Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks283 from public data
- Exploiting Source-side Monolingual Data in Neural Machine Translation298
Two approaches to make full use of the source-side monolingual data in NMT are proposed - the self-learning algorithm to generate the synthetic large-scale parallel data for NMT training and the multi-task learning framework using two NMTs to predict the translation and the reordered source- side monolingUAL sentences simultaneously.
- Character-Based LSTM-CRF with Radical-Level Features for Chinese Named Entity Recognition284
A bidirectional LSTM-CRF neural network that utilizes both character-level and radical-level representations for CNER is applied, and this paper is the first to use character-based BLSTm- CRF neural architecture for Cner.
- 203
- MSMO: Multimodal Summarization with Multimodal Output199
A novel multimodal automatic evaluation (MMAE) method which considers both intra- modality salience and inter-modality relevance is constructed and the experimental results show the effectiveness of MMAE.
- 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.
- NCLS: Neural Cross-Lingual Summarization148
This work presents an end-to-end CLS framework, which it refers to as Neural Cross-Lingual Summarization (NCLS), and proposes to further improve NCLS by incorporating two related tasks, monolingual summarization and machine translation, into the training process of CLS under multi-task learning.
- Multi-modal Sentence Summarization with Modality Attention and Image Filtering123
A modality-based attention mechanism to pay different attention to image patches and text units, and image filters to selectively use visual information to enhance the semantics of the input sentence are proposed.
- Multi-modal Summarization for Asynchronous Collection of Text, Image, Audio and Video123
This work proposes 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.
- Multimodal Summarization with Guidance of Multimodal Reference120
This work proposes a multimodal objective function with the guidance of multimodAL reference to use the loss from the summary generation and the image selection, and proposes a novel evaluation metric based on joint multi-modality representation, projecting the model output and multimodals reference into a joint semantic space during evaluation.
- Bilingually-constrained Phrase Embeddings for Machine Translation120
This work proposes Bilingually-constrained Recursive Auto-encoders (BRAE) to learn semantic phrase embeddings (compact vector representations for phrases), which can distinguish the phrases with different semantic meanings.
- Synchronous Bidirectional Neural Machine Translation112
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.
- Ensure the Correctness of the Summary: Incorporate Entailment Knowledge into Abstractive Sentence Summarization105
This paper proposes an entailments-aware encoder under multi-task framework and an entailment-aware decoder by entailment Reward Augmented Maximum Likelihood (RAML) training, and demonstrates that their models significantly outperform baselines from the aspects of informativeness and correctness.
- Knowledge Graphs Enhanced Neural Machine Translation103
A novel KGs enhanced NMT method to improve the translation quality of entities by transforming the source and target KGs into a unified semantic space and generating adequate pseudo parallel sentence pairs that contain these induced entity pairs.
- 98
- MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series89
The MAP-Neo is the first fully open-sourced bilingual LLM with comparable performance compared to existing state-of-the-art LLMs, and is hoped to enhance and strengthen the open research community and inspire more innovations and creativities to facilitate the further improvements of LLMs.
- Keywords-Guided Abstractive Sentence Summarization86
This paper proposes an abstractive sentence summarization method by applying guidance signals of keywords to both the encoder and the decoder in the sequence-to-sequence model, and demonstrates that multi-task learning and keywords-oriented guidance facilitate sentence summarizing task.
- 86
- Neural System Combination for Machine Translation81
This paper proposes a neural system combination framework leveraging multi-source NMT, which takes as input the outputs of NMT and SMT systems and produces the final translation.
- Three Strategies to Improve One-to-Many Multilingual Translation78
This work introduces three strategies to improve one-to-many multilingual translation by balancing the shared and unique features and proposes to divide the hidden cells of the decoder into shared and language-dependent ones.
- Transformer: A General Framework from Machine Translation to Others76
The framework of Transformer is introduced, the main challenges in NMT are discussed and the representative methods for each challenge are listed and possible future research directions are suggested.
- Synchronous Speech Recognition and Speech-to-Text Translation with Interactive Decoding74
A novel interactive attention mechanism is proposed which enables ASR and ST to perform synchronously and interactively in a single model and can outperform strong baselines on the quality of speech translation and achieve better speech recognition performances as well.
- 73
- 72
- Neural machine translation: Challenges, progress and future69
This article makes a review of NMT framework, discusses the challenges in NMT, introduces some exciting recent progresses and finally looks forward to some potential future research trends.
- Dynamic Context Selection for Document-level Neural Machine Translation via Reinforcement Learning66
This work introduces a selection module that is independent of the translation module to score each candidate context sentence, and proposes two strategies to explicitly select a variable number of context sentences and feed them into thetranslation module.
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 2026-10-13. 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.