arXiv subjects

Xiangyang Li

Publications and source records attributed to Xiangyang Li.

At least 73 records · Page 4Linked to original sources

arXiv2023

GridMM: Grid Memory Map for Vision-and-Language Navigation

Vision-and-language navigation (VLN) enables the agent to navigate to a remote location following the natural language instruction in 3D environments. To represent the previously visited environment, most approaches for VLN implement memory using recurrent states, topological maps, or top-down semantic maps. In contrast to these approaches, we build the top-down egocentric and dynamically growing Grid Memory Map (i.e., GridMM) to structure the visited environment. From a global perspective, historical observations are projected into a unified grid map in a top-down view, which can better represent the spatial relations of the environment. From a local perspective, we further propose an instruction relevance aggregation method to capture fine-grained visual clues in each grid region. Extensive experiments are conducted on both the REVERIE, R2R, SOON datasets in the discrete environments, and the R2R-CE dataset in the continuous environments, showing the superiority of our proposed method.

cs.CV↗

arXiv2023

Plug-and-Play Document Modules for Pre-trained Models

Large-scale pre-trained models (PTMs) have been widely used in document-oriented NLP tasks, such as question answering. However, the encoding-task coupling requirement results in the repeated encoding of the same documents for different tasks and queries, which is highly computationally inefficient. To this end, we target to decouple document encoding from downstream tasks, and propose to represent each document as a plug-and-play document module, i.e., a document plugin, for PTMs (PlugD). By inserting document plugins into the backbone PTM for downstream tasks, we can encode a document one time to handle multiple tasks, which is more efficient than conventional encoding-task coupling methods that simultaneously encode documents and input queries using task-specific encoders. Extensive experiments on 8 datasets of 4 typical NLP tasks show that PlugD enables models to encode documents once and for all across different scenarios. Especially, PlugD can save $69\%$ computational costs while achieving comparable performance to state-of-the-art encoding-task coupling methods. Additionally, we show that PlugD can serve as an effective post-processing way to inject knowledge into task-specific models, improving model performance without any additional model training.

cs.CL↗

arXiv2023

Rethinking Dense Retrieval's Few-Shot Ability

Few-shot dense retrieval (DR) aims to effectively generalize to novel search scenarios by learning a few samples. Despite its importance, there is little study on specialized datasets and standardized evaluation protocols. As a result, current methods often resort to random sampling from supervised datasets to create "few-data" setups and employ inconsistent training strategies during evaluations, which poses a challenge in accurately comparing recent progress. In this paper, we propose a customized FewDR dataset and a unified evaluation benchmark. Specifically, FewDR employs class-wise sampling to establish a standardized "few-shot" setting with finely-defined classes, reducing variability in multiple sampling rounds. Moreover, the dataset is disjointed into base and novel classes, allowing DR models to be continuously trained on ample data from base classes and a few samples in novel classes. This benchmark eliminates the risk of novel class leakage, providing a reliable estimation of the DR model's few-shot ability. Our extensive empirical results reveal that current state-of-the-art DR models still face challenges in the standard few-shot scene. Our code and data will be open-sourced at https://github.com/OpenMatch/ANCE-Tele.

cs.CL↗

arXiv2023

KERM: Knowledge Enhanced Reasoning for Vision-and-Language Navigation

Vision-and-language navigation (VLN) is the task to enable an embodied agent to navigate to a remote location following the natural language instruction in real scenes. Most of the previous approaches utilize the entire features or object-centric features to represent navigable candidates. However, these representations are not efficient enough for an agent to perform actions to arrive the target location. As knowledge provides crucial information which is complementary to visible content, in this paper, we propose a Knowledge Enhanced Reasoning Model (KERM) to leverage knowledge to improve agent navigation ability. Specifically, we first retrieve facts (i.e., knowledge described by language descriptions) for the navigation views based on local regions from the constructed knowledge base. The retrieved facts range from properties of a single object (e.g., color, shape) to relationships between objects (e.g., action, spatial position), providing crucial information for VLN. We further present the KERM which contains the purification, fact-aware interaction, and instruction-guided aggregation modules to integrate visual, history, instruction, and fact features. The proposed KERM can automatically select and gather crucial and relevant cues, obtaining more accurate action prediction. Experimental results on the REVERIE, R2R, and SOON datasets demonstrate the effectiveness of the proposed method.

cs.CV↗

arXiv2023

MR.Brick: Designing A Remote Mixed-reality Educational Game System for Promoting Children's Social & Collaborative Skills

Children are one of the groups most influenced by COVID-19-related social distancing, and a lack of contact with peers can limit their opportunities to develop social and collaborative skills. However, remote socialization and collaboration as an alternative approach is still a great challenge for children. This paper presents MR.Brick, a Mixed Reality (MR) educational game system that helps children adapt to remote collaboration. A controlled experimental study involving 24 children aged six to ten was conducted to compare MR.Brick with the traditional video game by measuring their social and collaborative skills and analyzing their multi-modal playing behaviours. The results showed that MR.Brick was more conducive to children's remote collaboration experience than the traditional video game. Given the lack of training systems designed for children to collaborate remotely, this study may inspire interaction design and educational research in related fields.

cs.HC↗

arXiv2022

TeleMelody: Lyric-to-Melody Generation with a Template-Based Two-Stage Method

Lyric-to-melody generation is an important task in automatic songwriting. Previous lyric-to-melody generation systems usually adopt end-to-end models that directly generate melodies from lyrics, which suffer from several issues: 1) lack of paired lyric-melody training data; 2) lack of control on generated melodies. In this paper, we develop TeleMelody, a two-stage lyric-to-melody generation system with music template (e.g., tonality, chord progression, rhythm pattern, and cadence) to bridge the gap between lyrics and melodies (i.e., the system consists of a lyric-to-template module and a template-to-melody module). TeleMelody has two advantages. First, it is data efficient. The template-to-melody module is trained in a self-supervised way (i.e., the source template is extracted from the target melody) that does not need any lyric-melody paired data. The lyric-to-template module is made up of some rules and a lyric-to-rhythm model, which is trained with paired lyric-rhythm data that is easier to obtain than paired lyric-melody data. Second, it is controllable. The design of template ensures that the generated melodies can be controlled by adjusting the musical elements in template. Both subjective and objective experimental evaluations demonstrate that TeleMelody generates melodies with higher quality, better controllability, and less requirement on paired lyric-melody data than previous generation systems.

cs.SD↗

arXiv2022

Contrastive Learning enhanced Author-Style Headline Generation

Headline generation is a task of generating an appropriate headline for a given article, which can be further used for machine-aided writing or enhancing the click-through ratio. Current works only use the article itself in the generation, but have not taken the writing style of headlines into consideration. In this paper, we propose a novel Seq2Seq model called CLH3G (Contrastive Learning enhanced Historical Headlines based Headline Generation) which can use the historical headlines of the articles that the author wrote in the past to improve the headline generation of current articles. By taking historical headlines into account, we can integrate the stylistic features of the author into our model, and generate a headline not only appropriate for the article, but also consistent with the author's style. In order to efficiently learn the stylistic features of the author, we further introduce a contrastive learning based auxiliary task for the encoder of our model. Besides, we propose two methods to use the learned stylistic features to guide both the pointer and the decoder during the generation. Experimental results show that historical headlines of the same user can improve the headline generation significantly, and both the contrastive learning module and the two style features fusion methods can further boost the performance.

cs.CL↗

arXiv2022

IntTower: the Next Generation of Two-Tower Model for Pre-Ranking System

Scoring a large number of candidates precisely in several milliseconds is vital for industrial pre-ranking systems. Existing pre-ranking systems primarily adopt the \textbf{two-tower} model since the ``user-item decoupling architecture'' paradigm is able to balance the \textit{efficiency} and \textit{effectiveness}. However, the cost of high efficiency is the neglect of the potential information interaction between user and item towers, hindering the prediction accuracy critically. In this paper, we show it is possible to design a two-tower model that emphasizes both information interactions and inference efficiency. The proposed model, IntTower (short for \textit{Interaction enhanced Two-Tower}), consists of Light-SE, FE-Block and CIR modules. Specifically, lightweight Light-SE module is used to identify the importance of different features and obtain refined feature representations in each tower. FE-Block module performs fine-grained and early feature interactions to capture the interactive signals between user and item towers explicitly and CIR module leverages a contrastive interaction regularization to further enhance the interactions implicitly. Experimental results on three public datasets show that IntTower outperforms the SOTA pre-ranking models significantly and even achieves comparable performance in comparison with the ranking models. Moreover, we further verify the effectiveness of IntTower on a large-scale advertisement pre-ranking system. The code of IntTower is publicly available\footnote{https://github.com/archersama/IntTower}

cs.IR↗

arXiv2022

Two-Dimensional Semiconducting Metal Organic Frameworks with Auxetic Effect, Room Temperature Ferrimagnetism, Chiral Ferroelectricity, Bipolar Spin Polarization and Topological Nodal Lines/Points

Two-dimensional (2D) semiconductors integrated with two or more functions are the cornerstone for constructing multifunctional nanodevices, but remain largely limited. Here, by tuning the spin state of organic linkers and the symmetry/topology of crystal lattice, we predict a class of unprecedented multifunctional semiconductors in 2D Cr(II) five-membered heterocyclic metal organic frameworks that simultaneously possess auxetic effect, room temperature ferrimagnetism, chiral ferroe-lectricity, electrically reversible spin polarization and topological nodal lines/points. Taking 2D Cr(TDZ)$_2$ (TDZ=1.2.5-thiadiazole) as an exemplification, the auxetic effect is produced by the anti-tetra-chiral lattice structure. The high temperature ferrimagnetism originates from the strong d-p direct magnetic exchange interaction between Cr cations and TDZ doublet radical anions. Meanwhile, the clockwise-counterclockwise alignment of TDZ' dipoles results in unique 2D chiral ferroelectricity with atomic-scale vortex-antivortex states. 2D Cr(TDZ)$_2$ is an intrinsic bipolar magnetic semiconductor where half-metallic conduction with switchable spin-polarization direction can be induced by applying a gate voltage. Besides, the symmetry of the little group C$_4$ of lattice structure endows 2D Cr(TDZ)$_2$ with topological nodal lines and a quadratic nodal point in the Brillouin zone near the Fermi level.

cond-mat.mtrl-sci↗

arXiv2022

Low Resource Style Transfer via Domain Adaptive Meta Learning

Text style transfer (TST) without parallel data has achieved some practical success. However, most of the existing unsupervised text style transfer methods suffer from (i) requiring massive amounts of non-parallel data to guide transferring different text styles. (ii) colossal performance degradation when fine-tuning the model in new domains. In this work, we propose DAML-ATM (Domain Adaptive Meta-Learning with Adversarial Transfer Model), which consists of two parts: DAML and ATM. DAML is a domain adaptive meta-learning approach to learn general knowledge in multiple heterogeneous source domains, capable of adapting to new unseen domains with a small amount of data. Moreover, we propose a new unsupervised TST approach Adversarial Transfer Model (ATM), composed of a sequence-to-sequence pre-trained language model and uses adversarial style training for better content preservation and style transfer. Results on multi-domain datasets demonstrate that our approach generalizes well on unseen low-resource domains, achieving state-of-the-art results against ten strong baselines.

cs.CL↗

arXiv2021

Two-Dimensional Bipolar Magnetic Semiconductor with High Curie Temperature and Electrically Controllable Spin Polarization Realized in Exfoliated Cr(pyrazine)$_2$ Monolayer

Exploring two-dimensional (2D) magnetic semiconductors with room temperature magnetic ordering and electrically controllable spin polarization is a highly desirable but challenging task for nanospintronics. Here, through first principles calculations, we propose to realize such a material by exfoliating the recently synthesized organometallic layered crystal Li$_{0.7}$[Cr(pyz)$_2$]Cl$_{0.7}$0.25$\cdot$(THF) (pyz = pyrazine, THF = tetrahydrofuran) [Science 370, 587 (2020)]. The feasibility of exfoliation is confirmed by the rather low exfoliation energy of 0.27 J/m$^2$, even smaller than that of graphite. In exfoliated Cr(pyz)$_2$ monolayer, each pyrazine ring grabs one electron from the Cr atom to become a radical anion, then a strong $d$-$p$ direct exchange magnetic interaction emerges between Cr cations and pyrazine radicals, resulting in room temperature ferrimagnetism with a Curie temperature of 342 K. Moreover, Cr(pyz)$_2$ monolayer is revealed to be an intrinsic bipolar magnetic semiconductor where electrical doping can induce half-metallic conduction with controllable spin-polarization direction.

cond-mat.mtrl-sci↗

arXiv2021

Line Marching Algorithm For Planar Kinematic Swarm Robots: A Dynamic Leader-Follower Approach

Most of the existing formation algorithms for multiagent systems are fully label-specified, i.e., the desired position for each agent in the formation is uniquely determined by its label, which would inevitably make the formation algorithms vulnerable to agent failures. To address this issue, in this paper, we propose a dynamic leader-follower approach to solving the line marching problem for a swarm of planar kinematic robots. In contrast to the existing results, the desired positions for the robots in the line are not fully label-specified, but determined in a dynamic way according to the current state of the robot swarm. By constantly forming a chain of leader-follower pairs, exact formation can be achieved by pairwise leader-following tracking. Since the order of the chain of leader-follower pairs is constantly updated, the proposed algorithm shows strong robustness against robot failures. Comprehensive numerical results are provided to evaluate the performance of the proposed algorithm.

cs.RO↗

arXiv2021

Dataset Bias in Few-shot Image Recognition

The goal of few-shot image recognition (FSIR) is to identify novel categories with a small number of annotated samples by exploiting transferable knowledge from training data (base categories). Most current studies assume that the transferable knowledge can be well used to identify novel categories. However, such transferable capability may be impacted by the dataset bias, and this problem has rarely been investigated before. Besides, most of few-shot learning methods are biased to different datasets, which is also an important issue that needs to be investigated deeply. In this paper, we first investigate the impact of transferable capabilities learned from base categories. Specifically, we use the relevance to measure relationships between base categories and novel categories. Distributions of base categories are depicted via the instance density and category diversity. The FSIR model learns better transferable knowledge from relevant training data. In the relevant data, dense instances or diverse categories can further enrich the learned knowledge. Experimental results on different sub-datasets of ImagNet demonstrate category relevance, instance density and category diversity can depict transferable bias from base categories. Second, we investigate performance differences on different datasets from dataset structures and different few-shot learning methods. Specifically, we introduce image complexity, intra-concept visual consistency, and inter-concept visual similarity to quantify characteristics of dataset structures. We use these quantitative characteristics and four few-shot learning methods to analyze performance differences on five different datasets. Based on the experimental analysis, some insightful observations are obtained from the perspective of both dataset structures and few-shot learning methods. We hope these observations are useful to guide future FSIR research.

cs.CV↗

arXiv2021

Exploring Text-transformers in AAAI 2021 Shared Task: COVID-19 Fake News Detection in English

In this paper, we describe our system for the AAAI 2021 shared task of COVID-19 Fake News Detection in English, where we achieved the 3rd position with the weighted F1 score of 0.9859 on the test set. Specifically, we proposed an ensemble method of different pre-trained language models such as BERT, Roberta, Ernie, etc. with various training strategies including warm-up,learning rate schedule and k-fold cross-validation. We also conduct an extensive analysis of the samples that are not correctly classified. The code is available at:https://github.com/archersama/3rd-solution-COVID19-Fake-News-Detection-in-English.

cs.CL↗

arXiv2020

Review of Text Style Transfer Based on Deep Learning

Text style transfer is a hot issue in recent natural language processing,which mainly studies the text to adapt to different specific situations, audiences and purposes by making some changes. The style of the text usually includes many aspects such as morphology, grammar, emotion, complexity, fluency, tense, tone and so on. In the traditional text style transfer model, the text style is generally relied on by experts knowledge and hand-designed rules, but with the application of deep learning in the field of natural language processing, the text style transfer method based on deep learning Started to be heavily researched. In recent years, text style transfer is becoming a hot issue in natural language processing research. This article summarizes the research on the text style transfer model based on deep learning in recent years, and summarizes, analyzes and compares the main research directions and progress. In addition, the article also introduces public data sets and evaluation indicators commonly used for text style transfer. Finally, the existing characteristics of the text style transfer model are summarized, and the future development trend of the text style transfer model based on deep learning is analyzed and forecasted.

cs.CL↗

arXiv2020

FenceMask: A Data Augmentation Approach for Pre-extracted Image Features

We propose a novel data augmentation method named 'FenceMask' that exhibits outstanding performance in various computer vision tasks. It is based on the 'simulation of object occlusion' strategy, which aim to achieve the balance between object occlusion and information retention of the input data. By enhancing the sparsity and regularity of the occlusion block, our augmentation method overcome the difficulty of small object augmentation and notably improve performance over baselines. Sufficient experiments prove the performance of our method is better than other simulate object occlusion approaches. We tested it on CIFAR10, CIFAR100 and ImageNet datasets for Coarse-grained classification, COCO2017 and VisDrone datasets for detection, Oxford Flowers, Cornel Leaf and Stanford Dogs datasets for Fine-Grained Visual Categorization. Our method achieved significant performance improvement on Fine-Grained Visual Categorization task and VisDrone dataset.

cs.CV↗

arXiv2020

Entanglement as upper bounded for the nonlocality of a general two-qubit system

Nonlocality and entanglement are not only the fundamental characteristics of quantum mechanics but also important resources for quantum information and computation applications. Exploiting the quantitative relationship between the two different resources is of both theoretical and practical significance. The common choice for quantifying the nonlocality of a two-qubit state is the maximal violation of the Clauser-Horne-Shimony-Holt inequality. That for entanglement is entanglement of formation, which is a function of the concurrence. In this paper, we systematically investigate the quantitative relationship between the entanglement and nonlocality of a general two-qubit system. We rederive a known upper bound on the nonlocality of a general two-qubit state, which depends on the state's entanglement. We investigate the condition that the nonlocality of two different two-qubit states can be optimally stimulated by the same nonlocality test setting and find the class of two-qubit state pairs that have this property. Finally, we obtain the necessary and sufficient condition that the upper bound can be reached.

quant-ph↗

arXiv2019

COOK: Chirp-OOK Communication with Self-reliant Bitrate Adaptation in Backscatter Networks

For large-scale Internet of Things (IoT), backscatter communication is a promising technology to reduce power consumption and simplify deployment. However, backscatter communication lacks stability, along with limited communication range within a few meters. Due to the limited computation ability of backscatter tags, it is burdensome to effectively adapt the bitrate for the time-varying channel. Thus, backscatter tags are failed to fully utilize the optimal transmission rate. In this paper, we design a system named COOK with self-reliant bitrate adaptation in backscatter communication. Channel symmetry allows backscatter tags to adjust bitrate depending on the received signal strength of the excitation source (ES) without feedback. In addition, the chirp spreading signal is exploited as the ES signal to enable backscatter tags to work under noise floor. Our modulation approach is denoted as Chirp-OOK since the tags reflect the chirp signal by employing the on-off keying modulation. It allows that receiver can decode under the noise floor and the bitrate varies flexibly as the communication range changes. We have implemented the prototype system based on the universal software radio peripheral (USRP) platform. Extensive experiment results demonstrate the effectiveness of the proposed system. Our system provides valid communication distance up to $27m$, which is 7 times as compared with normal backscatter system. The system significantly increases the backscatter communication stability, by supporting bitrate adaptation ranges from 0.33kbps to 1.2Mbps, and guaranteeing the bit error rate (BER) is below 1%.

eess.SP↗