Search Results for author:
Found 74 papers, 28 papers with code
Transformer with Syntactic Position Encoding for Machine Translation
It has been widely recognized that syntax information can help end-to-end neural machine translation (NMT) systems to achieve better translation.
Self Question-answering: Aspect-based Sentiment Analysis by Role Flipped Machine Reading Comprehension
In this paper, we investigate the unified ABSA task from the perspective of Machine Reading Comprehension (MRC) by observing that the aspect and the opinion terms can serve as the query and answer in MRC interchangeably.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+3
Panoramic Interests: Stylistic-Content Aware Personalized Headline Generation
Prevailing methods focus on user-oriented content preferences, but most of them overlook the fact that diverse stylistic preferences are integral to users' panoramic interests, leading to suboptimal personalization.
Controlling Large Language Models Through Concept Activation Vectors
During inference, GCAV steers the concept vector in LLMs, for example, by removing the toxicity concept vector from the activation layers.
AI-Driven Reinvention of Hydrological Modeling for Accurate Predictions and Interpretation to Transform Earth System Modeling
Traditional equation-driven hydrological models often struggle to accurately predict streamflow in challenging regional Earth systems like the Tibetan Plateau, while hybrid and existing algorithm-driven models face difficulties in interpreting hydrological behaviors.
Get Large Language Models Ready to Speak: A Late-fusion Approach for Speech Generation
Finally, we further explore MoLE-Llama in text-in-speech-out QA tasks, demonstrating its great potential as a multimodal dialog system capable of speech generation.
The Llama 3 Herd of Models
This paper presents a new set of foundation models, called Llama 3.
Ranked #3 on
Question Answering
on PeerQA
Deep Neural Networks with Symplectic Preservation Properties
We propose a deep neural network architecture designed such that its output forms an invertible symplectomorphism of the input.
LOGIN: A Large Language Model Consulted Graph Neural Network Training Framework
In this paper, we aim to streamline the GNN design process and leverage the advantages of Large Language Models (LLMs) to improve the performance of GNNs on downstream tasks.
EFSA: Towards Event-Level Financial Sentiment Analysis
In this paper, we extend financial sentiment analysis~(FSA) to event-level since events usually serve as the subject of the sentiment in financial text.
Ultra-lightweight Neural Differential DSP Vocoder For High Quality Speech Synthesis
A DSP vocoder often gets a lower audio quality due to consuming over-smoothed acoustic model predictions of approximate representations for the vocal tract.
Multi-Task Learning for Front-End Text Processing in TTS
We propose a multi-task learning (MTL) model for jointly performing three tasks that are commonly solved in a text-to-speech (TTS) front-end: text normalization (TN), part-of-speech (POS) tagging, and homograph disambiguation (HD).
Generating Synergistic Formulaic Alpha Collections via Reinforcement Learning
In practice, a set of formulaic alphas is often used together for better modeling precision, so we need to find synergistic formulaic alpha sets that work well together.
Attacking Pre-trained Recommendation
Recently, a series of pioneer studies have shown the potency of pre-trained models in sequential recommendation, illuminating the path of building an omniscient unified pre-trained recommendation model for different downstream recommendation tasks.
Self-Supervised Representations for Singing Voice Conversion
A singing voice conversion model converts a song in the voice of an arbitrary source singer to the voice of a target singer.
Synthetic Cross-accent Data Augmentation for Automatic Speech Recognition
In this work, we improve an accent-conversion model (ACM) which transforms native US-English speech into accented pronunciation.
Voice-preserving Zero-shot Multiple Accent Conversion
Most people who have tried to learn a foreign language would have experienced difficulties understanding or speaking with a native speaker's accent.
Towards zero-shot Text-based voice editing using acoustic context conditioning, utterance embeddings, and reference encoders
Text-based voice editing (TBVE) uses synthetic output from text-to-speech (TTS) systems to replace words in an original recording.
Solving Coupled Differential Equation Groups Using PINO-CDE
This framework integrates engineering dynamics and deep learning technologies and may reveal a new concept for CDEs solving and uncertainty propagation.
Customized Conversational Recommender Systems
In this paper, we propose two key points for CRS to improve the user experience: (1) Speaking like a human, human can speak with different styles according to the current dialogue context.
Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNN
However, both strategies are faced with some immediate problems: raw features cannot represent various properties of nodes (e. g., structure information), and representations learned by supervised GNN may suffer from the poor performance of the classifier on the poisoned graph.
Personalized Prompt for Sequential Recommendation
Specifically, we build the personalized soft prefix prompt via a prompt generator based on user profiles and enable a sufficient training of prompts via a prompt-oriented contrastive learning with both prompt- and behavior-based augmentations.
User-Centric Conversational Recommendation with Multi-Aspect User Modeling
In this work, we highlight that the user's historical dialogue sessions and look-alike users are essential sources of user preferences besides the current dialogue session in CRS.
Ranked #3 on
Recommendation Systems
on ReDial
(Recall@50 metric)
CCAT-NET: A Novel Transformer Based Semi-supervised Framework for Covid-19 Lung Lesion Segmentation
In this work, we propose a novel network structure that combines CNN and Transformer for the segmentation of COVID-19 lesions.
Multi-view Multi-behavior Contrastive Learning in Recommendation
We argue that MBR models should: (1) model the coarse-grained commonalities between different behaviors of a user, (2) consider both individual sequence view and global graph view in multi-behavior modeling, and (3) capture the fine-grained differences between multiple behaviors of a user.
Modeling Users' Behavior Sequences with Hierarchical Explainable Network for Cross-domain Fraud Detection
Thus, in this paper, we further propose a transfer framework to tackle the cross-domain fraud detection problem, which aims to transfer knowledge from existing domains (source domains) with enough and mature data to improve the performance in the new domain (target domain).
Multi-Representation Adaptation Network for Cross-domain Image Classification
Based on this, we present Multi-Representation Adaptation Network (MRAN) to accomplish the cross-domain image classification task via multi-representation alignment which can capture the information from different aspects.
Domain Adaptation with Category Attention Network for Deep Sentiment Analysis
Domain adaptation tasks such as cross-domain sentiment classification aim to utilize existing labeled data in the source domain and unlabeled or few labeled data in the target domain to improve the performance in the target domain via reducing the shift between the data distributions.
Modelling of Bi-directional Spatio-Temporal Dependence and Users' Dynamic Preferences for Missing POI Check-in Identification
Then, target temporal pattern in combination with user and POI information are fed into a multi-layer network to capture users' dynamic preferences.
Exploiting Bi-directional Global Transition Patterns and Personal Preferences for Missing POI Category Identification
To this end, in this paper, we propose a novel neural network approach to identify the missing POI categories by integrating both bi-directional global non-personal transition patterns and personal preferences of users.
Neural Hierarchical Factorization Machines for User's Event Sequence Analysis
Many prediction tasks of real-world applications need to model multi-order feature interactions in user's event sequence for better detection performance.
Mind the Gap: Cross-Lingual Information Retrieval with Hierarchical Knowledge Enhancement
The proposed model encodes the textual information in queries, documents and the KG with multilingual BERT, and incorporates the KG information in the query-document matching process with a hierarchical information fusion mechanism.
VocBench: A Neural Vocoder Benchmark for Speech Synthesis
We perform a subjective and objective evaluation to compare the performance of each vocoder along a different axis.
Discerning Decision-Making Process of Deep Neural Networks with Hierarchical Voting Transformation
To this end, in this paper, we aim to discern the decision-making processes of neural networks through a hierarchical voting strategy by developing an explainable deep learning model, namely Voting Transformation-based Explainable Neural Network (VOTEN).
Towards Robust Knowledge Graph Embedding via Multi-task Reinforcement Learning
This will lead to low-quality and unreliable representations of KGs.
Personalized Transfer of User Preferences for Cross-domain Recommendation
Specifically, a meta network fed with users' characteristic embeddings is learned to generate personalized bridge functions to achieve personalized transfer of preferences for each user.
Rethinking Pareto Approaches in Constrained Reinforcement Learning
Constrained Reinforcement Learning (CRL) burgeons broad interest in recent years, which pursues both goals of maximizing long-term returns and constraining costs.
ConRPG: Paraphrase Generation using Contexts as Regularizer
A long-standing issue with paraphrase generation is how to obtain reliable supervision signals.
Follow the Prophet: Accurate Online Conversion Rate Prediction in the Face of Delayed Feedback
The delayed feedback problem is one of the imperative challenges in online advertising, which is caused by the highly diversified feedback delay of a conversion varying from a few minutes to several days.
PENS: A Dataset and Generic Framework for Personalized News Headline Generation
To build up a benchmark for this problem, we publicize a large-scale dataset named PENS (PErsonalized News headlineS).
GuideBoot: Guided Bootstrap for Deep Contextual Bandits
The proposed method is efficient as it can make decisions on-the-fly by utilizing only one randomly chosen model, but is also effective as we show that it can be viewed as a non-Bayesian approximation of Thompson sampling.
Direct speech-to-speech translation with discrete units
When target text transcripts are available, we design a joint speech and text training framework that enables the model to generate dual modality output (speech and text) simultaneously in the same inference pass.
ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information
Recent pretraining models in Chinese neglect two important aspects specific to the Chinese language: glyph and pinyin, which carry significant syntax and semantic information for language understanding.
Deep Subdomain Adaptation Network for Image Classification
The adaptation can be achieved easily with most feed-forward network models by extending them with LMMD loss, which can be trained efficiently via back-propagation.
AMA-GCN: Adaptive Multi-layer Aggregation Graph Convolutional Network for Disease Prediction
The encoder can automatically construct the population graph using phenotypic measures which have a positive impact on the final results, and further realizes the fusion of multimodal information.
Transfer-Meta Framework for Cross-domain Recommendation to Cold-Start Users
With the advantage of meta learning which has good generalization ability to novel tasks, we propose a transfer-meta framework for CDR (TMCDR) which has a transfer stage and a meta stage.
Pick and Choose: A GNN-based Imbalanced Learning Approach for Fraud Detection
Graph-based fraud detection approaches have escalated lots of attention recently due to the abundant relational information of graph-structured data, which may be beneficial for the detection of fraudsters.
Ranked #5 on
Fraud Detection
on Amazon-Fraud
Multi-rate attention architecture for fast streamable Text-to-speech spectrum modeling
Typical high quality text-to-speech (TTS) systems today use a two-stage architecture, with a spectrum model stage that generates spectral frames and a vocoder stage that generates the actual audio.
Combat Data Shift in Few-shot Learning with Knowledge Graph
However, in real-world applications, few-shot learning paradigm often suffers from data shift, i. e., samples in different tasks, even in the same task, could be drawn from various data distributions.
FBWave: Efficient and Scalable Neural Vocoders for Streaming Text-To-Speech on the Edge
More efficient variants of FBWave can achieve up to 109x fewer MACs while still delivering acceptable audio quality.
Trust the Model When It Is Confident: Masked Model-based Actor-Critic
In complex and noisy settings, model-based RL tends to have trouble using the model if it does not know when to trust the model.
Modeling the Field Value Variations and Field Interactions Simultaneously for Fraud Detection
In this paper, we propose the Dual Importance-aware Factorization Machines (DIFM), which exploits the internal field information among users' behavior sequence from dual perspectives, i. e., field value variations and field interactions simultaneously for fraud detection.
Graph Factorization Machines for Cross-Domain Recommendation
In this paper, we propose a Graph Factorization Machine (GFM) which utilizes the popular Factorization Machine to aggregate multi-order interactions from neighborhood for recommendation.
A Survey on Knowledge Graph-Based Recommender Systems
On the one hand, we investigate the proposed algorithms by focusing on how the papers utilize the knowledge graph for accurate and explainable recommendation.
Transfer Learning Toolkit: Primers and Benchmarks
The transfer learning toolkit wraps the codes of 17 transfer learning models and provides integrated interfaces, allowing users to use those models by calling a simple function.
A Comprehensive Survey on Transfer Learning
In order to show the performance of different transfer learning models, over twenty representative transfer learning models are used for experiments.
Reading Like HER: Human Reading Inspired Extractive Summarization
In this work, we re-examine the problem of extractive text summarization for long documents.
Ranked #8 on
Extractive Text Summarization
on CNN / Daily Mail
Efficient and Adaptive Kernelization for Nonlinear Max-margin Multi-view Learning
Existing multi-view learning methods based on kernel function either require the user to select and tune a single predefined kernel or have to compute and store many Gram matrices to perform multiple kernel learning.
Learning beyond Predefined Label Space via Bayesian Nonparametric Topic Modelling
In real world machine learning applications, testing data may contain some meaningful new categories that have not been seen in labeled training data.
Unsupervised Neural Aspect Extraction with Sememes
Aspect extraction relies on identifying aspects by discovering coherence among words, which is challenging when word meanings are diversified and processing on short texts.
Aspect Extraction
Aspect Term Extraction and Sentiment Classification
+1
Deep Learning Detection of Inaccurate Smart Electricity Meters: A Case Study
Detecting inaccurate smart meters and targeting them for replacement can save significant resources.
Field-aware Calibration: A Simple and Empirically Strong Method for Reliable Probabilistic Predictions
It is often observed that the probabilistic predictions given by a machine learning model can disagree with averaged actual outcomes on specific subsets of data, which is also known as the issue of miscalibration.
Atom Responding Machine for Dialog Generation
To enrich the generated responses, ARM introduces a large number of molecule-mechanisms as various responding styles, which are conducted by taking different combinations from a few atom-mechanisms.
Warm Up Cold-start Advertisements: Improving CTR Predictions via Learning to Learn ID Embeddings
We propose Meta-Embedding, a meta-learning-based approach that learns to generate desirable initial embeddings for new ad IDs.
A Fast, Semi-Automatic Brain Structure Segmentation Algorithm for Magnetic Resonance Imaging
Medical image segmentation has become an essential technique in clinical and research-oriented applications.
Web Based Brain Volume Calculation for Magnetic Resonance Images
Brain volume calculations are crucial in modern medical research, especially in the study of neurodevelopmental disorders.
Policy Optimization with Model-based Explorations
Model-free reinforcement learning methods such as the Proximal Policy Optimization algorithm (PPO) have successfully applied in complex decision-making problems such as Atari games.
Knowledge Graph Embedding with Hierarchical Relation Structure
To this end, in this paper, we extend existing KGE models TransE, TransH and DistMult, to learn knowledge representations by leveraging the information from the HRS.
Hierarchical Neural Network for Extracting Knowledgeable Snippets and Documents
Additionally, a "low-level sharing, high-level splitting" structure of CNN is designed to handle the documents from different content domains.
Free-rider Episode Screening via Dual Partition Model
An effective technique for filtering free-rider episodes is using a partition model to divide an episode into two consecutive subepisodes and comparing the observed support of such episode with its expected support under the assumption that these two subepisodes occur independently.
Policy Gradients for Contextual Recommendations
We evaluate PGCR on toy datasets as well as a real-world dataset of personalized music recommendations.
Tree-Structured Neural Machine for Linguistics-Aware Sentence Generation
Then, with a proposed tree-structured search method, the model is able to generate the most probable responses in the form of dependency trees, which are finally flattened into sequences as the system output.
