Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks371 from public data
- ERNIE 2.0: A Continual Pre-Training Framework for Language Understanding914
A continual pre-training framework named ERNIE 2.0 which incrementally builds pre- training tasks and then learns pre-trained models on these constructed tasks via continual multi-task learning is proposed.
- RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering794
This work proposes an optimized training approach, called RocketQA, to improving dense passage retrieval, which significantly outperforms previous state-of-the-art models on both MSMARCO and Natural Questions and demonstrates that the performance of end-to-end QA can be improved based on theRocketQA retriever.
- Geometry-enhanced molecular representation learning for property prediction708
A novel geometry-enhanced molecular representation learning method that uses this geometric data in graph neural networks to predict a range of molecular properties and can considerably outperform various state-of-the-art baselines on different benchmarks.
- Multi-Task Learning for Multiple Language Translation657
The recently proposed neural machine translation model is extended to a multi-task learning framework which shares source language representation and separates the modeling of different target language translation.
- A support vector machine-based ensemble algorithm for breast cancer diagnosis440
The proposed WAUCE model achieves a higher accuracy with a significantly lower variance for breast cancer diagnosis compared to five other ensemble mechanisms and two common ensemble models, i.e., adaptive boosting and bagging classification tree.
- UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning431
A UNIfied-MOdal pre-training architecture, namely UNIMO, which can effectively adapt to both single- modal and multi-modal understanding and generation tasks, and is able to learn more generalizable representations.
- ERNIE-ViL: Knowledge Enhanced Vision-Language Representations through Scene Graphs424
A knowledge-enhanced approach, ERNIE-ViL, which incorporates structured knowledge obtained from scene graphs to learn joint representations of vision-language and ranks the first place on the VCR leaderboard with an absolute improvement of 3.7%.
- 399
- STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework341
A novel prefix-to-prefix framework for si- multaneous translation that implicitly learns to anticipate in a single translation model that achieves low latency and reasonable quality (compared to full-sentence translation) on 4 directions.
- RocketQAv2: A Joint Training Method for Dense Passage Retrieval and Passage Re-ranking321
A novel joint training approach for dense passage retrieval and passage reranking is proposed, where the dynamic listwise distillation is introduced, where a unified listwise training approach is designed for both the retriever and the re-ranker.
- DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications313
This paper introduces DuReader, a new large-scale, open-domain Chinese machine reading comprehension (MRC) dataset, designed to address real-world MRC, and organizes a shared competition to encourage the exploration of more models.
- SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis299
Sentiment Knowledge Enhanced Pre-training (SKEP) is introduced in order to learn a unified sentiment representation for multiple sentiment analysis tasks, and significantly outperforms strong pre-training baseline, and achieves new state-of-the-art results on most of the test datasets.
- PLATO: Pre-trained Dialogue Generation Model with Discrete Latent Variable297
This work proposes a novel dialogue generation pre-training framework to support various kinds of conversations, including chit-chat, knowledge grounded dialogues, and conversational question answering, and introduces discrete latent variables to tackle the inherent one-to-many mapping problem in response generation.
- Learning Semantic Hierarchies via Word Embeddings289
This paper proposes a novel and effective method for the construction of semantic hierarchies based on word embeddings, which can be used to measure the semantic relationship between words.
- Towards Conversational Recommendation over Multi-Type Dialogs254
This work creates a human-to-human Chinese dialog dataset DuRecDial, where there are multiple sequential dialogs for a pair of a recommendation seeker and a recommender, where the recommender proactively leads a multi-type dialog to approach recommendation targets and then makes multiple recommendations with rich interaction behavior.
- Pivot language approach for phrase-based statistical machine translation245
This paper proposes a novel method for phrase-based statistical machine translation based on the use of a pivot language, using BLEU as a metric, that significantly outperforms the standard model trained on a small bilingual corpus.
- Rare earth element geochemistry characteristics of seawater and porewater from deep sea in western Pacific238
This study suggests that porewater flux in the western Pacific basin is a minor source of REEs to seawater, and abundant REEs are enriched in sediments, which is mainly caused by the extensive oxic condition, low sedimentation rate and strong adsorption capacity of sediments.
- Progress in Machine Translation225
The history of machine translation is reviewed, including the basic framework and the current dominant framework, Transformer, as well as multilingual translation models to deal with the data sparseness problem and cutting-edge simultaneous translation methods that achieve a balance between translation quality and latency.
- Proactive Human-Machine Conversation with Explicit Conversation Goal219
Experimental results show that dialogue models that plan over the knowledge graph can make full use of related knowledge to generate more diverse multi-turn conversations.
- Cross-lingual Dependency Parsing Based on Distributed Representations201
This paper provides two algorithms for inducing cross-lingual distributed representations of words, which map vocabularies from two different languages into a common vector space and bridges the lexical feature gap by using distributed feature representations and their composition.
- 186
- ConSTGAT177
A spatial-temporal graph neural network that adopts a novel graph attention mechanism, which is designed to fully exploit the joint relations of spatial and temporal information, and a computationally efficient model that applies convolutions over local windows to capture a route's contextual information and further employs multi-task learning to improve the performance.
- End-to-End Speech Translation with Knowledge Distillation177
This paper proposes a knowledge distillation approach to improve end-to-end speech translation model by transferring the knowledge from text translation model throughknowledge distillation.
- 166
- Federated Learning with Class Imbalance Reduction166
An estimation scheme to reveal the class distribution without the awareness of raw data is designed and a multi-arm bandit based algorithm is proposed that can select the client set with minimal class imbalance and can significantly improve the convergence performance of the global model.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.