Search Results for author:
Found 42 papers, 22 papers with code
Generating Classical Chinese Poems via Conditional Variational Autoencoder and Adversarial Training
It is a challenging task to automatically compose poems with not only fluent expressions but also aesthetic wording.
Are Training Samples Correlated? Learning to Generate Dialogue Responses with Multiple References
Due to its potential applications, open-domain dialogue generation has become popular and achieved remarkable progress in recent years, but sometimes suffers from generic responses.
Stick to the Facts: Learning towards a Fidelity-oriented E-Commerce Product Description Generation
Different from other text generation tasks, in product description generation, it is of vital importance to generate faithful descriptions that stick to the product attribute information.
Modeling Personalization in Continuous Space for Response Generation via Augmented Wasserstein Autoencoders
In this work, we improve the WAE for response generation.
Cross-Lingual Low-Resource Set-to-Description Retrieval for Global E-Commerce
We manually collect a new and high-quality paired dataset, where each pair contains an unordered product attribute set in the source language and an informative product description in the target language.
Solution Path Algorithm for Twin Multi-class Support Vector Machine
Next, Lagrangian multipliers are proved to be 1 as the regularization parameter approaches infinity, thus, a simple yet effective initialization algorithm is devised.
Feature Adaptation of Pre-Trained Language Models across Languages and Domains with Robust Self-Training
To improve the robustness of self-training, in this paper we present class-aware feature self-distillation (CFd) to learn discriminative features from PrLMs, in which PrLM features are self-distilled into a feature adaptation module and the features from the same class are more tightly clustered.
Unsupervised Domain Adaptation of a Pretrained Cross-Lingual Language Model
Experimental results show that our proposed method achieves significant performance improvements over the state-of-the-art pretrained cross-lingual language model in the CLCD setting.
How does Truth Evolve into Fake News? An Empirical Study of Fake News Evolution
Automatically identifying fake news from the Internet is a challenging problem in deception detection tasks.
Dialogue History Matters! Personalized Response Selectionin Multi-turn Retrieval-based Chatbots
To fill the gap between these up-to-date methods and the real-world applications, we incorporate user-specific dialogue history into the response selection and propose a personalized hybrid matching network (PHMN).
Learning to Organize a Bag of Words into Sentences with Neural Networks: An Empirical Study
Sequential information, a. k. a., orders, is assumed to be essential for processing a sequence with recurrent neural network or convolutional neural network based encoders.
R-Drop: Regularized Dropout for Neural Networks
Dropout is a powerful and widely used technique to regularize the training of deep neural networks.
Ranked #4 on
Machine Translation
on WMT2014 English-French
Are BERT Families Zero-Shot Learners? A Study on Their Potential and Limitations
Starting from the resurgence of deep learning, language models (LMs) have never been so popular.
DM-CT: Consistency Training with Data and Model Perturbation
The common approach of consistency training is performed on the data-level, which typically utilizes the data augmentation strategy (or adversarial training) to make the predictions from the augmented input and the original input to be consistent, so that the model is more robust and attains better generalization ability.
Building an Efficient and Effective Retrieval-based Dialogue System via Mutual Learning
For this task, the adoption of pre-trained language models (such as BERT) has led to remarkable progress in a number of benchmarks.
CT4Rec: Simple yet Effective Consistency Training for Sequential Recommendation
State-of-the-art sequential recommendation models proposed very recently combine contrastive learning techniques for obtaining high-quality user representations.
Image-text Retrieval: A Survey on Recent Research and Development
On top of this, the efficiency-focused study on the ITR system is introduced as the third perspective.
A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond
While NAR generation can significantly accelerate inference speed for machine translation, the speedup comes at the cost of sacrificed translation accuracy compared to its counterpart, autoregressive (AR) generation.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+11
Chinese grammatical error correction based on knowledge distillation
In view of the poor robustness of existing Chinese grammatical error correction models on attack test sets and large model parameters, this paper uses the method of knowledge distillation to compress model parameters and improve the anti-attack ability of the model.
SelfMix: Robust Learning Against Textual Label Noise with Self-Mixup Training
The conventional success of textual classification relies on annotated data, and the new paradigm of pre-trained language models (PLMs) still requires a few labeled data for downstream tasks.
Improving Temporal Generalization of Pre-trained Language Models with Lexical Semantic Change
Existing methods mainly perform continual training to mitigate such a misalignment.
Robust Question Answering against Distribution Shifts with Test-Time Adaptation: An Empirical Study
To answer this question, we evaluate test-time adaptation (TTA) to improve a model after deployment.
AMOM: Adaptive Masking over Masking for Conditional Masked Language Model
Experiments on \textbf{3} different tasks (neural machine translation, summarization, and code generation) with \textbf{15} datasets in total confirm that our proposed simple method achieves significant performance improvement over the strong CMLM model.
RenewNAT: Renewing Potential Translation for Non-Autoregressive Transformer
Non-autoregressive neural machine translation (NAT) models are proposed to accelerate the inference process while maintaining relatively high performance.
Gated Mechanism Enhanced Multi-Task Learning for Dialog Routing
Although most existing methods can fulfil this requirement, they can only model single-source dialog data and cannot effectively capture the underlying knowledge of relations among data and subtasks.
Test-Time Adaptation with Perturbation Consistency Learning
Accordingly, in this paper, we propose perturbation consistency learning (PCL), a simple test-time adaptation method to promote the model to make stable predictions for samples with distribution shifts.
Can Diffusion Model Achieve Better Performance in Text Generation? Bridging the Gap between Training and Inference!
Diffusion models have been successfully adapted to text generation tasks by mapping the discrete text into the continuous space.
AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation
Diffusion models have gained significant attention in the realm of image generation due to their exceptional performance.
CMD: a framework for Context-aware Model self-Detoxification
In view of this, we introduce a Context-aware Model self-Detoxification~(CMD) framework that pays attention to both the context and the detoxification process, i. e., first detoxifying the context and then making the language model generate along the safe context.
GameEval: Evaluating LLMs on Conversational Games
In this paper, we propose GameEval, a novel approach to evaluating LLMs through goal-driven conversational games, overcoming the limitations of previous methods.
Harnessing the Power of David against Goliath: Exploring Instruction Data Generation without Using Closed-Source Models
Instruction tuning is instrumental in enabling Large Language Models~(LLMs) to follow user instructions to complete various open-domain tasks.
LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models
Graphic layout generation, a growing research field, plays a significant role in user engagement and information perception.
OpenBA: An Open-sourced 15B Bilingual Asymmetric seq2seq Model Pre-trained from Scratch
This report provides the main details to pre-train an analogous model, including pre-training data processing, Bilingual Flan data collection, the empirical observations that inspire our model architecture design, training objectives of different stages, and other enhancement techniques.
G-SPEED: General SParse Efficient Editing MoDel
Large Language Models~(LLMs) have demonstrated incredible capabilities in understanding, generating, and manipulating languages.
Beyond Hard Samples: Robust and Effective Grammatical Error Correction with Cycle Self-Augmenting
By leveraging the augmenting data from the GEC models themselves in the post-training process and introducing regularization data for cycle training, our proposed method can effectively improve the model robustness of well-trained GEC models with only a few more training epochs as an extra cost.
KBioXLM: A Knowledge-anchored Biomedical Multilingual Pretrained Language Model
We achieve a biomedical multilingual corpus by incorporating three granularity knowledge alignments (entity, fact, and passage levels) into monolingual corpora.
Resolving Crash Bugs via Large Language Models: An Empirical Study
Evaluating IntDiagSolver on multiple LLMs reveals consistent enhancement in the accuracy of crash bug resolution, including ChatGPT, Claude, and CodeLlama.
StrokeNUWA: Tokenizing Strokes for Vector Graphic Synthesis
To leverage LLMs for visual synthesis, traditional methods convert raster image information into discrete grid tokens through specialized visual modules, while disrupting the model's ability to capture the true semantic representation of visual scenes.
Rethinking Negative Instances for Generative Named Entity Recognition
In the Named Entity Recognition (NER) task, recent advancements have seen the remarkable improvement of LLMs in a broad range of entity domains via instruction tuning, by adopting entity-centric schema.
Plan-CVAE: A Planning-based Conditional Variational Autoencoder for Story Generation
Story generation is a challenging task of automatically creating natural languages to describe a sequence of events, which requires outputting text with not only a consistent topic but also novel wordings.
