Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks266 from public data
- Relational Graph Attention Network for Aspect-based Sentiment Analysis720
This paper defines a unified aspect-oriented dependency tree structure rooted at a target aspect by reshaping and pruning an ordinary dependency parse tree and proposes a relational graph attention network (R-GAT) to encode the new tree structure for sentiment prediction.
- SG-Net: Syntax-Guided Machine Reading Comprehension197
This work uses syntax to guide the text modeling by incorporating explicit syntactic constraints into attention mechanism for better linguistically motivated word representations and shows that the proposed SG-Net design helps achieve substantial performance improvement over strong baselines.
- 182
- Instance Weighting for Neural Machine Translation Domain Adaptation141
Two instance weighting technologies, i.e., sentence weighting and domain weighting with a dynamic weight learning strategy, are proposed for NMT domain adaptation and empirical results show that the proposed methods can substantially improve NMT performance.
- 137
- Boundary Enhanced Neural Span Classification for Nested Named Entity Recognition135
This work proposes a boundary enhanced neural span classification model that has the ability to generate high-quality candidate spans and greatly reduces the time complexity during inference, and incorporates an additional boundary detection task to predict those words that are boundaries of entities.
- Igniting Language Intelligence: The Hitchhiker’s Guide from Chain-of-Thought Reasoning to Language Agents126
A thorough discourse is orchestrated, penetrating vital research dimensions, encompassing the foundational mechanics of CoT techniques, with a focus on elucidating the circumstances and justification behind its efficacy; the paradigm shift in CoT; and the burgeoning of language agents fortified by CoT approaches.
- Neural Machine Translation with Universal Visual Representation124
A universal visual representation learned over the monolingual corpora with image annotations is presented, which overcomes the lack of large-scale bilingual sentence-image pairs, thereby extending image applicability in NMT.
- 119
- Exploring Human-Like Translation Strategy with Large Language Models118
This work proposes the MAPS framework, which stands for Multi-Aspect Prompting and Selection, and enables LLMs first to analyze the given source sentence and induce three aspects of translation-related knowledge to guide the final translation process.
- Sentence Embedding for Neural Machine Translation Domain Adaptation110
The NMT’s internal embedding of the source sentence is exploited and the sentence embedding similarity is used to select the sentences which are close to in-domain data to substantially improve NMT performance.
- Neural Topic Modeling with Bidirectional Adversarial Training99
The proposed Bidirectional Adversarial Topic (BAT) model is the first attempt of applying bidirectional adversarial training for neural topic modeling and shows that BAT and Gaussian-BAT obtain more coherent topics, outperforming several competitive baselines.
- Syntax-Directed Attention for Neural Machine Translation96
This paper extends the local attention with syntax-distance constraint, which focuses on syntactically related source words with the predicted target word to learning a more effective context vector for predicting translation, to provide more translation performance for NMT from source representation.
- A Study on ReLU and Softmax in Transformer94
A full ReLU architecture named ReLUFormer is proposed which performs better than the baseline Transformer on long sequence tasks such as document translation and FFN and key-value memory are equivalent, and thus the Transformer can be viewed as a memory network where FFNs and self-attention networks are both key- value memories.
- SentiX: A Sentiment-Aware Pre-Trained Model for Cross-Domain Sentiment Analysis93
This paper pre-train a sentiment-aware language model (SentiX) via domain-invariant sentiment knowledge from large-scale review datasets, and utilize it for cross-domain sentiment analysis task without fine-tuning.
- Threshold segmentation algorithm for automatic extraction of cerebral vessels from brain magnetic resonance angiography images74
The proposed threshold segmentation method can be used to accurately and efficiently extract cerebral vessels from brain MRA images and may be used for studies focusing on three-dimensional visualization and volumetric quantification of cerebral vessels.
- Data-dependent Gaussian Prior Objective for Language Generation70
Experimental results show that the proposed data-dependent Gaussian prior objective (D2GPo) can effectively make use of more detailed prior in the data and significantly improve the performance of typical language generation tasks, including supervised and unsupervised machine translation, text summarization, storytelling, and image caption.
- High-accuracy optical convolution unit architecture for convolutional neural networks by cascaded acousto-optical modulator arrays68
Besides the effectiveness and high accuracy, the simplified OCU architecture served as a building block could be easily duplicated and integrated to future chip-scale optical CNNs.
- Multi-Domain Dialogue Acts and Response Co-Generation66
A neural co-generation model that generates dialogue acts and responses concurrently and achieves very favorable improvement over several state-of-the-art models in both automatic and human evaluations.
- 64
- Neural Machine Translation with Source Dependency Representation64
A novel NMT with source dependency representation to improve translation performance of NMT, especially long sentences, is proposed and empirical results show that this method achieves 1.6 BLEU improvements on average over a strong NMT system.
- Recognizing textual entailment using sentence similarity based on dependency tree skeletons64
A novel approach to RTE that exploits a structure-oriented sentence representation followed by a similarity function that makes use of a limited size of training data without any external knowledge bases or handcrafted inference rules is presented.
- BiSET: Bi-directional Selective Encoding with Template for Abstractive Summarization61
A novel Bi-directional Selective Encoding with Template (BiSET) model, which leverages template discovered from training data to softly select key information from each source article to guide its summarization process, is proposed.
- Using Word Embeddings to Enhance Keyword Identification for Scientific Publications61
This paper proposes an approach that uses word embedding vectors as an external knowledge base for both keyword extraction and generation, and shows that this approach outperforms many baseline algorithms, and is comparable to the state-of-the-art algorithm on the authors' chosen dataset.
- Text Compression-aided Transformer Encoding54
This paper proposes explicit and implicit text compression approaches to enhance the Transformer encoding and evaluates models using this approach on several typical downstream tasks that rely on the encoding heavily, and concludes that text compression helps the encoders to learn better language representations.
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.