Search Results for author: Sheng Gao

Found 17 papers, 9 papers with code

Hybrid Multimodal Feature Extraction, Mining and Fusion for Sentiment Analysis

no code implementations5 Aug 2022 Jia Li, Ziyang Zhang, Junjie Lang, Yueqi Jiang, Liuwei An, Peng Zou, Yangyang Xu, Sheng Gao, Jie Lin, Chunxiao Fan, Xiao Sun, Meng Wang

In this paper, we present our solutions for the Multimodal Sentiment Analysis Challenge (MuSe) 2022, which includes MuSe-Humor, MuSe-Reaction and MuSe-Stress Sub-challenges.

Data Augmentation Humor Detection +1

Analytical Composition of Differential Privacy via the Edgeworth Accountant

1 code implementation9 Jun 2022 Hua Wang, Sheng Gao, Huanyu Zhang, Milan Shen, Weijie J. Su

Many modern machine learning algorithms are composed of simple private algorithms; thus, an increasingly important problem is to efficiently compute the overall privacy loss under composition.

Sparse GCA and Thresholded Gradient Descent

no code implementations1 Jul 2021 Sheng Gao, Zongming Ma

Based on a Lagrangian form of the sample optimization problem, we propose a thresholded gradient descent algorithm for estimating GCA loading vectors and matrices in high dimensions.

LiteGEM: Lite Geometry Enhanced Molecular Representation Learning for Quantum Property Prediction

1 code implementation28 Jun 2021 Shanzhuo Zhang, Lihang Liu, Sheng Gao, Donglong He, Xiaomin Fang, Weibin Li, Zhengjie Huang, Weiyue Su, Wenjin Wang

In this report, we (SuperHelix team) present our solution to KDD Cup 2021-PCQM4M-LSC, a large-scale quantum chemistry dataset on predicting HOMO-LUMO gap of molecules.

Representation Learning Self-Supervised Learning

A Joint Model for Dropped Pronoun Recovery and Conversational Discourse Parsing in Chinese Conversational Speech

1 code implementation ACL 2021 Jingxuan Yang, Kerui Xu, Jun Xu, Si Li, Sheng Gao, Jun Guo, Nianwen Xue, Ji-Rong Wen

A second (multi-relational) GCN is then applied to the utterance states to produce a discourse relation-augmented representation for the utterances, which are then fused together with token states in each utterance as input to a dropped pronoun recovery layer.

Discourse Parsing

Improving Abstractive Dialogue Summarization with Conversational Structure and Factual Knowledge

no code implementations1 Jan 2021 Lulu Zhao, Zeyuan Yang, Weiran Xu, Sheng Gao, Jun Guo

In this paper, we present a Knowledge Graph Enhanced Dual-Copy network (KGEDC), a novel framework for abstractive dialogue summarization with conversational structure and factual knowledge.

Abstractive Dialogue Summarization

Transformer-GCRF: Recovering Chinese Dropped Pronouns with General Conditional Random Fields

1 code implementation Findings of the Association for Computational Linguistics 2020 Jingxuan Yang, Kerui Xu, Jun Xu, Si Li, Sheng Gao, Jun Guo, Ji-Rong Wen, Nianwen Xue

Exploratory analysis also demonstrates that the GCRF did help to capture the dependencies between pronouns in neighboring utterances, thus contributes to the performance improvements.

Machine Translation Translation

Recovering Dropped Pronouns in Chinese Conversations via Modeling Their Referents

1 code implementation NAACL 2019 Jingxuan Yang, Jianzhuo Tong, Si Li, Sheng Gao, Jun Guo, Nianwen Xue

Pronouns are often dropped in Chinese sentences, and this happens more frequently in conversational genres as their referents can be easily understood from context.

Machine Translation Translation

Guiding Generation for Abstractive Text Summarization Based on Key Information Guide Network

no code implementations NAACL 2018 Chenliang Li, Weiran Xu, Si Li, Sheng Gao

Then, we introduce a Key Information Guide Network (KIGN), which encodes the keywords to the key information representation, to guide the process of generation.

Abstractive Text Summarization

A Tree Search Algorithm for Sequence Labeling

1 code implementation29 Apr 2018 Yadi Lao, Jun Xu, Yanyan Lan, Jiafeng Guo, Sheng Gao, Xue-Qi Cheng

Inspired by the success and methodology of the AlphaGo Zero, MM-Tag formalizes the problem of sequence tagging with a Monte Carlo tree search (MCTS) enhanced Markov decision process (MDP) model, in which the time steps correspond to the positions of words in a sentence from left to right, and each action corresponds to assign a tag to a word.

Chunking Decision Making +2

Neural Regularized Domain Adaptation for Chinese Word Segmentation

no code implementations WS 2017 Zuyi Bao, Si Li, Weiran Xu, Sheng Gao

For Chinese word segmentation, the large-scale annotated corpora mainly focus on newswire and only a handful of annotated data is available in other domains such as patents and literature.

Chinese Word Segmentation Domain Adaptation +2

Improving Cross-domain Recommendation through Probabilistic Cluster-level Latent Factor Model--Extended Version

no code implementations24 Sep 2014 Siting Ren, Sheng Gao

Cross-domain recommendation has been proposed to transfer user behavior pattern by pooling together the rating data from multiple domains to alleviate the sparsity problem appearing in single rating domains.

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