Search Results for author:
Found 26 papers, 13 papers with code
A Fine-Grained Domain Adaption Model for Joint Word Segmentation and POS Tagging
Self-training is one promising solution for it, which struggles to construct a set of high-quality pseudo training instances for the target domain.
Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
In this work, we introduce the Qwen3 Embedding series, a significant advancement over its predecessor, the GTE-Qwen series, in text embedding and reranking capabilities, built upon the Qwen3 foundation models.
Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs
The Contrastive Language-Image Pre-training (CLIP) framework has become a widely used approach for multimodal representation learning, particularly in image-text retrieval and clustering.
Towards Text-Image Interleaved Retrieval
In this work, we introduce the text-image interleaved retrieval (TIIR) task, where the query and document are interleaved text-image sequences, and the model is required to understand the semantics from the interleaved context for effective retrieval.
Bridging Modalities: Improving Universal Multimodal Retrieval by Multimodal Large Language Models
Last, we provide in-depth analyses of model scaling and training strategies, and perform ablation studies on both the model and synthetic data.
GME: Improving Universal Multimodal Retrieval by Multimodal LLMs
Last, we provide in-depth analyses of model scaling and training strategies, and perform ablation studies on both the model and synthetic data.
When Text Embedding Meets Large Language Model: A Comprehensive Survey
Text embedding has become a foundational technology in natural language processing (NLP) during the deep learning era, driving advancements across a wide array of downstream tasks.
Improving General Text Embedding Model: Tackling Task Conflict and Data Imbalance through Model Merging
Recently, the advent of pretrained language models, along with unified benchmarks like the Massive Text Embedding Benchmark (MTEB), has facilitated the development of versatile general-purpose text embedding models.
An End-to-End Model for Photo-Sharing Multi-modal Dialogue Generation
We propose the first end-to-end model for photo-sharing multi-modal dialogue generation, which integrates an image perceptron and an image generator with a large language model.
mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval
We first introduce a text encoder (base size) enhanced with RoPE and unpadding, pre-trained in a native 8192-token context (longer than 512 of previous multilingual encoders).
Chinese Sequence Labeling with Semi-Supervised Boundary-Aware Language Model Pre-training
Experimental results on Chinese sequence labeling datasets demonstrate that the improved BABERT variant outperforms the vanilla version, not only on these tasks but also more broadly across a range of Chinese natural language understanding tasks.
A Two-Stage Adaptation of Large Language Models for Text Ranking
In this work, we propose a two-stage progressive paradigm to better adapt LLMs to text ranking.
Text Representation Distillation via Information Bottleneck Principle
Pre-trained language models (PLMs) have recently shown great success in text representation field.
Language Models are Universal Embedders
As such cases span from English to other natural or programming languages, from retrieval to classification and beyond, it is desirable to build a unified embedding model rather than dedicated ones for each scenario.
Hybrid Retrieval and Multi-stage Text Ranking Solution at TREC 2022 Deep Learning Track
Large-scale text retrieval technology has been widely used in various practical business scenarios.
Towards General Text Embeddings with Multi-stage Contrastive Learning
We present GTE, a general-purpose text embedding model trained with multi-stage contrastive learning.
Challenging Decoder helps in Masked Auto-Encoder Pre-training for Dense Passage Retrieval
Recently, various studies have been directed towards exploring dense passage retrieval techniques employing pre-trained language models, among which the masked auto-encoder (MAE) pre-training architecture has emerged as the most promising.
Retrieval Oriented Masking Pre-training Language Model for Dense Passage Retrieval
Pre-trained language model (PTM) has been shown to yield powerful text representations for dense passage retrieval task.
Unsupervised Boundary-Aware Language Model Pretraining for Chinese Sequence Labeling
We apply BABERT for feature induction of Chinese sequence labeling tasks.
Ranked #1 on
Chinese Word Segmentation
on MSRA
Chinese Named Entity Recognition
Chinese Word Segmentation
+4
HLATR: Enhance Multi-stage Text Retrieval with Hybrid List Aware Transformer Reranking
Existing text retrieval systems with state-of-the-art performance usually adopt a retrieve-then-reranking architecture due to the high computational cost of pre-trained language models and the large corpus size.
Ranked #1 on
Passage Re-Ranking
on MS MARCO
Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrieval
We find that the performance of retrieval models trained on dataset from general domain will inevitably decrease on specific domain.
Keyphrase Extraction with Dynamic Graph Convolutional Networks and Diversified Inference
Keyphrase extraction (KE) aims to summarize a set of phrases that accurately express a concept or a topic covered in a given document.
Coupling Distant Annotation and Adversarial Training for Cross-Domain Chinese Word Segmentation
In order to simultaneously alleviate these two issues, this paper proposes to couple distant annotation and adversarial training for cross-domain CWS.
Hierarchy-Aware Global Model for Hierarchical Text Classification
Hierarchical text classification is an essential yet challenging subtask of multi-label text classification with a taxonomic hierarchy.
General Classification
Hierarchical Multi-label Classification
+4
Understanding Feature Selection and Feature Memorization in Recurrent Neural Networks
Gated models resolve this conflict by adaptively adjusting their state-update equations, whereas Vanilla RNN resolves this conflict by assigning different dimensions different tasks.
Prototypical Recurrent Unit
For this purpose, we design a simple and controllable task, called ``memorization problem'', where the networks are trained to memorize certain targeted information.
