognitive science, and given limited computational resources -- just a pre-trained model and a fixed number of training instances -- we propose three general strategies aimed to improve non-extractive machine reading comprehension (MRC): (i) BACK AND FORTH READING that considers both the original and reverse order of an input sequence, (ii) HIGHLIGHTING, which adds a trainable embedding to the text embedding of tokens that are relevant to the question and candidate answers, and (iii) SELF-ASSESSMENT that generates practice questions and candidate answers directly from the text in an unsupervised manner. By fine-tuning a pre-trained language model (Radford et al., 2018) with our proposed strategies on the largest general domain multiple-choice MRC dataset RACE, we obtain a 5.8% absolute increase in accuracy over the previous best result achieved by the same pre-trained model fine-tuned on RACE without the use of strategies. We further fine-tune the resulting model on a target MRC task, leading to an absolute improvement of 6.2% in average accuracy over previous state-of-the-art approaches on six representative non-extractive MRC datasets from different domains (i.e., ARC, OpenBookQA, MCTest, SemEval-2018 Task 11, ROCStories, and MultiRC). These results demonstrate the effectiveness of our proposed strategies and the versatility and general applicability of our fine-tuned models that incorporate these strategies. Core code is available at https://github.com/nlpdata/strategy/.

cs.CL↗

arXiv2019

Nanomechanical characterization of quantum interference in a topological insulator nanowire

The discovery of two-dimensional gapless Dirac fermions in graphene and topological insulators (TI) has sparked extensive ongoing research toward applications of their unique electronic properties. The gapless surface states in three-dimensional insulators indicate a distinct topological phase of matter with a non-trivial Z2 invariant that can be verified by angle-resolved photoemission spectroscopy or magnetoresistance quantum oscillation. In TI nanowires, the gapless surface states exhibit Aharonov-Bohm (AB) oscillations in conductance, with this quantum interference effect accompanying a change in the number of transverse one-dimensional modes in transport. Thus, while the density of states (DOS) of such nanowires is expected to show such AB oscillation, this effect has yet to be observed. Here, we adopt nanomechanical measurements that reveal AB oscillations in the DOS of a topological insulator. The TI nanowire under study is an electromechanical resonator embedded in an electrical circuit, and quantum capacitance effects from DOS oscillation modulate the circuit capacitance thereby altering the spring constant to generate mechanical resonant frequency shifts. Detection of the quantum capacitance effects from surface-state DOS is facilitated by the small effective capacitances and high quality factors of nanomechanical resonators, and as such the present technique could be extended to study diverse quantum materials at nanoscale.

cond-mat.mes-hall↗

arXiv2019

DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehension

We present DREAM, the first dialogue-based multiple-choice reading comprehension dataset. Collected from English-as-a-foreign-language examinations designed by human experts to evaluate the comprehension level of Chinese learners of English, our dataset contains 10,197 multiple-choice questions for 6,444 dialogues. In contrast to existing reading comprehension datasets, DREAM is the first to focus on in-depth multi-turn multi-party dialogue understanding. DREAM is likely to present significant challenges for existing reading comprehension systems: 84% of answers are non-extractive, 85% of questions require reasoning beyond a single sentence, and 34% of questions also involve commonsense knowledge. We apply several popular neural reading comprehension models that primarily exploit surface information within the text and find them to, at best, just barely outperform a rule-based approach. We next investigate the effects of incorporating dialogue structure and different kinds of general world knowledge into both rule-based and (neural and non-neural) machine learning-based reading comprehension models. Experimental results on the DREAM dataset show the effectiveness of dialogue structure and general world knowledge. DREAM will be available at https://dataset.org/dream/.

cs.CL↗

arXiv2019

From Plots to Endings: A Reinforced Pointer Generator for Story Ending Generation

We introduce a new task named Story Ending Generation (SEG), whic-h aims at generating a coherent story ending from a sequence of story plot. Wepropose a framework consisting of a Generator and a Reward Manager for thistask. The Generator follows the pointer-generator network with coverage mech-anism to deal with out-of-vocabulary (OOV) and repetitive words. Moreover, amixed loss method is introduced to enable the Generator to produce story endingsof high semantic relevance with story plots. In the Reward Manager, the rewardis computed to fine-tune the Generator with policy-gradient reinforcement learn-ing (PGRL). We conduct experiments on the recently-introduced ROCStoriesCorpus. We evaluate our model in both automatic evaluation and human evalua-tion. Experimental results show that our model exceeds the sequence-to-sequencebaseline model by 15.75% and 13.57% in terms of CIDEr and consistency scorerespectively.

cs.CL↗

arXiv2019

DEMN: Distilled-Exposition Enhanced Matching Network for Story Comprehension

This paper proposes a Distilled-Exposition Enhanced Matching Network (DEMN) for story-cloze test, which is still a challenging task in story comprehension. We divide a complete story into three narrative segments: an \textit{exposition}, a \textit{climax}, and an \textit{ending}. The model consists of three modules: input module, matching module, and distillation module. The input module provides semantic representations for the three segments and then feeds them into the other two modules. The matching module collects interaction features between the ending and the climax. The distillation module distills the crucial semantic information in the exposition and infuses it into the matching module in two different ways. We evaluate our single and ensemble model on ROCStories Corpus \cite{Mostafazadeh2016ACA}, achieving an accuracy of 80.1\% and 81.2\% on the test set respectively. The experimental results demonstrate that our DEMN model achieves a state-of-the-art performance.

cs.CL↗

arXiv2019

Multi-Perspective Fusion Network for Commonsense Reading Comprehension

Commonsense Reading Comprehension (CRC) is a significantly challenging task, aiming at choosing the right answer for the question referring to a narrative passage, which may require commonsense knowledge inference. Most of the existing approaches only fuse the interaction information of choice, passage, and question in a simple combination manner from a \emph{union} perspective, which lacks the comparison information on a deeper level. Instead, we propose a Multi-Perspective Fusion Network (MPFN), extending the single fusion method with multiple perspectives by introducing the \emph{difference} and \emph{similarity} fusion\deleted{along with the \emph{union}}. More comprehensive and accurate information can be captured through the three types of fusion. We design several groups of experiments on MCScript dataset \cite{Ostermann:LREC18:MCScript} to evaluate the effectiveness of the three types of fusion respectively. From the experimental results, we can conclude that the difference fusion is comparable with union fusion, and the similarity fusion needs to be activated by the union fusion. The experimental result also shows that our MPFN model achieves the state-of-the-art with an accuracy of 83.52\% on the official test set.

cs.CL↗

arXiv2019

Multi-turn Inference Matching Network for Natural Language Inference

Natural Language Inference (NLI) is a fundamental and challenging task in Natural Language Processing (NLP). Most existing methods only apply one-pass inference process on a mixed matching feature, which is a concatenation of different matching features between a premise and a hypothesis. In this paper, we propose a new model called Multi-turn Inference Matching Network (MIMN) to perform multi-turn inference on different matching features. In each turn, the model focuses on one particular matching feature instead of the mixed matching feature. To enhance the interaction between different matching features, a memory component is employed to store the history inference information. The inference of each turn is performed on the current matching feature and the memory. We conduct experiments on three different NLI datasets. The experimental results show that our model outperforms or achieves the state-of-the-art performance on all the three datasets.

cs.CL↗

arXiv2018

Unsupervised Speech Recognition via Segmental Empirical Output Distribution Matching

We consider the problem of training speech recognition systems without using any labeled data, under the assumption that the learner can only access to the input utterances and a phoneme language model estimated from a non-overlapping corpus. We propose a fully unsupervised learning algorithm that alternates between solving two sub-problems: (i) learn a phoneme classifier for a given set of phoneme segmentation boundaries, and (ii) refining the phoneme boundaries based on a given classifier. To solve the first sub-problem, we introduce a novel unsupervised cost function named Segmental Empirical Output Distribution Matching, which generalizes the work in (Liu et al., 2017) to segmental structures. For the second sub-problem, we develop an approximate MAP approach to refining the boundaries obtained from Wang et al. (2017). Experimental results on TIMIT dataset demonstrate the success of this fully unsupervised phoneme recognition system, which achieves a phone error rate (PER) of 41.6%. Although it is still far away from the state-of-the-art supervised systems, we show that with oracle boundaries and matching language model, the PER could be improved to 32.5%.This performance approaches the supervised system of the same model architecture, demonstrating the great potential of the proposed method.

eess.AS↗

arXiv2018

A Comparison of Lattice-free Discriminative Training Criteria for Purely Sequence-Trained Neural Network Acoustic Models

In this work, three lattice-free (LF) discriminative training criteria for purely sequence-trained neural network acoustic models are compared on LVCSR tasks, namely maximum mutual information (MMI), boosted maximum mutual information (bMMI) and state-level minimum Bayes risk (sMBR). We demonstrate that, analogous to LF-MMI, a neural network acoustic model can also be trained from scratch using LF-bMMI or LF-sMBR criteria respectively without the need of cross-entropy pre-training. Furthermore, experimental results on Switchboard-300hrs and Switchboard+Fisher-2100hrs datasets show that models trained with LF-bMMI consistently outperform those trained with plain LF-MMI and achieve a relative word error rate (WER) reduction of 5% over competitive temporal convolution projected LSTM (TDNN-LSTMP) LF-MMI baselines.

cs.LG↗

arXiv2018

Emergence of excitonic superfluid at topological-insulator surfaces

Excitons are spin integer particles that are predicted to condense into a coherent quantum state at sufficiently low temperature, and exciton condensates can be realized at much higher temperature than condensates of atoms because of strong Coulomb binding and small mass. Signatures of exciton condensation have been reported in double quantum wells1-4, microcavities5, graphene6, and transition metal dichalcogenides7. Nonetheless, transport of exciton condensates is not yet understood and it is unclear whether an exciton condensate is a superfluid8,9 or an insulating electronic crystal10,11. Topological insulators (TIs) with massless particles and unique spin textures12 have been theoretically predicted13 as a promising platform for achieving exciton condensation. Here we report experimental evidence of excitonic superfluid phase on the surface of three-dimensional (3D) TIs. We unambiguously confirmed that electrons and holes are paired into charge neutral bound states by the electric field independent photocurrent distributions. And we observed a millimetre-long transport distance of these excitons up to 40 K, which strongly suggests dissipationless propagation. The robust macroscopic quantum states achieved with simple device architecture and broadband photoexcitation at relatively high temperature are expected to find novel applications in quantum computations and spintronics.

cond-mat.mes-hall↗

arXiv2018

Robust Neural Abstractive Summarization Systems and Evaluation against Adversarial Information

Sequence-to-sequence (seq2seq) neural models have been actively investigated for abstractive summarization. Nevertheless, existing neural abstractive systems frequently generate factually incorrect summaries and are vulnerable to adversarial information, suggesting a crucial lack of semantic understanding. In this paper, we propose a novel semantic-aware neural abstractive summarization model that learns to generate high quality summaries through semantic interpretation over salient content. A novel evaluation scheme with adversarial samples is introduced to measure how well a model identifies off-topic information, where our model yields significantly better performance than the popular pointer-generator summarizer. Human evaluation also confirms that our system summaries are uniformly more informative and faithful as well as less redundant than the seq2seq model.

cs.CL↗

arXiv2018

XL-NBT: A Cross-lingual Neural Belief Tracking Framework

Task-oriented dialog systems are becoming pervasive, and many companies heavily rely on them to complement human agents for customer service in call centers. With globalization, the need for providing cross-lingual customer support becomes more urgent than ever. However, cross-lingual support poses great challenges---it requires a large amount of additional annotated data from native speakers. In order to bypass the expensive human annotation and achieve the first step towards the ultimate goal of building a universal dialog system, we set out to build a cross-lingual state tracking framework. Specifically, we assume that there exists a source language with dialog belief tracking annotations while the target languages have no annotated dialog data of any form. Then, we pre-train a state tracker for the source language as a teacher, which is able to exploit easy-to-access parallel data. We then distill and transfer its own knowledge to the student state tracker in target languages. We specifically discuss two types of common parallel resources: bilingual corpus and bilingual dictionary, and design different transfer learning strategies accordingly. Experimentally, we successfully use English state tracker as the teacher to transfer its knowledge to both Italian and German trackers and achieve promising results.

cs.CL↗

arXiv2018

Observation of anomalous π modes in photonic Floquet engineering

Recent progresses on Floquet topological phases have shed new light on time-dependant quantum systems, among which one-dimensional (1D) Floquet systems have been under extensive theoretical research. However, an unambiguous experimental observation of these 1D Floquet topological phases has still been lacking. Here, by periodically bending ultrathin metallic arrays of coupled corrugated waveguides, a photonic Floquet simulator was well designed and successfully fabricated to simulate the periodically driven Su-Schrieffer-Heeger model. Intriguingly, under moderate driven frequencies, we first experimentally observed and theoretically verified the Floquet topological $π$ mode propagating along the array's boundary. The different evolutionary behaviors between static and non-static topological end modes have also been clearly demonstrated. Our experiment also reveals the universal high-frequency behavior in perically driven systems. We emphasize that, our system can serve as a powerful and versatile testing ground for various phenomena related to time-dependant 1D quantum phases, such as Thouless charge pumping and manybody localization.

quant-ph↗

arXiv2018

Deep Extractor Network for Target Speaker Recovery From Single Channel Speech Mixtures

Speaker-aware source separation methods are promising workarounds for major difficulties such as arbitrary source permutation and unknown number of sources. However, it remains challenging to achieve satisfying performance provided a very short available target speaker utterance (anchor). Here we present a novel "deep extractor network" which creates an extractor point for the target speaker in a canonical high dimensional embedding space, and pulls together the time-frequency bins corresponding to the target speaker. The proposed model is different from prior works in that the canonical embedding space encodes knowledges of both the anchor and the mixture during an end-to-end training phase: First, embeddings for the anchor and mixture speech are separately constructed in a primary embedding space, and then combined as an input to feed-forward layers to transform to a canonical embedding space which we discover more stable than the primary one. Experimental results show that given a very short utterance, the proposed model can efficiently recover high quality target speech from a mixture, which outperforms various baseline models, with 5.2% and 6.6% relative improvements in SDR and PESQ respectively compared with a baseline oracle deep attracor model. Meanwhile, we show it can be generalized well to more than one interfering speaker.

cs.SD↗

arXiv2018

Recent Progresses in Deep Learning based Acoustic Models (Updated)

In this paper, we summarize recent progresses made in deep learning based acoustic models and the motivation and insights behind the surveyed techniques. We first discuss acoustic models that can effectively exploit variable-length contextual information, such as recurrent neural networks (RNNs), convolutional neural networks (CNNs), and their various combination with other models. We then describe acoustic models that are optimized end-to-end with emphasis on feature representations learned jointly with rest of the system, the connectionist temporal classification (CTC) criterion, and the attention-based sequence-to-sequence model. We further illustrate robustness issues in speech recognition systems, and discuss acoustic model adaptation, speech enhancement and separation, and robust training strategies. We also cover modeling techniques that lead to more efficient decoding and discuss possible future directions in acoustic model research.

eess.AS↗

arXiv2018

Fabrication and Characterization of Superconducting Quantum Interference Device using (Bi_{1-x}Sb_x)_2Se_3 Topological Insulator Nanoribbons

We report on the fabrication and electrical transport properties of superconducting quantum interference devices (SQUIDs) made from a (Bi_{1-x}Sb_x)_2Se_3 topological insulator (TI) nanoribbon (NR) connected with Pb0.5In0.5 superconducting electrodes. Below the transition temperature of the superconducting Pb0.5In0.5 electrodes, periodic oscillations of the critical current are observed in the TI NR SQUID under a magnetic field applied perpendicular to the plane owing to flux quantization. Also the output voltage modulates as a function of the external magnetic field. Moreover, the SQUID the SQUID shows a voltage modulation envelope, which is considered to represent the Fraunhofer-like patterns of each single junction. These properties of the TI NR SQUID would provide a useful method to explore Majorana fermions.

cond-mat.supr-con↗

arXiv2017

Joint Separation and Denoising of Noisy Multi-talker Speech using Recurrent Neural Networks and Permutation Invariant Training

In this paper we propose to use utterance-level Permutation Invariant Training (uPIT) for speaker independent multi-talker speech separation and denoising, simultaneously. Specifically, we train deep bi-directional Long Short-Term Memory (LSTM) Recurrent Neural Networks (RNNs) using uPIT, for single-channel speaker independent multi-talker speech separation in multiple noisy conditions, including both synthetic and real-life noise signals. We focus our experiments on generalizability and noise robustness of models that rely on various types of a priori knowledge e.g. in terms of noise type and number of simultaneous speakers. We show that deep bi-directional LSTM RNNs trained using uPIT in noisy environments can improve the Signal-to-Distortion Ratio (SDR) as well as the Extended Short-Time Objective Intelligibility (ESTOI) measure, on the speaker independent multi-talker speech separation and denoising task, for various noise types and Signal-to-Noise Ratios (SNRs). Specifically, we first show that LSTM RNNs can achieve large SDR and ESTOI improvements, when evaluated using known noise types, and that a single model is capable of handling multiple noise types with only a slight decrease in performance. Furthermore, we show that a single LSTM RNN can handle both two-speaker and three-speaker noisy mixtures, without a priori knowledge about the exact number of speakers. Finally, we show that LSTM RNNs trained using uPIT generalize well to noise types not seen during training.

cs.SD↗

arXiv2017

Empirical Evaluation of Parallel Training Algorithms on Acoustic Modeling

Deep learning models (DLMs) are state-of-the-art techniques in speech recognition. However, training good DLMs can be time consuming especially for production-size models and corpora. Although several parallel training algorithms have been proposed to improve training efficiency, there is no clear guidance on which one to choose for the task in hand due to lack of systematic and fair comparison among them. In this paper we aim at filling this gap by comparing four popular parallel training algorithms in speech recognition, namely asynchronous stochastic gradient descent (ASGD), blockwise model-update filtering (BMUF), bulk synchronous parallel (BSP) and elastic averaging stochastic gradient descent (EASGD), on 1000-hour LibriSpeech corpora using feed-forward deep neural networks (DNNs) and convolutional, long short-term memory, DNNs (CLDNNs). Based on our experiments, we recommend using BMUF as the top choice to train acoustic models since it is most stable, scales well with number of GPUs, can achieve reproducible results, and in many cases even outperforms single-GPU SGD. ASGD can be used as a substitute in some cases.

cs.CL↗