Search Results for author:
Found 142 papers, 68 papers with code
基于迭代信息传递和滑动窗口注意力的问题生成模型研究(Question Generation Model Based on Iterative Message Passing and Sliding Windows Hierarchical Attention)
“知识图谱问题生成任务是从给定的知识图谱中生成与其相关的问题。目前, 知识图谱问题生成模型主要使用基于RNN或Transformer对知识图谱子图进行编码, 但这种方式丢失了显式的图结构化信息, 在解码器中忽视了局部信息对节点的重要性。本文提出迭代信息传递图编码器来编码子图, 获取子图显式的图结构化信息, 此外, 我们还使用滑动窗口注意力机制提高RNN解码器, 提升子图局部信息对节点的重要度。从WQ和PQ数据集上的实验结果看, 我们提出的模型比KTG模型在BLEU4指标上分别高出2. 16和15. 44, 证明了该模型的有效性。”
InspireMusic: Integrating Super Resolution and Large Language Model for High-Fidelity Long-Form Music Generation
This framework enables the controllable generation of high-fidelity long-form music at a higher sampling rate from both text and audio prompts.
UniCodec: Unified Audio Codec with Single Domain-Adaptive Codebook
The emergence of audio language models is empowered by neural audio codecs, which establish critical mappings between continuous waveforms and discrete tokens compatible with language model paradigms.
LED-Merging: Mitigating Safety-Utility Conflicts in Model Merging with Location-Election-Disjoint
Fine-tuning pre-trained Large Language Models (LLMs) for specialized tasks incurs substantial computational and data costs.
Ten Challenging Problems in Federated Foundation Models
This paper provides a comprehensive summary of the ten challenging problems inherent in FedFMs, encompassing foundational theory, utilization of private data, continual learning, unlearning, Non-IID and graph data, bidirectional knowledge transfer, incentive mechanism design, game mechanism design, model watermarking, and efficiency.
Optimal Algorithms in Linear Regression under Covariate Shift: On the Importance of Precondition
For (i), we prove that the optimal estimator can be simply a certain linear transformation of the best estimator for the source distribution.
When GNNs meet symmetry in ILPs: an orbit-based feature augmentation approach
In this work, we investigate the properties of permutation equivariance and invariance in GNNs, particularly in relation to the inherent symmetry of ILP formulations.
MinMo: A Multimodal Large Language Model for Seamless Voice Interaction
Previous models for voice interactions are categorized as native and aligned.
V2C-CBM: Building Concept Bottlenecks with Vision-to-Concept Tokenizer
Concept Bottleneck Models (CBMs) offer inherent interpretability by initially translating images into human-comprehensible concepts, followed by a linear combination of these concepts for classification.
KaLM-Embedding: Superior Training Data Brings A Stronger Embedding Model
As retrieval-augmented generation prevails in large language models, embedding models are becoming increasingly crucial.
FedMeld: A Model-dispersal Federated Learning Framework for Space-ground Integrated Networks
By decomposing the problem into sequential SC and MR subproblems without compromising the optimality, we derive the round interval solution in a closed form and the mixing ratio in a semi-closed form to achieve the \textit{optimal} latency-accuracy tradeoff.
Zero-Shot Artifact2Artifact: Self-incentive artifact removal for photoacoustic imaging without any data
However, the quality of 3D PAI is often degraded due to reconstruction artifacts caused by the sparse and angle-limited configuration of detector arrays.
CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models
By training on a large-scale multilingual dataset, CosyVoice 2 achieves human-parity naturalness, minimal response latency, and virtually lossless synthesis quality in the streaming mode.
4D SlingBAG: spatial-temporal coupled Gaussian ball for large-scale dynamic 3D photoacoustic iterative reconstruction
However, for existing IR algorithms, multi-frame 3D reconstruction leads to extremely high memory consumption and prolonged computation time, with limited consideration of the spatial-temporal continuity between data frames.
Concept Based Continuous Prompts for Interpretable Text Classification
Continuous prompts have become widely adopted for augmenting performance across a wide range of natural language tasks.
DNN Task Assignment in UAV Networks: A Generative AI Enhanced Multi-Agent Reinforcement Learning Approach
Unmanned Aerial Vehicles (UAVs) possess high mobility and flexible deployment capabilities, prompting the development of UAVs for various application scenarios within the Internet of Things (IoT).
DECRL: A Deep Evolutionary Clustering Jointed Temporal Knowledge Graph Representation Learning Approach
To this end, we propose a Deep Evolutionary Clustering jointed temporal knowledge graph Representation Learning approach (DECRL).
LogSHIELD: A Graph-based Real-time Anomaly Detection Framework using Frequency Analysis
We present a real-time threat detection approach using frequency-domain analysis of provenance graphs.
OmniFlatten: An End-to-end GPT Model for Seamless Voice Conversation
However, achieving low latency and natural interactions in full-duplex dialogue systems remains a significant challenge, especially considering human conversation dynamics such as interruptions, backchannels, and overlapping speech.
Machine Unlearning in Forgettability Sequence
Machine unlearning (MU) is becoming a promising paradigm to achieve the "right to be forgotten", where the training trace of any chosen data points could be eliminated, while maintaining the model utility on general testing samples after unlearning.
IntrinsicVoice: Empowering LLMs with Intrinsic Real-time Voice Interaction Abilities
Current methods of building LLMs with voice interaction capabilities rely heavily on explicit text autoregressive generation before or during speech response generation to maintain content quality, which unfortunately brings computational overhead and increases latency in multi-turn interactions.
Unified Audio Event Detection
Sound Event Detection (SED) detects regions of sound events, while Speaker Diarization (SD) segments speech conversations attributed to individual speakers.
Thermal3D-GS: Physics-induced 3D Gaussians for Thermal Infrared Novel-view Synthesis
However, thermal infrared imaging is influenced by physical characteristics such as atmospheric transmission effects and thermal conduction, hindering the precise reconstruction of intricate details in thermal infrared scenes, manifesting as issues of floaters and indistinct edge features in synthesized images.
WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling
Despite the reduced number of tokens, WavTokenizer achieves state-of-the-art reconstruction quality with outstanding UTMOS scores and inherently contains richer semantic information.
Integrating Audio, Visual, and Semantic Information for Enhanced Multimodal Speaker Diarization
Then we introduce a joint pairwise constraint propagation algorithm to cluster speakers based on these visual and semantic constraints.
Recording for Eyes, Not Echoing to Ears: Contextualized Spoken-to-Written Conversion of ASR Transcripts
To improve readability, we propose a Contextualized Spoken-to-Written conversion (CoS2W) task to address ASR and grammar errors and also transfer the informal text into the formal style with content preserved, utilizing contexts and auxiliary information.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Multimodal Fusion and Coherence Modeling for Video Topic Segmentation
In this work, we improve supervised VTS by thoroughly exploring multimodal fusion and multimodal coherence modeling.
Efficient Sampling for Data-Driven Frequency Stability Constraint via Forward-Mode Automatic Differentiation
Encoding frequency stability constraints in the operation problem is challenging due to its complex dynamics.
Sliding Gaussian ball adaptive growth (SlingBAG): point cloud-based iterative algorithm for large-scale 3D photoacoustic imaging
Large-scale 3D photoacoustic (PA) imaging has become increasingly important for both clinical and pre-clinical applications.
CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens
Based on the tokens, we further propose a scalable zero-shot TTS synthesizer, CosyVoice, which consists of an LLM for text-to-token generation and a conditional flow matching model for token-to-speech synthesis.
FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs
This report introduces FunAudioLLM, a model family designed to enhance natural voice interactions between humans and large language models (LLMs).
Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application
Through in-depth understanding of the latest advancements and practical applications, this survey provides valuable resources for researchers, paving the way for sustained progress in this field.
Low-Rank Mixture-of-Experts for Continual Medical Image Segmentation
However, the incorrect pseudo-labels may corrupt the learned feature and lead to a new problem that the better the model is trained on the old task, the poorer the model performs on the new tasks.
ClinicalLab: Aligning Agents for Multi-Departmental Clinical Diagnostics in the Real World
Existing clinical diagnostic evaluation benchmarks for evaluating medical agents powered by LLMs have severe limitations.
Skip-Layer Attention: Bridging Abstract and Detailed Dependencies in Transformers
The Transformer architecture has significantly advanced deep learning, particularly in natural language processing, by effectively managing long-range dependencies.
Self-Distillation Prototypes Network: Learning Robust Speaker Representations without Supervision
SDPN assigns the representation of the augmented views of an utterance to the same prototypes as the representation of the original view, thereby enabling effective knowledge transfer between the views.
PDHG-Unrolled Learning-to-Optimize Method for Large-Scale Linear Programming
In this work, we propose an FOM-unrolled neural network (NN) called PDHG-Net, and propose a two-stage L2O method to solve large-scale LP problems.
ERes2NetV2: Boosting Short-Duration Speaker Verification Performance with Computational Efficiency
Speaker verification systems experience significant performance degradation when tasked with short-duration trial recordings.
ControlSpeech: Towards Simultaneous Zero-shot Speaker Cloning and Zero-shot Language Style Control With Decoupled Codec
In this paper, we present ControlSpeech, a text-to-speech (TTS) system capable of fully cloning the speaker's voice and enabling arbitrary control and adjustment of speaking style, merely based on a few seconds of audio prompt and a simple textual style description prompt.
CodeHalu: Investigating Code Hallucinations in LLMs via Execution-based Verification
By evaluating 17 popular LLMs using this benchmark, we reveal significant differences in their accuracy and reliability in code generation, offering detailed insights for further improving the code generation capabilities of LLMs.
3D-Speaker-Toolkit: An Open-Source Toolkit for Multimodal Speaker Verification and Diarization
With 3D-Speaker-Toolkit, we establish a new benchmark for multimodal speaker analysis.
PE: A Poincare Explanation Method for Fast Text Hierarchy Generation
The research focus has shifted to Hierarchical Attribution (HA) for its ability to model feature interactions.
Digital Twin-Empowered Task Assignment in Aerial MEC Network: A Resource Coalition Cooperation Approach with Generative Model
Moreover, the resource mutual exclusion problem of dynamic task assignment has not been effectively solved.
Interpreting What Typical Fault Signals Look Like via Prototype-matching
To understand the classification logic and explain what typical fault signals look like, the prototype matching network (PMN) is proposed by combining the human-inherent prototype-matching with autoencoder (AE).
EasyRL4Rec: An Easy-to-use Library for Reinforcement Learning Based Recommender Systems
EasyRL4Rec seeks to facilitate the model development and experimental process in the domain of RL-based RSs.
Language-Codec: Reducing the Gaps Between Discrete Codec Representation and Speech Language Models
Furthermore, we also validate the efficiency of the Language-Codec on downstream speech language models.
An Embarrassingly Simple Approach for LLM with Strong ASR Capacity
We found that delicate designs are not necessary, while an embarrassingly simple composition of off-the-shelf speech encoder, LLM, and the only trainable linear projector is competent for the ASR task.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
CIDR: A Cooperative Integrated Dynamic Refining Method for Minimal Feature Removal Problem
The minimal feature removal problem in the post-hoc explanation area aims to identify the minimal feature set (MFS).
CodeScope: An Execution-based Multilingual Multitask Multidimensional Benchmark for Evaluating LLMs on Code Understanding and Generation
Finally, we systematically evaluate and analyze eight mainstream LLMs and demonstrate the superior breadth and challenges of CodeScope for evaluating LLMs on code understanding and generation tasks compared to other benchmarks.
Loss Masking Is Not Needed in Decoder-only Transformer for Discrete-token-based ASR
We find that applying the conventional cross-entropy loss on input speech tokens does not consistently improve the ASR performance over the Loss Masking approach.
Imaging through multimode fibres with physical prior
The role of the physical prior is to simplify the mapping relationship between the speckle pattern and the target image, thereby reducing the computational complexity.
Differentially Private Pre-Trained Model Fusion using Decentralized Federated Graph Matching
Model fusion is becoming a crucial component in the context of model-as-a-service scenarios, enabling the delivery of high-quality model services to local users.
Improving Long Document Topic Segmentation Models With Enhanced Coherence Modeling
Our approach improve $F_1$ of old SOTA by 3. 42 (73. 74 -> 77. 16) and reduces $P_k$ by 1. 11 points (15. 0 -> 13. 89) on WIKI-727K and achieves an average relative reduction of 4. 3% on $P_k$ on WikiSection.
MeKB-Rec: Personal Knowledge Graph Learning for Cross-Domain Recommendation
Then we learn a semantic representation of MeKB for the cross-domain recommendation.
PAGE: Equilibrate Personalization and Generalization in Federated Learning
Federated learning (FL) is becoming a major driving force behind machine learning as a service, where customers (clients) collaboratively benefit from shared local updates under the orchestration of the service provider (server).
CodeTransOcean: A Comprehensive Multilingual Benchmark for Code Translation
To advance research on code translation and meet diverse requirements of real-world applications, we construct CodeTransOcean, a large-scale comprehensive benchmark that supports the largest variety of programming languages for code translation.
ITRE: Low-light Image Enhancement Based on Illumination Transmission Ratio Estimation
In this paper, we propose a novel Retinex-based method, called ITRE, which suppresses noise and artifacts from the origin of the model, prevents over-exposure throughout the enhancement process.
LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT
Previous mainstream audio-and-text LLMs use discrete audio tokens to represent both input and output audio; however, they suffer from performance degradation on tasks such as automatic speech recognition, speech-to-text translation, and speech enhancement over models using continuous speech features.
FLEDGE: Ledger-based Federated Learning Resilient to Inference and Backdoor Attacks
Federated learning (FL) is a distributed learning process that uses a trusted aggregation server to allow multiple parties (or clients) to collaboratively train a machine learning model without having them share their private data.
Multi-level Asymmetric Contrastive Learning for Volumetric Medical Image Segmentation Pre-training
Moreover, we develop a multi-level contrastive learning strategy that integrates correspondences across feature-level, image-level, and pixel-level representations to ensure the encoder and decoder capture comprehensive details from representations of varying scales and granularities during the pre-training phase.
Leveraging Speech PTM, Text LLM, and Emotional TTS for Speech Emotion Recognition
In this paper, we explored how to boost speech emotion recognition (SER) with the state-of-the-art speech pre-trained model (PTM), data2vec, text generation technique, GPT-4, and speech synthesis technique, Azure TTS.
Improving Speaker Diarization using Semantic Information: Joint Pairwise Constraints Propagation
Speaker diarization has gained considerable attention within speech processing research community.
Twofold Structured Features-Based Siamese Network for Infrared Target Tracking
Nowadays, infrared target tracking has been a critical technology in the field of computer vision and has many applications, such as motion analysis, pedestrian surveillance, intelligent detection, and so forth.
Branches Mutual Promotion for End-to-End Weakly Supervised Semantic Segmentation
Existing methods adopt an online-trained classification branch to provide pseudo annotations for supervising the segmentation branch.
Self-Distillation Prototypes Network: Learning Robust Speaker Representations without Supervision
To mitigate this problem, we introduce a diversity regularization term to embeddings in SDPN.
Improving BERT with Hybrid Pooling Network and Drop Mask
Transformer-based pre-trained language models, such as BERT, achieve great success in various natural language understanding tasks.
FedBone: Towards Large-Scale Federated Multi-Task Learning
The conflicting gradient projection technique is used to enhance the generalization of the large-scale general model between different tasks.
3D-Speaker: A Large-Scale Multi-Device, Multi-Distance, and Multi-Dialect Corpus for Speech Representation Disentanglement
Disentangling uncorrelated information in speech utterances is a crucial research topic within speech community.
Exploiting Correlations Between Contexts and Definitions with Multiple Definition Modeling
In this paper, we carefully design a new task called Multiple Definition Modeling (MDM) that pool together all contexts and definition of target words.
Advancing Precise Outline-Conditioned Text Generation with Task Duality and Explicit Outline Control
Furthermore, we identify an issue of imbalanced utilization of the outline information in the precise outline-conditioned generation, which is ubiquitously observed across fine-tuned models and zero-shot inference models.
BA-SOT: Boundary-Aware Serialized Output Training for Multi-Talker ASR
The recently proposed serialized output training (SOT) simplifies multi-talker automatic speech recognition (ASR) by generating speaker transcriptions separated by a special token.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Exploring Speaker-Related Information in Spoken Language Understanding for Better Speaker Diarization
In this paper, we propose methods to extract speaker-related information from semantic content in multi-party meetings, which, as we will show, can further benefit speaker diarization.
An Enhanced Res2Net with Local and Global Feature Fusion for Speaker Verification
This paper proposes a novel architecture called Enhanced Res2Net (ERes2Net), which incorporates both local and global feature fusion techniques to improve the performance.
Semantic VAD: Low-Latency Voice Activity Detection for Speech Interaction
For speech interaction, voice activity detection (VAD) is often used as a front-end.
CASA-ASR: Context-Aware Speaker-Attributed ASR
In addition, a two-pass decoding strategy is further proposed to fully leverage the contextual modeling ability resulting in a better recognition performance.
Ditto: A Simple and Efficient Approach to Improve Sentence Embeddings
Prior studies diagnose the anisotropy problem in sentence representations from pre-trained language models, e. g., BERT, without fine-tuning.
Hyperspectral Image Super-Resolution via Dual-domain Network Based on Hybrid Convolution
Moreover, to further improve the perceptual quality of HSI, a frequency loss(HFL) is introduced to optimize the model in the frequency domain.
PointCAT: Cross-Attention Transformer for point cloud
Transformer-based models have significantly advanced natural language processing and computer vision in recent years.
Meeting Action Item Detection with Regularized Context Modeling
We construct and release the first Chinese meeting corpus with manual action item annotations.
Overview of the ICASSP 2023 General Meeting Understanding and Generation Challenge (MUG)
ICASSP2023 General Meeting Understanding and Generation Challenge (MUG) focuses on prompting a wide range of spoken language processing (SLP) research on meeting transcripts, as SLP applications are critical to improve users' efficiency in grasping important information in meetings.
MUG: A General Meeting Understanding and Generation Benchmark
To prompt SLP advancement, we establish a large-scale general Meeting Understanding and Generation Benchmark (MUG) to benchmark the performance of a wide range of SLP tasks, including topic segmentation, topic-level and session-level extractive summarization and topic title generation, keyphrase extraction, and action item detection.
Adaptive Knowledge Distillation between Text and Speech Pre-trained Models
Learning on a massive amount of speech corpus leads to the recent success of many self-supervised speech models.
Weighted Sampling for Masked Language Modeling
Experiments on the Semantic Textual Similarity benchmark (STS) show that WSBERT significantly improves sentence embeddings over BERT.
One-Pot Multi-Frame Denoising
Therefore, it is necessary to avoid the restriction of clean labels and make full use of noisy data for model training.
A Graphical Point Process Framework for Understanding Removal Effects in Multi-Touch Attribution
Marketers employ various online advertising channels to reach customers, and they are particularly interested in attribution for measuring the degree to which individual touchpoints contribute to an eventual conversion.
Enhancing Multi-modal and Multi-hop Question Answering via Structured Knowledge and Unified Retrieval-Generation
Moreover, the pipelined approaches of retrieval and generation might result in poor generation performance when retrieval performance is low.
DopplerBAS: Binaural Audio Synthesis Addressing Doppler Effect
Recently, binaural audio synthesis (BAS) has emerged as a promising research field for its applications in augmented and virtual realities.
MIMO Is All You Need : A Strong Multi-In-Multi-Out Baseline for Video Prediction
The mainstream of the existing approaches for video prediction builds up their models based on a Single-In-Single-Out (SISO) architecture, which takes the current frame as input to predict the next frame in a recursive manner.
Gradient Domain Weighted Guided Image Filtering
Guided image filter is a well-known local filter in image processing.
Language-Assisted Deep Learning for Autistic Behaviors Recognition
In such cases, automatic recognition systems based on computer vision and machine learning (in particular deep learning) technology can alleviate this issue to a large extent.
Pushing the limits of self-supervised speaker verification using regularized distillation framework
A range of experiments conducted on the VoxCeleb datasets demonstrate the superiority of the regularized DINO framework in speaker verification.
A Comparative Study on Multichannel Speaker-Attributed Automatic Speech Recognition in Multi-party Meetings
Speaker-attributed automatic speech recognition (SA-ASR) in multi-party meeting scenarios is one of the most valuable and challenging ASR task.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
TFN: An Interpretable Neural Network with Time-Frequency Transform Embedded for Intelligent Fault Diagnosis
However, the CNN is a typical black-box model, and the mechanism of CNN's decision-making are not clear, which limits its application in high-reliability-required fault diagnosis scenarios.
Bagging Regional Classification Activation Maps for Weakly Supervised Object Localization
Classification activation map (CAM), utilizing the classification structure to generate pixel-wise localization maps, is a crucial mechanism for weakly supervised object localization (WSOL).
DePA: Improving Non-autoregressive Machine Translation with Dependency-Aware Decoder
We propose a novel and general Dependency-Aware Decoder (DePA) to enhance target dependency modeling in the decoder of fully NAT models from two perspectives: decoder self-attention and decoder input.
Weakly Supervised Object Localization as Domain Adaption
To avoid this problem, this work provides a novel perspective that models WSOL as a domain adaption (DA) task, where the score estimator trained on the source/image domain is tested on the target/pixel domain to locate objects.
ProsoSpeech: Enhancing Prosody With Quantized Vector Pre-training in Text-to-Speech
Specifically, we first introduce a word-level prosody encoder, which quantizes the low-frequency band of the speech and compresses prosody attributes in the latent prosody vector (LPV).
Background-aware Classification Activation Map for Weakly Supervised Object Localization
In our B-CAM, two image-level features, aggregated by pixel-level features of potential background and object locations, are used to purify the object feature from the object-related background and to represent the feature of the pure-background sample, respectively.
Super-resolution reconstruction of cytoskeleton image based on A-net deep learning network
To date, live-cell imaging at the nanometer scale remains challenging.
MDERank: A Masked Document Embedding Rank Approach for Unsupervised Keyphrase Extraction
In this work, we propose a novel unsupervised embedding-based KPE approach, Masked Document Embedding Rank (MDERank), to address this problem by leveraging a mask strategy and ranking candidates by the similarity between embeddings of the source document and the masked document.
PoNet: Pooling Network for Efficient Token Mixing in Long Sequences
We propose a novel Pooling Network (PoNet) for token mixing in long sequences with linear complexity.
BeamTransformer: Microphone Array-based Overlapping Speech Detection
We propose BeamTransformer, an efficient architecture to leverage beamformer's edge in spatial filtering and transformer's capability in context sequence modeling.
Towards Making Deep Learning-based Vulnerability Detectors Robust
Automatically detecting software vulnerabilities in source code is an important problem that has attracted much attention.
From Single to Multiple: Leveraging Multi-level Prediction Spaces for Video Forecasting
Despite video forecasting has been a widely explored topic in recent years, the mainstream of the existing work still limits their models with a single prediction space but completely neglects the way to leverage their model with multi-prediction spaces.
Sequence Model with Self-Adaptive Sliding Window for Efficient Spoken Document Segmentation
Evaluations are conducted on the English Wiki-727K document segmentation benchmark, a Chinese Wikipedia-based document segmentation dataset we created, and an in-house Chinese spoken document dataset.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
TRS: Transferability Reduced Ensemble via Promoting Gradient Diversity and Model Smoothness
To answer these questions, in this work we first theoretically analyze and outline sufficient conditions for adversarial transferability between models; then propose a practical algorithm to reduce the transferability between base models within an ensemble to improve its robustness.
Learning Synergistic Attention for Light Field Salient Object Detection
We propose a novel Synergistic Attention Network (SA-Net) to address the light field salient object detection by establishing a synergistic effect between multi-modal features with advanced attention mechanisms.
Discriminative Self-training for Punctuation Prediction
Punctuation prediction for automatic speech recognition (ASR) output transcripts plays a crucial role for improving the readability of the ASR transcripts and for improving the performance of downstream natural language processing applications.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Pre-training for Spoken Language Understanding with Joint Textual and Phonetic Representation Learning
In this paper, we propose a novel joint textual-phonetic pre-training approach for learning spoken language representations, aiming at exploring the full potentials of phonetic information to improve SLU robustness to ASR errors.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+7
TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothness
To answer these questions, in this work we first theoretically analyze and outline sufficient conditions for adversarial transferability between models; then propose a practical algorithm to reduce the transferability between base models within an ensemble to improve its robustness.
RGB-D Salient Object Detection via 3D Convolutional Neural Networks
The proposed model, named RD3D, aims at pre-fusion in the encoder stage and in-depth fusion in the decoder stage to effectively promote the full integration of RGB and depth streams.
Multi-feature driven active contour segmentation model for infrared image with intensity inhomogeneity
Active contour model (ACM) is one of the most widely used image segmentation tools at present, but the existing methods only utilize the local or global single feature information of image to minimize the energy function, which is easy to cause false segmentations in IR images.
FinRL: A Deep Reinforcement Learning Library for Automated Stock Trading in Quantitative Finance
In this paper, we introduce a DRL library FinRL that facilitates beginners to expose themselves to quantitative finance and to develop their own stock trading strategies.
EF-Net: A novel enhancement and fusion network for RGB-D saliency detection
Finally, we propose an effective layer-wise aggregation module to fuse the features extracted from the enhanced depth maps and RGB images for the accurate detection of salient objects.
Infrared target tracking based on proximal robust principal component analysis method
Infrared target tracking plays an important role in both civil and military fields.
Controllable Time-Delay Transformer for Real-Time Punctuation Prediction and Disfluency Detection
With the increased applications of automatic speech recognition (ASR) in recent years, it is essential to automatically insert punctuation marks and remove disfluencies in transcripts, to improve the readability of the transcripts as well as the performance of subsequent applications, such as machine translation, dialogue systems, and so forth.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Sequential Neural Networks for Noetic End-to-End Response Selection
The noetic end-to-end response selection challenge as one track in the 7th Dialog System Technology Challenges (DSTC7) aims to push the state of the art of utterance classification for real world goal-oriented dialog systems, for which participants need to select the correct next utterances from a set of candidates for the multi-turn context.
Transfer Learning for Context-Aware Spoken Language Understanding
We explore different transfer learning approaches to reduce dependency on data collection and annotation.
Spoken Language Understanding
Task-Oriented Dialogue Systems
+2
Dual Adversarial Domain Adaptation
Recent experiments have shown that when the discriminator is provided with domain information in both domains and label information in the source domain, it is able to preserve the complex multimodal information and high semantic information in both domains.
Ranked #6 on
Domain Adaptation
on ImageCLEF-DA
Homogeneous Online Transfer Learning with Online Distribution Discrepancy Minimization
In this paper, we propose a novel online transfer learning method which seeks to find a new feature representation, so that the marginal distribution and conditional distribution discrepancy can be online reduced simultaneously.
T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack
In particular, we propose a tree-based autoencoder to embed the discrete text data into a continuous representation space, upon which we optimize the adversarial perturbation.
ColluEagle: Collusive review spammer detection using Markov random fields
Previous works use review network effects, i. e. the relationships among reviewers, reviews, and products, to detect fake reviews or review spammers, but ignore time effects, which are critical in characterizing group spamming.
Align, Mask and Select: A Simple Method for Incorporating Commonsense Knowledge into Language Representation Models
We also observe that fine-tuned models after the proposed pre-training approach maintain comparable performance on other NLP tasks, such as sentence classification and natural language inference tasks, compared to the original BERT models.
Ranked #27 on
Common Sense Reasoning
on CommonsenseQA
Gift Contagion in Online Groups: Evidence From Virtual Red Packets
Using data on 36 million online red packet gifts on a large social site in East Asia, we leverage a natural experimental design to identify the social contagion of gift giving in online groups.
Several Experiments on Investigating Pretraining and Knowledge-Enhanced Models for Natural Language Inference
Natural language inference (NLI) is among the most challenging tasks in natural language understanding.
High-speed in vitro intensity diffraction tomography
We demonstrate a label-free, scan-free {\it intensity} diffraction tomography technique utilizing annular illumination (aIDT) to rapidly characterize large-volume 3D refractive index distributions in vitro.
Optics Biological Physics
BERT for Joint Intent Classification and Slot Filling
Intent classification and slot filling are two essential tasks for natural language understanding.
Ranked #3 on
Slot Filling
on ATIS
Sequential Attention-based Network for Noetic End-to-End Response Selection
The noetic end-to-end response selection challenge as one track in Dialog System Technology Challenges 7 (DSTC7) aims to push the state of the art of utterance classification for real world goal-oriented dialog systems, for which participants need to select the correct next utterances from a set of candidates for the multi-turn context.
Ranked #1 on
Conversational Response Selection
on Advising Corpus
Thermal Infrared Colorization via Conditional Generative Adversarial Network
Transforming a thermal infrared image into a realistic RGB image is a challenging task.
A Semi-parametric Realized Joint Value-at-Risk and Expected Shortfall Regression Framework
One-day-ahead VaR and ES forecasting results favor the proposed models, especially when incorporating the sub-sampled Realized Variance and the sub-sampled Realized Range in the model.
Enhancing Sentence Embedding with Generalized Pooling
This paper explores generalized pooling methods to enhance sentence embedding.
Ranked #10 on
Sentiment Analysis
on Yelp Fine-grained classification
Natural Language Inference with External Knowledge
Modeling informal inference in natural language is very challenging.
A Sequential Neural Encoder with Latent Structured Description for Modeling Sentences
The description layer utilizes modified LSTM units to process these chunk-level vectors in a recurrent manner and produces sequential encoding outputs.
Neural Natural Language Inference Models Enhanced with External Knowledge
With the availability of large annotated data, it has recently become feasible to train complex models such as neural-network-based inference models, which have shown to achieve the state-of-the-art performance.
Ranked #22 on
Natural Language Inference
on SNLI
Adaptive compressed 3D imaging based on wavelet trees and Hadamard multiplexing with a single photon counting detector
The proposed multi-resolution photon counting 3D imaging technique acquires a high-resolution 3D image from a coarse image and edges at successfully finer resolution sampled by Hadamard multiplexing along the wavelet trees.
Recurrent Neural Network-Based Sentence Encoder with Gated Attention for Natural Language Inference
The RepEval 2017 Shared Task aims to evaluate natural language understanding models for sentence representation, in which a sentence is represented as a fixed-length vector with neural networks and the quality of the representation is tested with a natural language inference task.
Ranked #71 on
Natural Language Inference
on SNLI
Natural Language Inference
Natural Language Understanding
+1
Micro Fourier Transform Profilometry ($μ$FTP): 3D shape measurement at 10,000 frames per second
Recent advances in imaging sensors and digital light projection technology have facilitated a rapid progress in 3D optical sensing, enabling 3D surfaces of complex-shaped objects to be captured with improved resolution and accuracy.
Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering
The last several years have seen intensive interest in exploring neural-network-based models for machine comprehension (MC) and question answering (QA).
Ranked #39 on
Question Answering
on SQuAD1.1 dev
Distraction-Based Neural Networks for Document Summarization
Distributed representation learned with neural networks has recently shown to be effective in modeling natural languages at fine granularities such as words, phrases, and even sentences.
Enhanced LSTM for Natural Language Inference
Reasoning and inference are central to human and artificial intelligence.
Ranked #32 on
Natural Language Inference
on SNLI
