Search Results for author:
Found 128 papers, 45 papers with code
Addressing Asymmetry in Multilingual Neural Machine Translation with Fuzzy Task Clustering
However, the existing clustering methods based on language similarity cannot handle the asymmetric problem in multilingual NMT, i. e., one translation task A can benefit from another translation task B but task B will be harmed by task A.
Cross-Modal Cloze Task: A New Task to Brain-to-Word Decoding
More importantly, it demonstrates that it is feasible to decode a certain word within a large vocabulary from its neural brain activity.
Entity-level Cross-modal Learning Improves Multi-modal Machine Translation
Inspired by the findings of (CITATION) that entities are most informative in the image, we propose an explicit entity-level cross-modal learning approach that aims to augment the entity representation.
ChineseWebText 2.0: Large-Scale High-quality Chinese Web Text with Multi-dimensional and fine-grained information
With this approach, we release the largest, high-quality and fine-grained Chinese text ChineseWebText2. 0, which consists of 3. 8TB and each text is associated with a quality score, domain labels, a toxicity label and a toxicity score, facilitating the LLM researchers to select data based on various types of fine-grained information.
LOCAL: Learning with Orientation Matrix to Infer Causal Structure from Time Series Data
LOCAL is the first attempt to formulate a quasi-maximum likelihood-based score function for learning the dynamic DAG equivalent to the ground truth.
Language Imbalance Driven Rewarding for Multilingual Self-improving
Large Language Models (LLMs) have achieved state-of-the-art performance across numerous tasks.
Hit the Sweet Spot! Span-Level Ensemble for Large Language Models
On the other hand, token-level ensemble methods enable real-time correction through fine-grained ensemble at each generation step.
Enhancing Knowledge Distillation of Large Language Models through Efficient Multi-Modal Distribution Alignment
Knowledge distillation (KD) is an effective model compression method that can transfer the internal capabilities of large language models (LLMs) to smaller ones.
Qwen2.5-Coder Technical Report
In this report, we introduce the Qwen2. 5-Coder series, a significant upgrade from its predecessor, CodeQwen1. 5.
ManiDext: Hand-Object Manipulation Synthesis via Continuous Correspondence Embeddings and Residual-Guided Diffusion
At each step of the denoising process, we incorporate the current hand pose residual as a refinement target into the network, guiding the network to correct inaccurate hand poses.
I-SHEEP: Self-Alignment of LLM from Scratch through an Iterative Self-Enhancement Paradigm
Large Language Models (LLMs) have achieved significant advancements, however, the common learning paradigm treats LLMs as passive information repositories, neglecting their potential for active learning and alignment.
Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models
The remarkable success of Large Language Models (LLMs) has ushered natural language processing (NLP) research into a new era.
SpikeLLM: Scaling up Spiking Neural Network to Large Language Models via Saliency-based Spiking
In contrast, human brains, which contain approximately 86 billion biological neurons, exhibit significantly greater energy efficiency compared to LLMs with a similar number of parameters.
BLSP-Emo: Towards Empathetic Large Speech-Language Models
In this paper, we present BLSP-Emo (Bootstrapped Language-Speech Pretraining with Emotion support), a novel approach to developing an end-to-end speech-language model capable of understanding both semantics and emotions in speech and generate empathetic responses.
SpikeLM: Towards General Spike-Driven Language Modeling via Elastic Bi-Spiking Mechanisms
We plug this elastic bi-spiking mechanism in language modeling, named SpikeLM.
Diver: Large Language Model Decoding with Span-Level Mutual Information Verification
Large language models (LLMs) have shown impressive capabilities in adapting to various tasks when provided with task-specific instructions.
X-Instruction: Aligning Language Model in Low-resource Languages with Self-curated Cross-lingual Instructions
In addition, we find that models tuned on cross-lingual instruction following samples can follow the instruction in the output language without further tuning.
BLSP-KD: Bootstrapping Language-Speech Pre-training via Knowledge Distillation
Recent end-to-end approaches have shown promise in extending large language models (LLMs) to speech inputs, but face limitations in directly assessing and optimizing alignment quality and fail to achieve fine-grained alignment due to speech-text length mismatch.
MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series
To improve the transparency of LLMs, the research community has formed to open-source truly open LLMs (e. g., Pythia, Amber, OLMo), where more details (e. g., pre-training corpus and training code) are being provided.
Bridging the Gap between Different Vocabularies for LLM Ensemble
Ensembling different large language models (LLMs) to unleash their complementary potential and harness their individual strengths is highly valuable.
COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuning
Remarkable progress on English instruction tuning has facilitated the efficacy and reliability of large language models (LLMs).
DEEP-ICL: Definition-Enriched Experts for Language Model In-Context Learning
It has long been assumed that the sheer number of parameters in large language models (LLMs) drives in-context learning (ICL) capabilities, enabling remarkable performance improvements by leveraging task-specific demonstrations.
DPPA: Pruning Method for Large Language Model to Model Merging
In this paper, we introduce a dual-stage method termed Dynamic Pruning Partition Amplification (DPPA), devised to tackle the challenge of merging complex fine-tuned models.
Evolving to the Future: Unseen Event Adaptive Fake News Detection on Social Media
One of the unique challenges for fake news detection on social media is how to detect fake news on future events.
CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models
The advancement of large language models (LLMs) has enhanced the ability to generalize across a wide range of unseen natural language processing (NLP) tasks through instruction-following.
A Survey on Data Selection for LLM Instruction Tuning
Instruction tuning is a vital step of training large language models (LLM), so how to enhance the effect of instruction tuning has received increased attention.
Ins-HOI: Instance Aware Human-Object Interactions Recovery
To address this, we further propose a complementary training strategy that leverages synthetic data to introduce instance-level shape priors, enabling the disentanglement of occupancy fields for different instances.
BiPFT: Binary Pre-trained Foundation Transformer with Low-rank Estimation of Binarization Residual Polynomials
Specifically, we first analyze the binarization error in self-attention operations and derive the polynomials of binarization error.
Toward Real World Stereo Image Super-Resolution via Hybrid Degradation Model and Discriminator for Implied Stereo Image Information
Real-world stereo image super-resolution has a significant influence on enhancing the performance of computer vision systems.
MoDS: Model-oriented Data Selection for Instruction Tuning
First, our approach utilizes a quality evaluation model to filter out the high-quality subset from the original instruction dataset, and then designs an algorithm to further select from the high-quality subset a seed instruction dataset with good coverage.
Improving In-context Learning of Multilingual Generative Language Models with Cross-lingual Alignment
It aligns the internal sentence representations across different languages via multilingual contrastive learning and aligns outputs by following cross-lingual instructions in the target language.
ChineseWebText: Large-scale High-quality Chinese Web Text Extracted with Effective Evaluation Model
Using our proposed approach, we release the largest and latest large-scale high-quality Chinese web text ChineseWebText, which consists of 1. 42 TB and each text is associated with a quality score, facilitating the LLM researchers to choose the data according to the desired quality thresholds.
Interpreting and Exploiting Functional Specialization in Multi-Head Attention under Multi-task Learning
We further propose a simple multi-task training method to increase functional specialization and mitigate negative information transfer in multi-task learning.
Efficient Retrieval of Images with Irregular Patterns using Morphological Image Analysis: Applications to Industrial and Healthcare datasets
Recently, much attention has been directed towards the retrieval of irregular patterns within industrial or medical images by extracting features from the images, such as deep features, colour-based features, shape-based features and local features.
MuLanTTS: The Microsoft Speech Synthesis System for Blizzard Challenge 2023
In this paper, we present MuLanTTS, the Microsoft end-to-end neural text-to-speech (TTS) system designed for the Blizzard Challenge 2023.
BLSP: Bootstrapping Language-Speech Pre-training via Behavior Alignment of Continuation Writing
One is a cascaded approach where outputs (tokens or states) of a separately trained speech recognition system are used as inputs for LLMs, which limits their potential in modeling alignment between speech and text.
ForestMonkey: Toolkit for Reasoning with AI-based Defect Detection and Classification Models
Additionally, this paper investigates the time performance of the FM toolkit when applied to four AI models with different datasets.
Morphological Image Analysis and Feature Extraction for Reasoning with AI-based Defect Detection and Classification Models
As the use of artificial intelligent (AI) models becomes more prevalent in industries such as engineering and manufacturing, it is essential that these models provide transparent reasoning behind their predictions.
ProxyCap: Real-time Monocular Full-body Capture in World Space via Human-Centric Proxy-to-Motion Learning
For more accurate and physically plausible predictions in world space, our network is designed to learn human motions from a human-centric perspective, which enables the understanding of the same motion captured with different camera trajectories.
Ranked #224 on
3D Human Pose Estimation
on Human3.6M
BigTranslate: Augmenting Large Language Models with Multilingual Translation Capability over 100 Languages
Second, we continue training the model with a large-scale parallel dataset that covers 102 natural languages.
Ranked #4 on
Machine Translation
on FLoRes-200
Language Cognition and Language Computation -- Human and Machine Language Understanding
Language understanding is a key scientific issue in the fields of cognitive and computer science.
Life-long Learning for Multilingual Neural Machine Translation with Knowledge Distillation
To alleviate the CF, we investigate knowledge distillation based life-long learning methods.
1st Place Solutions for the UVO Challenge 2022
This paper describes the approach we have taken in the challenge.
Discrete Cross-Modal Alignment Enables Zero-Shot Speech Translation
Existing zero-shot methods fail to align the two modalities of speech and text into a shared semantic space, resulting in much worse performance compared to the supervised ST methods.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Other Roles Matter! Enhancing Role-Oriented Dialogue Summarization via Role Interactions
Therefore, we propose a novel role interaction enhanced method for role-oriented dialogue summarization.
A Roadmap for Big Model
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.
Learning Confidence for Transformer-based Neural Machine Translation
Confidence estimation aims to quantify the confidence of the model prediction, providing an expectation of success.
Instance-aware Prompt Learning for Language Understanding and Generation
Specifically, we suppose that each learnable prompt token has a different contribution to different instances, and we learn the contribution by calculating the relevance score between an instance and each prompt token.
CUGE: A Chinese Language Understanding and Generation Evaluation Benchmark
We argue that for general-purpose language intelligence evaluation, the benchmark itself needs to be comprehensive and systematic.
Parameter Differentiation based Multilingual Neural Machine Translation
Further analyses reveal that the parameter sharing configuration obtained by our method correlates well with the linguistic proximities.
Deep Learning-based Segmentation of Cerebral Aneurysms in 3D TOF-MRA using Coarse-to-Fine Framework
The segmentation metrics we used include DSC, HD, and VS.
Towards Brain-to-Text Generation: Neural Decoding with Pre-trained Encoder-Decoder Models
However, most of the existing studies have focused on discriminating which one in two stimuli corresponds to the given brain image, which is far from directly generating text from neural activities.
Exploiting Curriculum Learning in Unsupervised Neural Machine Translation
Back-translation (BT) has become one of the de facto components in unsupervised neural machine translation (UNMT), and it explicitly makes UNMT have translation ability.
CSDS: A Fine-Grained Chinese Dataset for Customer Service Dialogue Summarization
Therefore, in this paper, we introduce a novel Chinese dataset for Customer Service Dialogue Summarization (CSDS).
Augmenting Slot Values and Contexts for Spoken Language Understanding with Pretrained Models
We propose two strategies for finetuning process: value-based and context-based augmentation.
Attention Calibration for Transformer in Neural Machine Translation
Attention mechanisms have achieved substantial improvements in neural machine translation by dynamically selecting relevant inputs for different predictions.
Gaze Estimation with an Ensemble of Four Architectures
This paper presents a method for gaze estimation according to face images.
OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation
In this paper, we propose an Omni-perception Pre-Trainer (OPT) for cross-modal understanding and generation, by jointly modeling visual, text and audio resources.
Ranked #1 on
Image Retrieval
on Localized Narratives
Bilingual Mutual Information Based Adaptive Training for Neural Machine Translation
Recently, token-level adaptive training has achieved promising improvement in machine translation, where the cross-entropy loss function is adjusted by assigning different training weights to different tokens, in order to alleviate the token imbalance problem.
Pre-Training on Dynamic Graph Neural Networks
This paper proposes a pre-training method on dynamic graph neural networks (PT-DGNN), which uses dynamic attributed graph generation tasks to simultaneously learn the structure, semantics, and evolution features of the graph.
Touch Editing: A Flexible One-Time Interaction Approach for Translation
We propose a touch-based editing method for translation, which is more flexible than traditional keyboard-mouse-based translation postediting.
Distill and Replay for Continual Language Learning
The framework is based on language models and can be smoothly built with different language model architectures.
Knowledge Graph Enhanced Neural Machine Translation via Multi-task Learning on Sub-entity Granularity
Previous studies combining knowledge graph (KG) with neural machine translation (NMT) have two problems: i) Knowledge under-utilization: they only focus on the entities that appear in both KG and training sentence pairs, making much knowledge in KG unable to be fully utilized.
Multimodal Sentence Summarization via Multimodal Selective Encoding
Thus, we propose a multimodal selective gate network that considers reciprocal relationships between textual and multi-level visual features, including global image descriptor, activation grids, and object proposals, to select highlights of the event when encoding the source sentence.
Deep Template Matching for Pedestrian Attribute Recognition with the Auxiliary Supervision of Attribute-wise Keypoints
Pedestrian Attribute Recognition (PAR) has aroused extensive attention due to its important role in video surveillance scenarios.
Bridging the Modality Gap for Speech-to-Text Translation
End-to-end speech translation aims to translate speech in one language into text in another language via an end-to-end way.
Dynamic Context Selection for Document-level Neural Machine Translation via Reinforcement Learning
Specifically, we introduce a selection module that is independent of the translation module to score each candidate context sentence.
Attend, Translate and Summarize: An Efficient Method for Neural Cross-Lingual Summarization
Cross-lingual summarization aims at summarizing a document in one language (e. g., Chinese) into another language (e. g., English).
CASIA's System for IWSLT 2020 Open Domain Translation
This paper describes the CASIA{'}s system for the IWSLT 2020 open domain translation task.
Neural Machine Translation: Challenges, Progress and Future
Machine translation (MT) is a technique that leverages computers to translate human languages automatically.
Synchronous Speech Recognition and Speech-to-Text Translation with Interactive Decoding
Speech-to-text translation (ST), which translates source language speech into target language text, has attracted intensive attention in recent years.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Modelling cosmic ray electron physics in cosmological smoothed particle hydrodynamics simulation
Cosmic ray electron (CRE) acceleration and cooling are important physical processes in astrophysics.
High Energy Astrophysical Phenomena Cosmology and Nongalactic Astrophysics
Chinese Spelling Error Detection Using a Fusion Lattice LSTM
Spelling error detection serves as a crucial preprocessing in many natural language processing applications.
Synchronously Generating Two Languages with Interactive Decoding
In this paper, we introduce a novel interactive approach to translate a source language into two different languages simultaneously and interactively.
NCLS: Neural Cross-Lingual Summarization
Moreover, we propose to further improve NCLS by incorporating two related tasks, monolingual summarization and machine translation, into the training process of CLS under multi-task learning.
Are You for Real? Detecting Identity Fraud via Dialogue Interactions
In this paper, we focus on identity fraud detection in loan applications and propose to solve this problem with a novel interactive dialogue system which consists of two modules.
Understanding Memory Modules on Learning Simple Algorithms
Recent work has shown that memory modules are crucial for the generalization ability of neural networks on learning simple algorithms.
A Compact and Language-Sensitive Multilingual Translation Method
We verify our methods on various translation scenarios, including one-to-many, many-to-many and zero-shot.
Sequence Generation: From Both Sides to the Middle
The encoder-decoder framework has achieved promising process for many sequence generation tasks, such as neural machine translation and text summarization.
Incremental Learning from Scratch for Task-Oriented Dialogue Systems
Clarifying user needs is essential for existing task-oriented dialogue systems.
Memory Consolidation for Contextual Spoken Language Understanding with Dialogue Logistic Inference
Dialogue contexts are proven helpful in the spoken language understanding (SLU) system and they are typically encoded with explicit memory representations.
Synchronous Bidirectional Neural Machine Translation
In this paper, we introduce a synchronous bidirectional neural machine translation (SB-NMT) that predicts its outputs using left-to-right and right-to-left decoding simultaneously and interactively, in order to leverage both of the history and future information at the same time.
Ranked #27 on
Machine Translation
on WMT2014 English-German
End-to-End Speech Translation with Knowledge Distillation
End-to-end speech translation (ST), which directly translates from source language speech into target language text, has attracted intensive attentions in recent years.
Synchronous Bidirectional Inference for Neural Sequence Generation
In this work, we propose a synchronous bidirectional inference model to generate outputs using both left-to-right and right-to-left decoding simultaneously and interactively.
Language-Independent Representor for Neural Machine Translation
Current Neural Machine Translation (NMT) employs a language-specific encoder to represent the source sentence and adopts a language-specific decoder to generate target translation.
Three Strategies to Improve One-to-Many Multilingual Translation
However, previous studies show that one-to-many translation based on this framework cannot perform on par with the individually trained models.
Addressing Troublesome Words in Neural Machine Translation
One of the weaknesses of Neural Machine Translation (NMT) is in handling lowfrequency and ambiguous words, which we refer as troublesome words.
MSMO: Multimodal Summarization with Multimodal Output
In this paper, we propose a novel task, multimodal summarization with multimodal output (MSMO).
A Teacher-Student Framework for Maintainable Dialog Manager
Specifically, the {``}student{''} is an extended dialog manager based on a new ontology, and the {``}teacher{''} is existing resources used for guiding the learning process of the {``}student{''}.
Associative Multichannel Autoencoder for Multimodal Word Representation
In this paper we address the problem of learning multimodal word representations by integrating textual, visual and auditory inputs.
Source-Critical Reinforcement Learning for Transferring Spoken Language Understanding to a New Language
This paper focuses on the language transferring task given a tiny in-domain parallel SLU corpus.
Cultural Vocal Bursts Intensity Prediction
domain classification
+7
Ensure the Correctness of the Summary: Incorporate Entailment Knowledge into Abstractive Sentence Summarization
In this paper, we investigate the sentence summarization task that produces a summary from a source sentence.
Ranked #7 on
Text Summarization
on DUC 2004 Task 1
Source Critical Reinforcement Learning for Transferring Spoken Language Understanding to a New Language
An SLU corpus is a monolingual corpus with domain/intent/slot labels.
Cultural Vocal Bursts Intensity Prediction
domain classification
+9
Phrase Table as Recommendation Memory for Neural Machine Translation
Neural Machine Translation (NMT) has drawn much attention due to its promising translation performance recently.
Learning Multimodal Word Representation via Dynamic Fusion Methods
Multimodal models have been proven to outperform text-based models on learning semantic word representations.
Learning from Parenthetical Sentences for Term Translation in Machine Translation
Terms extensively exist in specific domains, and term translation plays a critical role in domain-specific machine translation (MT) tasks.
Investigating Inner Properties of Multimodal Representation and Semantic Compositionality with Brain-based Componential Semantics
Considering that multimodal models are originally motivated by human concept representations, we assume that correlating multimodal representations with brain-based semantics would interpret their inner properties to answer the above questions.
Learning Semantic Representations
Natural Language Understanding
Word, Subword or Character? An Empirical Study of Granularity in Chinese-English NMT
Our experiments show that subword model performs best for Chinese-to-English translation with the vocabulary which is not so big while hybrid word-character model is most suitable for English-to-Chinese translation.
Doppler-Radar Based Hand Gesture Recognition System Using Convolutional Neural Networks
In this paper, a Doppler Radar based hand gesture recognition system using convolutional neural networks is proposed.
Deformable Deep Convolutional Generative Adversarial Network in Microwave Based Hand Gesture Recognition System
Traditional vision-based hand gesture recognition systems is limited under dark circumstances.
BIG-bench Machine Learning
Generative Adversarial Network
+2
Towards Neural Machine Translation with Partially Aligned Corpora
While neural machine translation (NMT) has become the new paradigm, the parameter optimization requires large-scale parallel data which is scarce in many domains and language pairs.
Multi-modal Summarization for Asynchronous Collection of Text, Image, Audio and Video
In this work, we propose an extractive Multi-modal Summarization (MMS) method which can automatically generate a textual summary given a set of documents, images, audios and videos related to a specific topic.
Automatic Speech Recognition (ASR)
Document Summarization
+1
Exploiting Word Internal Structures for Generic Chinese Sentence Representation
We introduce a novel mixed characterword architecture to improve Chinese sentence representations, by utilizing rich semantic information of word internal structures.
Look-ahead Attention for Generation in Neural Machine Translation
The attention model has become a standard component in neural machine translation (NMT) and it guides translation process by selectively focusing on parts of the source sentence when predicting each target word.
Neural System Combination for Machine Translation
Neural machine translation (NMT) becomes a new approach to machine translation and generates much more fluent results compared to statistical machine translation (SMT).
Shortcut Sequence Tagging
To simply the stacked architecture, we propose a framework called shortcut block, which is a marriage of the gating mechanism and shortcuts, while discarding the self-connected part in LSTM cell.
Different Contexts Lead to Different Word Embeddings
Recent work for learning word representations has applied successfully to many NLP applications, such as sentiment analysis and question answering.
Ultra-Light Axion Dark Matter and its impacts on dark halo structure in $N$-body simulation
The existence of the solitonic core reveals the non-linear effect of quantum pressure and impacts the structure formation in the FDM model.
Cosmology and Nongalactic Astrophysics Astrophysics of Galaxies High Energy Physics - Phenomenology
Bridging Neural Machine Translation and Bilingual Dictionaries
Neural Machine Translation (NMT) has become the new state-of-the-art in several language pairs.
An Empirical Exploration of Skip Connections for Sequential Tagging
In this paper, we empirically explore the effects of various kinds of skip connections in stacked bidirectional LSTMs for sequential tagging.
A Dynamic Window Neural Network for CCG Supertagging
These motivate us to build a supertagger with a dynamic window approach, which can be treated as an attention mechanism on the local contexts.
Learning Sentence Representation with Guidance of Human Attention
Recently, much progress has been made in learning general-purpose sentence representations that can be used across domains.
One Sentence One Model for Neural Machine Translation
Neural machine translation (NMT) becomes a new state-of-the-art and achieves promising translation results using a simple encoder-decoder neural network.
Neural Name Translation Improves Neural Machine Translation
In order to control computational complexity, neural machine translation (NMT) systems convert all rare words outside the vocabulary into a single unk symbol.
A Bilingual Discourse Corpus and Its Applications
Existing discourse research only focuses on the monolingual languages and the inconsistency between languages limits the power of the discourse theory in multilingual applications such as machine translation.
Local Translation Prediction with Global Sentence Representation
With the sentence-level feature representation, we further design a feed-forward neural network to better predict translations using both local and global information.
Beyond Word-based Language Model in Statistical Machine Translation
Language model is one of the most important modules in statistical machine translation and currently the word-based language model dominants this community.
Unsupervised Tree Induction for Tree-based Translation
In current research, most tree-based translation models are built directly from parse trees.
