Search Results for author: Xianming Li

Found 9 papers, 6 papers with code

TDEER: An Efficient Translating Decoding Schema for Joint Extraction of Entities and Relations

1 code implementation EMNLP 2021 Xianming Li, Xiaotian Luo, Chenghao Dong, Daichuan Yang, Beidi Luan, Zhen He

To address such a problem, this paper proposes a novel efficient entities and relations extraction model called TDEER, which stands for Translating Decoding Schema for Joint Extraction of Entities and Relations.

Joint Entity and Relation Extraction Relation

ESE: Espresso Sentence Embeddings

1 code implementation22 Feb 2024 Xianming Li, Zongxi Li, Jing Li, Haoran Xie, Qing Li

High-quality sentence embeddings are fundamental in many natural language processing (NLP) tasks, such as semantic textual similarity (STS) and retrieval-augmented generation (RAG).

RAG Retrieval +5

Generative Deduplication For Socia Media Data Selection

no code implementations11 Jan 2024 Xianming Li, Jing Li

By doing so, it can improve social media language understanding performance and save training time.

Label Supervised LLaMA Finetuning

2 code implementations2 Oct 2023 Zongxi Li, Xianming Li, Yuzhang Liu, Haoran Xie, Jing Li, Fu-lee Wang, Qing Li, Xiaoqin Zhong

We evaluate this approach with Label Supervised LLaMA (LS-LLaMA), based on LLaMA-2-7B, a relatively small-scale LLM, and can be finetuned on a single GeForce RTX4090 GPU.

 Ranked #1 on Named Entity Recognition (NER) on CoNLL03 (F1 (micro) metric)

named-entity-recognition Named Entity Recognition +7

AnglE-optimized Text Embeddings

2 code implementations22 Sep 2023 Xianming Li, Jing Li

This novel approach effectively mitigates the adverse effects of the saturation zone in the cosine function, which can impede gradient and hinder optimization processes.

Language Modelling Large Language Model +3

Recurrent Attention Networks for Long-text Modeling

1 code implementation12 Jun 2023 Xianming Li, Zongxi Li, Xiaotian Luo, Haoran Xie, Xing Lee, Yingbin Zhao, Fu Lee Wang, Qing Li

Revisiting the self-attention mechanism and the recurrent structure, this paper proposes a novel long-document encoding model, Recurrent Attention Network (RAN), to enable the recurrent operation of self-attention.

Chunking

Robust Downlink Transmit Optimization under Quantized Channel Feedback via the Strong Duality for QCQP

no code implementations14 Dec 2020 Xianming Li, Yongwei Huang, Wing-Kin Ma

The minimization problem is accordingly turned into a QMI problem, and the problem is solved by a restricted linear matrix inequality relaxation with additional valid convex constraints.

Quantization valid

Incorporating Effective Global Information via Adaptive Gate Attention for Text Classification

no code implementations22 Feb 2020 Xianming Li, Zongxi Li, Yingbin Zhao, Haoran Xie, Qing Li

The dominant text classification studies focus on training classifiers using textual instances only or introducing external knowledge (e. g., hand-craft features and domain expert knowledge).

General Classification Sentence +2

Cannot find the paper you are looking for? You can Submit a new open access paper.