Search Results for author:
Found 54 papers, 11 papers with code
Integrating BERT and Score-based Feature Gates for Chinese Grammatical Error Diagnosis
This paper describes our proposed model for the Chinese Grammatical Error Diagnosis (CGED) task in NLPTEA2020.
ECNU_ICA at SemEval-2022 Task 10: A Simple and Unified Model for Monolingual and Crosslingual Structured Sentiment Analysis
The task aims to extract the structured sentiment information (e. g., holder, target, expression and sentiment polarity) in a text.
Multi-Scale Distribution Deep Variational Autoencoder for Explanation Generation
Generating explanations for recommender systems is essential for improving their transparency, as users often wish to understand the reason for receiving a specified recommendation.
KERS: A Knowledge-Enhanced Framework for Recommendation Dialog Systems with Multiple Subgoals
Recommendation dialogs require the system to build a social bond with users to gain trust and develop affinity in order to increase the chance of a successful recommendation.
C3SASR: Cheap Causal Convolutions for Self-Attentive Sequential Recommendation
We evaluate the effectiveness of the proposed model in terms of both accurate and calibrated sequential recommendation.
I4U System Description for NIST SRE'20 CTS Challenge
This manuscript describes the I4U submission to the 2020 NIST Speaker Recognition Evaluation (SRE'20) Conversational Telephone Speech (CTS) Challenge.
Incorporating Pre-training Paradigm for Antibody Sequence-Structure Co-design
Specifically, we first pre-train an antibody language model based on the sequence data, then propose a one-shot way for sequence and structure generation of CDR to avoid the heavy cost and error propagation from an autoregressive manner, and finally leverage the pre-trained antibody model for the antigen-specific antibody generation model with some carefully designed modules.
Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection
To address these problems, we construct the homogeneous structure between the point cloud and images to avoid projective information loss by transforming the camera features into the LiDAR 3D space.
THUEE system description for NIST 2020 SRE CTS challenge
This paper presents the system description of the THUEE team for the NIST 2020 Speaker Recognition Evaluation (SRE) conversational telephone speech (CTS) challenge.
An Information Minimization Based Contrastive Learning Model for Unsupervised Sentence Embeddings Learning
To address this problem, we present an information minimization based contrastive learning (InforMin-CL) model to retain the useful information and discard the redundant information by maximizing the mutual information and minimizing the information entropy between positive instances meanwhile for unsupervised sentence representation learning.
A Multi-Format Transfer Learning Model for Event Argument Extraction via Variational Information Bottleneck
Event argument extraction (EAE) aims to extract arguments with given roles from texts, which have been widely studied in natural language processing.
A Graph Isomorphism Network with Weighted Multiple Aggregators for Speech Emotion Recognition
Speech emotion recognition (SER) is an essential part of human-computer interaction.
Hierarchic Temporal Convolutional Network With Cross-Domain Encoder for Music Source Separation
In this paper, we propose a model which combines the complexed spectrogram domain feature and time-domain feature by a cross-domain encoder (CDE) and adopts the hierarchic temporal convolutional network (HTCN) for multiple music sources separation.
Ranked #6 on
Music Source Separation
on MUSDB18
A Knowledge-Enhanced Adversarial Model for Cross-lingual Structured Sentiment Analysis
Notably, we propose a Knowledge-Enhanced Adversarial Model (\texttt{KEAM}) with both implicit distributed and explicit structural knowledge to enhance the cross-lingual transfer.
Enhancing Event-Level Sentiment Analysis with Structured Arguments
Previous studies about event-level sentiment analysis (SA) usually model the event as a topic, a category or target terms, while the structured arguments (e. g., subject, object, time and location) that have potential effects on the sentiment are not well studied.
CUP: Curriculum Learning based Prompt Tuning for Implicit Event Argument Extraction
Implicit event argument extraction (EAE) aims to identify arguments that could scatter over the document.
DACSR: Decoupled-Aggregated End-to-End Calibrated Sequential Recommendation
In this work, we focus on the calibrated recommendations for sequential recommendation, which is connected to both fairness and diversity.
Shifting More Attention to Visual Backbone: Query-modulated Refinement Networks for End-to-End Visual Grounding
Moreover, since the backbones are query-agnostic, it is difficult to completely avoid the inconsistency issue by training the visual backbone end-to-end in the visual grounding framework.
Multi-channel Attentive Graph Convolutional Network With Sentiment Fusion For Multimodal Sentiment Analysis
This paper proposes a Multi-channel Attentive Graph Convolutional Network (MAGCN), consisting of two main components: cross-modality interactive learning and sentimental feature fusion.
Cross-Domain Document Layout Analysis via Unsupervised Document Style Guide
Our framework is an unsupervised document layout analysis framework.
Long-Tail Session-based Recommendation from Calibration
Accurate predictions in session-based recommendations have progressed, but a few studies have focused on skewed recommendation lists caused by popularity bias.
Co-evolution Transformer for Protein Contact Prediction
These methods generally derive coevolutionary features by aggregating the learned residue representations from individual sequences with equal weights, which is inconsistent with the premise that residue co-evolutions are a reflection of collective covariation patterns of numerous homologous proteins.
Pre-training Co-evolutionary Protein Representation via A Pairwise Masked Language Model
The key problem in the protein sequence representation learning is to capture the co-evolutionary information reflected by the inter-residue co-variation in the sequences.
Improved Drug-target Interaction Prediction with Intermolecular Graph Transformer
The identification of active binding drugs for target proteins (termed as drug-target interaction prediction) is the key challenge in virtual screening, which plays an essential role in drug discovery.
Inferring Substitutable and Complementary Products with Knowledge-Aware Path Reasoning based on Dynamic Policy Network
To achieve this, existing approaches take advantage of the knowledge graphs to learn more evidences for inference, whereas they often suffer from invalid reasoning for lack of elegant decision making strategies.
Document Image Layout Analysis via Explicit Edge Embedding Network
Layout analysis from a document image plays an important role in document content understanding and information extraction systems.
TransTCN: An Attention-based TCN Framework for Sequential Modeling
The model was evaluated across a wide range of the tasks in time series, which are commonly used to the benchmark of TCN and recurrent networks.
A Survey of Human-in-the-loop for Machine Learning
Humans can provide training data for machine learning applications and directly accomplish tasks that are hard for computers in the pipeline with the help of machine-based approaches.
ECNUICA at SemEval-2021 Task 11: Rule based Information Extraction Pipeline
The purpose of the task was to extract triples from a paper in the Nature Language Processing field for constructing an Open Research Knowledge Graph.
ECNU\_ICA\_1 SemEval-2021 Task 4: Leveraging Knowledge-enhanced Graph Attention Networks for Reading Comprehension of Abstract Meaning
This paper describes our system for SemEval-2021 Task 4: Reading Comprehension of Abstract Meaning.
Document Layout Analysis via Dynamic Residual Feature Fusion
The document layout analysis (DLA) aims to split the document image into different interest regions and understand the role of each region, which has wide application such as optical character recognition (OCR) systems and document retrieval.
Is ``hot pizza'' Positive or Negative? Mining Target-aware Sentiment Lexicons
Modelling a word{'}s polarity in different contexts is a key task in sentiment analysis.
Data-driven criterion for the solid-liquid transition of two-dimensional self-propelled colloidal particles far from equilibrium
We establish an explicit data-driven criterion for identifying the solid-liquid transition of two-dimensional self-propelled colloidal particles in the far from equilibrium parameter regime, where the transition points predicted by different conventional empirical criteria for melting and freezing diverge.
Soft Condensed Matter Statistical Mechanics
Emergent criticality and universality class of spin and charge density wave transitions of two-component lattice Bose gases in optical cavities at finite temperature
At the temperature scale around half of the on-site interaction energy, we find a new critical regime emerges and features, in particular, a new bicritical line and two critical lines associated with the finite temperature SDW-CDW, homogeneous-SDW, and homogeneous-CDW transition, respectively.
Quantum Gases Statistical Mechanics
SentiX: A Sentiment-Aware Pre-Trained Model for Cross-Domain Sentiment Analysis
However, due to the variety of users{'} emotional expressions across domains, fine-tuning the pre-trained models on the source domain tends to overfit, leading to inferior results on the target domain.
Prompt Agnostic Essay Scorer: A Domain Generalization Approach to Cross-prompt Automated Essay Scoring
Cross-prompt automated essay scoring (AES) requires the system to use non target-prompt essays to award scores to a target-prompt essay.
ECNU-SenseMaker at SemEval-2020 Task 4: Leveraging Heterogeneous Knowledge Resources for Commonsense Validation and Explanation
As a result, this model performs quite well in both validation and explanation.
SAS: Dialogue State Tracking via Slot Attention and Slot Information Sharing
Dialogue state tracker is responsible for inferring user intentions through dialogue history.
SEEK: Segmented Embedding of Knowledge Graphs
In recent years, knowledge graph embedding becomes a pretty hot research topic of artificial intelligence and plays increasingly vital roles in various downstream applications, such as recommendation and question answering.
Ranked #1 on
Link Prediction
on YAGO37
A Real-Time Deep Network for Crowd Counting
Automatic analysis of highly crowded people has attracted extensive attention from computer vision research.
THUEE system description for NIST 2019 SRE CTS Challenge
This paper describes the systems submitted by the department of electronic engineering, institute of microelectronics of Tsinghua university and TsingMicro Co. Ltd. (THUEE) to the NIST 2019 speaker recognition evaluation CTS challenge.
Cascaded Detail-Preserving Networks for Super-Resolution of Document Images
The accuracy of OCR is usually affected by the quality of the input document image and different kinds of marred document images hamper the OCR results.
Scene Text Recognition with Temporal Convolutional Encoder
In this paper, we study text recognition framework by considering the long-term temporal dependencies in the encoder stage.
Fast Video Crowd Counting with a Temporal Aware Network
Crowd counting aims to count the number of instantaneous people in a crowded space, and many promising solutions have been proposed for single image crowd counting.
Edge-Aware Deep Image Deblurring
In this paper, we resort to human visual demands of sharp edges and propose a two-phase edge-aware deep network to improve deep image deblurring.
Exploiting Noisy Data in Distant Supervision Relation Classification
Distant supervision has obtained great progress on relation classification task.
Adaptive Scenario Discovery for Crowd Counting
Crowd counting, i. e., estimation number of the pedestrian in crowd images, is emerging as an important research problem with the public security applications.
Multiobjective Optimization Training of PLDA for Speaker Verification
Most current state-of-the-art text-independent speaker verification systems take probabilistic linear discriminant analysis (PLDA) as their backend classifiers.
Multiobjective Optimization
Text-Independent Speaker Verification
EmojiIt at SemEval-2018 Task 2: An Effective Attention-Based Recurrent Neural Network Model for Emoji Prediction with Characters Gated Words
This paper presents our single model to Subtask 1 of SemEval 2018 Task 2: Emoji Prediction in English.
Precise Temporal Action Localization by Evolving Temporal Proposals
The performances of existing action localization approaches remain unsatisfactory in precisely determining the beginning and the end of an action.
MTGAN: Speaker Verification through Multitasking Triplet Generative Adversarial Networks
In this paper, we propose an enhanced triplet method that improves the encoding process of embeddings by jointly utilizing generative adversarial mechanism and multitasking optimization.
Sound Audio and Speech Processing
Comparison of Multiple Features and Modeling Methods for Text-dependent Speaker Verification
Additionally, we also find that even though bottleneck features perform well for text-independent speaker verification, they do not outperform MFCCs on the most challenging Imposter-Correct trials on RedDots.
