Search Results for author:
Found 62 papers, 28 papers with code
Counterfactual Matters: Intrinsic Probing For Dialogue State Tracking
Our findings are: the performance variance of generative DSTs is not only due to the model structure itself, but can be attributed to the distribution of cross-domain values.
Understanding LLMs' Cross-Lingual Context Retrieval: How Good It Is And Where It Comes From
The ability of cross-lingual context retrieval is a fundamental aspect of cross-lingual alignment of large language models (LLMs), where the model extracts context information in one language based on requests in another language.
Investigating and Scaling up Code-Switching for Multilingual Language Model Pre-Training
Large language models (LLMs) exhibit remarkable multilingual capabilities despite the extreme language imbalance in the pre-training data.
A Comprehensive Survey on Long Context Language Modeling
With the growing number of long documents, dialogues, and other textual data, it is important to develop Long Context Language Models (LCLMs) that can process and analyze extensive inputs in an effective and efficient way.
Palette of Language Models: A Solver for Controlled Text Generation
Recent advancements in large language models have revolutionized text generation with their remarkable capabilities.
SafeDialBench: A Fine-Grained Safety Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks
With the rapid advancement of Large Language Models (LLMs), the safety of LLMs has been a critical concern requiring precise assessment.
Harnessing Diverse Perspectives: A Multi-Agent Framework for Enhanced Error Detection in Knowledge Graphs
For specific industrial scenarios, our framework can facilitate the training of specialized agents using domain-specific knowledge graphs for error detection, which highlights the potential industrial application value of our framework.
Uni-AdaFocus: Spatial-temporal Dynamic Computation for Video Recognition
This paper presents a comprehensive exploration of the phenomenon of data redundancy in video understanding, with the aim to improve computational efficiency.
MoE-LPR: Multilingual Extension of Large Language Models through Mixture-of-Experts with Language Priors Routing
Then, the model reviews the knowledge of the original languages with replay data amounting to less than 1% of post-pretraining, where we incorporate language priors routing to better recover the abilities of the original languages.
On Calibration of Speech Classification Models: Insights from Energy-Based Model Investigations
For speech classification tasks, deep learning models often achieve high accuracy but exhibit shortcomings in calibration, manifesting as classifiers exhibiting overconfidence.
Exploring Energy-Based Models for Out-of-Distribution Detection in Dialect Identification
The diverse nature of dialects presents challenges for models trained on specific linguistic patterns, rendering them susceptible to errors when confronted with unseen or out-of-distribution (OOD) data.
Large Language Models Are Cross-Lingual Knowledge-Free Reasoners
However, the relationship between capabilities in different languages is less explored.
CEC: A Noisy Label Detection Method for Speaker Recognition
In this paper, we propose a novel noisy label detection approach based on two new statistical metrics: Continuous Inconsistent Counting (CIC) and Total Inconsistent Counting (TIC).
PolySpeech: Exploring Unified Multitask Speech Models for Competitiveness with Single-task Models
Recently, there have been attempts to integrate various speech processing tasks into a unified model.
GenDistiller: Distilling Pre-trained Language Models based on an Autoregressive Generative Model
Pre-trained speech language models such as HuBERT and WavLM leverage unlabeled speech data for self-supervised learning and offer powerful representations for numerous downstream tasks.
EMERGE: Integrating RAG for Improved Multimodal EHR Predictive Modeling
However, current models that utilize clinical notes and multivariate time-series EHR data often lack the necessary medical context for precise clinical tasks.
Getting More from Less: Large Language Models are Good Spontaneous Multilingual Learners
Recently, Large Language Models (LLMs) have shown impressive language capabilities.
The 2nd FutureDial Challenge: Dialog Systems with Retrieval Augmented Generation (FutureDial-RAG)
Recently, increasing research interests have focused on retrieval augmented generation (RAG) to mitigate hallucination for large language models (LLMs).
InjectTST: A Transformer Method of Injecting Global Information into Independent Channels for Long Time Series Forecasting
A channel identifier, a global mixing module and a self-contextual attention module are devised in InjectTST.
Plugin Speech Enhancement: A Universal Speech Enhancement Framework Inspired by Dynamic Neural Network
In this study, we present a novel weighting prediction approach, which explicitly learns the task relationships from downstream training information to address the core challenge of universal speech enhancement.
Depth Map Denoising Network and Lightweight Fusion Network for Enhanced 3D Face Recognition
With the increasing availability of consumer depth sensors, 3D face recognition (FR) has attracted more and more attention.
Collaborative Word-based Pre-trained Item Representation for Transferable Recommendation
In this paper, we propose CoWPiRec, an approach of Collaborative Word-based Pre-trained item representation for Recommendation.
Prompt Pool based Class-Incremental Continual Learning for Dialog State Tracking
Inspired by the recently emerging prompt tuning method that performs well on dialog systems, we propose to use the prompt pool method, where we maintain a pool of key-value paired prompts and select prompts from the pool according to the distance between the dialog history and the prompt keys.
Cascaded Multi-task Adaptive Learning Based on Neural Architecture Search
Cascading multiple pre-trained models is an effective way to compose an end-to-end system.
GenDistiller: Distilling Pre-trained Language Models based on Generative Models
Self-supervised pre-trained models such as HuBERT and WavLM leverage unlabeled speech data for representation learning and offer significantly improve for numerous downstream tasks.
Fine-grained Recognition with Learnable Semantic Data Augmentation
Since images belonging to the same meta-category usually share similar visual appearances, mining discriminative visual cues is the key to distinguishing fine-grained categories.
Dynamic Perceiver for Efficient Visual Recognition
Early exits are placed exclusively within the classification branch, thus eliminating the need for linear separability in low-level features.
MPPN: Multi-Resolution Periodic Pattern Network For Long-Term Time Series Forecasting
To capture the intrinsic patterns of time series, we propose a novel deep learning network architecture, named Multi-resolution Periodic Pattern Network (MPPN), for long-term series forecasting.
MFSN: Multi-perspective Fusion Search Network For Pre-training Knowledge in Speech Emotion Recognition
Considering comprehensiveness, we partition speech knowledge into Textual-related Emotional Content (TEC) and Speech-related Emotional Content (SEC), capturing cues from both semantic and acoustic perspectives, and we design a new architecture search space to fully leverage them.
Healing Unsafe Dialogue Responses with Weak Supervision Signals
Recent years have seen increasing concerns about the unsafe response generation of large-scale dialogue systems, where agents will learn offensive or biased behaviors from the real-world corpus.
Knowledge-Retrieval Task-Oriented Dialog Systems with Semi-Supervision
Most existing task-oriented dialog (TOD) systems track dialog states in terms of slots and values and use them to query a database to get relevant knowledge to generate responses.
ESCL: Equivariant Self-Contrastive Learning for Sentence Representations
Previous contrastive learning methods for sentence representations often focus on insensitive transformations to produce positive pairs, but neglect the role of sensitive transformations that are harmful to semantic representations.
Adaptive Hybrid Spatial-Temporal Graph Neural Network for Cellular Traffic Prediction
First, we apply adaptive hybrid graph learning to learn the compound spatial correlations among cell towers.
Multi-Action Dialog Policy Learning from Logged User Feedback
To cope with this problem, we explore to improve multi-action dialog policy learning with explicit and implicit turn-level user feedback received for historical predictions (i. e., logged user feedback) that are cost-efficient to collect and faithful to real-world scenarios.
Federated Learning over Coupled Graphs
In this work, we propose a novel FL framework for graph data, FedCog, to efficiently handle coupled graphs that are a kind of distributed graph data, but widely exist in a variety of real-world applications such as mobile carriers' communication networks and banks' transaction networks.
A Generative User Simulator with GPT-based Architecture and Goal State Tracking for Reinforced Multi-Domain Dialog Systems
Second, an important ingredient in a US is that the user goal can be effectively incorporated and tracked; but how to flexibly integrate goal state tracking and develop an end-to-end trainable US for multi-domains has remained to be a challenge.
Jointly Reinforced User Simulator and Task-oriented Dialog System with Simplified Generative Architecture
Recently, there has been progress in supervised funetuning pretrained GPT-2 to build end-to-end task-oriented dialog (TOD) systems.
Information Extraction and Human-Robot Dialogue towards Real-life Tasks: A Baseline Study with the MobileCS Dataset
Recently, there have merged a class of task-oriented dialogue (TOD) datasets collected through Wizard-of-Oz simulated games.
Generalized Intent Discovery: Learning from Open World Dialogue System
Traditional intent classification models are based on a pre-defined intent set and only recognize limited in-domain (IND) intent classes.
PSSAT: A Perturbed Semantic Structure Awareness Transferring Method for Perturbation-Robust Slot Filling
Most existing slot filling models tend to memorize inherent patterns of entities and corresponding contexts from training data.
Advancing Semi-Supervised Task Oriented Dialog Systems by JSA Learning of Discrete Latent Variable Models
In this paper, we propose to apply JSA to semi-supervised learning of the latent state TOD models, which is referred to as JSA-TOD.
A Challenge on Semi-Supervised and Reinforced Task-Oriented Dialog Systems
A challenge on Semi-Supervised and Reinforced Task-Oriented Dialog Systems, Co-located with EMNLP2022 SereTOD Workshop.
Meta Auxiliary Learning for Low-resource Spoken Language Understanding
Spoken language understanding (SLU) treats automatic speech recognition (ASR) and natural language understanding (NLU) as a unified task and usually suffers from data scarcity.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
A CTC Triggered Siamese Network with Spatial-Temporal Dropout for Speech Recognition
Analysis shows that our proposed approach brings a better uniformity for the trained model and enlarges the CTC spikes obviously.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Curriculum-Based Self-Training Makes Better Few-Shot Learners for Data-to-Text Generation
Despite the success of text-to-text pre-trained models in various natural language generation (NLG) tasks, the generation performance is largely restricted by the number of labeled data in downstream tasks, particularly in data-to-text generation tasks.
"Think Before You Speak": Improving Multi-Action Dialog Policy by Planning Single-Action Dialogs
Multi-action dialog policy (MADP), which generates multiple atomic dialog actions per turn, has been widely applied in task-oriented dialog systems to provide expressive and efficient system responses.
Network Topology Optimization via Deep Reinforcement Learning
A2C-GS consists of three novel components, including a verifier to validate the correctness of a generated network topology, a graph neural network (GNN) to efficiently approximate topology rating, and a DRL actor layer to conduct a topology search.
Building Markovian Generative Architectures over Pretrained LM Backbones for Efficient Task-Oriented Dialog Systems
Recently, Transformer based pretrained language models (PLMs), such as GPT2 and T5, have been leveraged to build generative task-oriented dialog (TOD) systems.
Multiple Confidence Gates For Joint Training Of SE And ASR
Joint training of speech enhancement model (SE) and speech recognition model (ASR) is a common solution for robust ASR in noisy environments.
Harmonic gated compensation network plus for ICASSP 2022 DNS CHALLENGE
Therefore, we previously proposed a harmonic gated compensation network (HGCN) to predict the full harmonic locations based on the unmasked harmonics and process the result of a coarse enhancement module to recover the masked harmonics.
HGCN: Harmonic gated compensation network for speech enhancement
Mask processing in the time-frequency (T-F) domain through the neural network has been one of the mainstreams for single-channel speech enhancement.
Adaptive Multi-receptive Field Spatial-Temporal Graph Convolutional Network for Traffic Forecasting
AMF-STGCN extends GCN by (1) jointly modeling the complex spatial-temporal dependencies in mobile networks, (2) applying attention mechanisms to capture various Receptive Fields of heterogeneous base stations, and (3) introducing an extra decoder based on a fully connected deep network to conquer the error propagation challenge with multi-step forecasting.
Variational Latent-State GPT for Semi-Supervised Task-Oriented Dialog Systems
In this paper, we propose Variational Latent-State GPT model (VLS-GPT), which is the first to combine the strengths of the two approaches.
GenAD: General Representations of Multivariate Time Series for Anomaly Detection
However, due to complex correlations and various temporal patterns of large-scale multivariate time series, a general unsupervised anomaly detection model with higher F1-score and Timeliness remains a challenging task.
Adaptive Spatial-Temporal Inception Graph Convolutional Networks for Multi-step Spatial-Temporal Network Data Forecasting
Spatial-temporal data forecasting is of great importance for industries such as telecom network operation and transportation management.
Learning to Check Contract Inconsistencies
This will result in the issue of contract inconsistencies, which may severely impair the legal validity of the contract.
Towards Low-Resource Semi-Supervised Dialogue Generation with Meta-Learning
In this paper, we propose a meta-learning based semi-supervised explicit dialogue state tracker (SEDST) for neural dialogue generation, denoted as MEDST.
A structure-enhanced graph convolutional network for sentiment analysis
Syntactic information is essential for both sentiment analysis(SA) and aspect-based sentiment analysis(ABSA).
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning
In this paper we aim at alleviating the reliance on belief state labels in building end-to-end dialog systems, by leveraging unlabeled dialog data towards semi-supervised learning.
Ranked #2 on
End-To-End Dialogue Modelling
on MULTIWOZ 2.1
Meta-Reinforced Multi-Domain State Generator for Dialogue Systems
The state-of-the-art accuracy for DST is below 50{\%} for a multi-domain dialogue task.
Elastic CRFs for Open-ontology Slot Filling
An ontology is defined by the collection of slots and the values that each slot can take.
