arXiv subjects

Zehao Lin

Publications and source records attributed to Zehao Lin.

49 records · Page 3Linked to original sources

arXiv2022

Scaled indium oxide transistors fabricated using atomic layer deposition

In order to continue to improve integrated circuit performance and functionality, scaled transistors with short channel lengths and low thickness are needed. But the further scaling of silicon-based devices and the development of alternative semiconductor channel materials that are compatible with current fabrication processes is challenging. Here we report atomic-layer-deposited indium oxide transistors with channel lengths down to 8 nm, channel thicknesses down to 0.5 nm and equivalent dielectric oxide thickness down to 0.84 nm. Due to the scaled device dimensions and low contact resistance, the devices exhibit high on-state currents of 3.1 A/mm at a drain voltage of 0.5 V and a transconductance of 1.5 S/mm at a drain voltage 1 V. Our devices are a promising alternative channel material for scaled transistors with back-end-of-line processing compatibility.

cond-mat.mtrl-sci↗

arXiv2021

"Wait, I'm Still Talking!" Predicting the Dialogue Interaction Behavior Using Imagine-Then-Arbitrate Model

Producing natural and accurate responses like human beings is the ultimate goal of intelligent dialogue agents. So far, most of the past works concentrate on selecting or generating one pertinent and fluent response according to current query and its context. These models work on a one-to-one environment, making one response to one utterance each round. However, in real human-human conversations, human often sequentially sends several short messages for readability instead of a long message in one turn. Thus messages will not end with an explicit ending signal, which is crucial for agents to decide when to reply. So the first step for an intelligent dialogue agent is not replying but deciding if it should reply at the moment. To address this issue, in this paper, we propose a novel Imagine-then-Arbitrate (ITA) neural dialogue model to help the agent decide whether to wait or to make a response directly. Our method has two imaginator modules and an arbitrator module. The two imaginators will learn the agent's and user's speaking style respectively, generate possible utterances as the input of the arbitrator, combining with dialogue history. And the arbitrator decides whether to wait or to make a response to the user directly. To verify the performance and effectiveness of our method, we prepared two dialogue datasets and compared our approach with several popular models. Experimental results show that our model performs well on addressing ending prediction issue and outperforms baseline models.

cs.CL↗

arXiv2021

Predict-then-Decide: A Predictive Approach for Wait or Answer Task in Dialogue Systems

Different people have different habits of describing their intents in conversations. Some people tend to deliberate their intents in several successive utterances, i.e., they use several consistent messages for readability instead of a long sentence to express their question. This creates a predicament faced by the application of dialogue systems, especially in real-world industry scenarios, in which the dialogue system is unsure whether it should answer the query of user immediately or wait for further supplementary input. Motivated by such an interesting predicament, we define a novel Wait-or-Answer task for dialogue systems. We shed light on a new research topic about how the dialogue system can be more intelligent to behave in this Wait-or-Answer quandary. Further, we propose a predictive approach named Predict-then-Decide (PTD) to tackle this Wait-or-Answer task. More specifically, we take advantage of a decision model to help the dialogue system decide whether to wait or answer. The decision of decision model is made with the assistance of two ancillary prediction models: a user prediction and an agent prediction. The user prediction model tries to predict what the user would supplement and uses its prediction to persuade the decision model that the user has some information to add, so the dialogue system should wait. The agent prediction model tries to predict the answer of the dialogue system and convince the decision model that it is a superior choice to answer the query of user immediately since the input of user has come to an end. We conduct our experiments on two real-life scenarios and three public datasets. Experimental results on five datasets show our proposed PTD approach significantly outperforms the existing models in solving this Wait-or-Answer problem.

cs.CL↗

arXiv2021

A Morphological Classification of 18190 Molecular Clouds Identified in $^{12}$CO Data from the MWISP Survey

We attempt to visually classify the morphologies of 18190 molecular clouds, which are identified in the $^{12}$CO(1-0) spectral line data over $\sim$ 450 deg$^{2}$ of the second Galactic quadrant from the Milky Way Imaging Scroll Painting project (MWISP). Using the velocity-integrated intensity maps of the $^{12}$CO(1-0) emission, molecular clouds are first divided into unresolved and resolved ones. The resolved clouds are further classified as non-filaments or filaments. Among the 18190 molecular clouds, $\sim$ 25 $\%$ are unresolved, $\sim$ 64$\%$ are non-filaments, and $\sim$ 11$\%$ are filaments. In the terms of the integrated flux of $^{12}$CO(1-0) spectra of the whole 18190 molecular clouds, $\sim$ 90$\%$ are from filaments, $\sim$ 9$\%$ are from non-filaments, and the rest $\sim$ 1$\%$ are from unresolved sources. Although non-filaments are dominant in the number of the discrete molecular clouds, filaments are the main contributor of $^{12}$CO emission flux. We also present the number distributions of physical parameters of the molecular clouds in our catalog, including their angular sizes, velocity spans, peak intensities of $^{12}$CO(1-0) emission, and $^{12}$CO(1-0) total fluxes. We find that there is a systematic difference between the angular sizes of the non-filaments and filaments, with the filaments tending to have larger angular scales. The H$_{2}$ column densities of them are not significantly different. We also discuss the observational effects, such as those induced by the finite spatial resolution, beam dilution and line-of-sight projection, on the morphological classification of molecular clouds in our sample.

astro-ph.GA↗

arXiv2021

Similar Scenes arouse Similar Emotions: Parallel Data Augmentation for Stylized Image Captioning

Stylized image captioning systems aim to generate a caption not only semantically related to a given image but also consistent with a given style description. One of the biggest challenges with this task is the lack of sufficient paired stylized data. Many studies focus on unsupervised approaches, without considering from the perspective of data augmentation. We begin with the observation that people may recall similar emotions when they are in similar scenes, and often express similar emotions with similar style phrases, which underpins our data augmentation idea. In this paper, we propose a novel Extract-Retrieve-Generate data augmentation framework to extract style phrases from small-scale stylized sentences and graft them to large-scale factual captions. First, we design the emotional signal extractor to extract style phrases from small-scale stylized sentences. Second, we construct the plugable multi-modal scene retriever to retrieve scenes represented with pairs of an image and its stylized caption, which are similar to the query image or caption in the large-scale factual data. In the end, based on the style phrases of similar scenes and the factual description of the current scene, we build the emotion-aware caption generator to generate fluent and diversified stylized captions for the current scene. Extensive experimental results show that our framework can alleviate the data scarcity problem effectively. It also significantly boosts the performance of several existing image captioning models in both supervised and unsupervised settings, which outperforms the state-of-the-art stylized image captioning methods in terms of both sentence relevance and stylishness by a substantial margin.

cs.CV↗

arXiv2021

Dialogue State Tracking with Multi-Level Fusion of Predicted Dialogue States and Conversations

Most recently proposed approaches in dialogue state tracking (DST) leverage the context and the last dialogue states to track current dialogue states, which are often slot-value pairs. Although the context contains the complete dialogue information, the information is usually indirect and even requires reasoning to obtain. The information in the lastly predicted dialogue states is direct, but when there is a prediction error, the dialogue information from this source will be incomplete or erroneous. In this paper, we propose the Dialogue State Tracking with Multi-Level Fusion of Predicted Dialogue States and Conversations network (FPDSC). This model extracts information of each dialogue turn by modeling interactions among each turn utterance, the corresponding last dialogue states, and dialogue slots. Then the representation of each dialogue turn is aggregated by a hierarchical structure to form the passage information, which is utilized in the current turn of DST. Experimental results validate the effectiveness of the fusion network with 55.03% and 59.07% joint accuracy on MultiWOZ 2.0 and MultiWOZ 2.1 datasets, which reaches the state-of-the-art performance. Furthermore, we conduct the deleted-value and related-slot experiments on MultiWOZ 2.1 to evaluate our model.

cs.CL↗

arXiv2021

Examinations of CO completeness based on three independent CO surveys

We report the global properties recovered by an ongoing CO survey of the Milky Way Imaging Scroll Painting (MWISP) toward the Galactic outskirts. %To better understand the observational biases, Our results are also compared to those extracted by a uniform decomposition method from the CfA 1.2 m CO survey and the FCRAO 14 m outer Galaxy survey (OGS). We find that more extended and unseen structures are present in the MWISP data. The total flux across the disk recovered by the MWISP survey is 1.6 times larger than those recovered by the CfA and OGS surveys in the case of the same resolution. The discrepancies are scaling with distance. For example, in the outermost OSC arm, the flux ratios for MWISP-to-CfA and MWISP-to-OGS increase up to 43.8 and 7.4, respectively. Nonetheless, the census of molecular gas in our Galaxy is still far from complete by the MWISP, with flux completeness of $<$58%. The total mass ratios of the tabulated molecular clouds between different surveys are similar to the CO flux ratio. The application of these ratios to the total H$_{\rm 2}$ mass of our Galaxy yields a correction factor of at least 1.4, meaning that the H$_{\rm 2}$ mass of our Galaxy should be at least 40% more massive than previously determined. Including the completeness correction, an even more significant fraction of the matter should be contributed by baryonic matter. The mass spectrum in the outer Galactic plane is better described by a non-truncating power-law with $γ$=$-$1.83$\pm$0.05, and an upper mass of $M_0$=(1.3$\pm$0.5)$\times$10$^{\rm 6}$ $M_\odot$.

astro-ph.GA↗

arXiv2020

Why In2O3 Can Make 0.7 nm Atomic Layer Thin Transistors?

In this work, we demonstrate enhancement-mode field-effect transistors by atomic-layer-deposited (ALD) amorphous In2O3 channel with thickness down to 0.7 nm. Thickness is found to be critical on the materials and electron transport of In2O3. Controllable thickness of In2O3 at atomic scale enables the design of sufficient 2D carrier density in the In2O3 channel integrated with the conventional dielectric. The threshold voltage and channel carrier density are found to be considerably tuned by channel thickness. Such phenomenon is understood by the trap neutral level (TNL) model where the Fermi-level tends to align deeply inside the conduction band of In2O3 and can be modulated to the bandgap in atomic layer thin In2O3 due to quantum confinement effect, which is confirmed by density function theory (DFT) calculation. The demonstration of enhancement-mode amorphous In2O3 transistors suggests In2O3 is a competitive channel material for back-end-of-line (BEOL) compatible transistors and monolithic 3D integration applications.

cond-mat.mtrl-sci↗

arXiv2020

Scaled Atomic-Layer-Deposited Indium Oxide Nanometer Transistors with Maximum Drain Current Exceeding 2 A/mm at Drain Voltage of 0.7 V

In this work, we demonstrate scaled back-end-of-line (BEOL) compatible indium oxide (In2O3) transistors by atomic layer deposition (ALD) with channel thickness (Tch) of 1.0-1.5 nm, channel length (Lch) down to 40 nm, and equivalent oxide thickness (EOT) of 2.1 nm, with record high drain current of 2.0 A/mm at VDS of 0.7 V among all oxide semiconductors. Enhancement-mode In2O3 transistors with ID over 1.0 A/mm at VDS of 1 V are also achieved by controlling the channel thickness down to 1.0 nm at atomic layer scale. Such high current density in a relatively low mobility amorphous oxide semiconductor is understood by the formation of high density 2D channel beyond 4E13 /cm2 at HfO2/In2O3 oxide/oxide interface.

cond-mat.mtrl-sci↗

arXiv2020

Teacher-Student Framework Enhanced Multi-domain Dialogue Generation

Dialogue systems dealing with multi-domain tasks are highly required. How to record the state remains a key problem in a task-oriented dialogue system. Normally we use human-defined features as dialogue states and apply a state tracker to extract these features. However, the performance of such a system is limited by the error propagation of a state tracker. In this paper, we propose a dialogue generation model that needs no external state trackers and still benefits from human-labeled semantic data. By using a teacher-student framework, several teacher models are firstly trained in their individual domains, learn dialogue policies from labeled states. And then the learned knowledge and experience are merged and transferred to a universal student model, which takes raw utterance as its input. Experiments show that the dialogue system trained under our framework outperforms the one uses a belief tracker.

cs.CL↗

arXiv2020

MTSS: Learn from Multiple Domain Teachers and Become a Multi-domain Dialogue Expert

How to build a high-quality multi-domain dialogue system is a challenging work due to its complicated and entangled dialogue state space among each domain, which seriously limits the quality of dialogue policy, and further affects the generated response. In this paper, we propose a novel method to acquire a satisfying policy and subtly circumvent the knotty dialogue state representation problem in the multi-domain setting. Inspired by real school teaching scenarios, our method is composed of multiple domain-specific teachers and a universal student. Each individual teacher only focuses on one specific domain and learns its corresponding domain knowledge and dialogue policy based on a precisely extracted single domain dialogue state representation. Then, these domain-specific teachers impart their domain knowledge and policies to a universal student model and collectively make this student model a multi-domain dialogue expert. Experiment results show that our method reaches competitive results with SOTAs in both multi-domain and single domain setting.

cs.CL↗

arXiv2019

Task-Oriented Conversation Generation Using Heterogeneous Memory Networks

How to incorporate external knowledge into a neural dialogue model is critically important for dialogue systems to behave like real humans. To handle this problem, memory networks are usually a great choice and a promising way. However, existing memory networks do not perform well when leveraging heterogeneous information from different sources. In this paper, we propose a novel and versatile external memory networks called Heterogeneous Memory Networks (HMNs), to simultaneously utilize user utterances, dialogue history and background knowledge tuples. In our method, historical sequential dialogues are encoded and stored into the context-aware memory enhanced by gating mechanism while grounding knowledge tuples are encoded and stored into the context-free memory. During decoding, the decoder augmented with HMNs recurrently selects each word in one response utterance from these two memories and a general vocabulary. Experimental results on multiple real-world datasets show that HMNs significantly outperform the state-of-the-art data-driven task-oriented dialogue models in most domains.

cs.CL↗

arXiv2018

Chiral Landau levels in Weyl semimetal NbAs with multiple topological carriers

Recently, Weyl semimetals have been experimentally discovered in both inversion-symmetry-breaking and time-reversal-symmetry-breaking crystals. The non-trivial topology in Weyl semimetals can manifest itself with exotic phenomena which have been extensively investigated by photoemission and transport measurements. Despite the numerous experimental efforts on Fermi arcs and chiral anomaly, the existence of unconventional zeroth Landau levels, as a unique hallmark of Weyl fermions which is highly related to chiral anomaly, remains elusive owing to the stringent experimental requirements. Here, we report the magneto-optical study of Landau quantization in Weyl semimetal NbAs. High magnetic fields drive the system towards the quantum limit which leads to the observation of zeroth chiral Landau levels in two inequivalent Weyl nodes. As compared to other Landau levels, the zeroth chiral Landau level exhibits a distinct linear dispersion in z momentum direction and allows the optical transitions without the limitation of zero z momentum or square root of magnetic field evolution. The magnetic field dependence of the zeroth Landau levels further verifies the predicted particle-hole asymmetry of the Weyl cones. Meanwhile, the optical transitions from the normal Landau levels exhibit the coexistence of multiple carriers including an unexpected massive Dirac fermion, pointing to a more complex topological nature in inversion-symmetry-breaking Weyl semimetals. Our results provide insights into the Landau quantization of Weyl fermions and demonstrate an effective tool for studying complex topological systems.

cond-mat.mes-hall↗