arXiv subjects

Yingxia Shao

Publications and source records attributed to Yingxia Shao.

At least 55 records · Page 3Linked to original sources

arXiv2023

RetroMAE-2: Duplex Masked Auto-Encoder For Pre-Training Retrieval-Oriented Language Models

To better support information retrieval tasks such as web search and open-domain question answering, growing effort is made to develop retrieval-oriented language models, e.g., RetroMAE and many others. Most of the existing works focus on improving the semantic representation capability for the contextualized embedding of the [CLS] token. However, recent study shows that the ordinary tokens besides [CLS] may provide extra information, which help to produce a better representation effect. As such, it's necessary to extend the current methods where all contextualized embeddings can be jointly pre-trained for the retrieval tasks. In this work, we propose a novel pre-training method called Duplex Masked Auto-Encoder, a.k.a. DupMAE. It is designed to improve the quality of semantic representation where all contextualized embeddings of the pre-trained model can be leveraged. It takes advantage of two complementary auto-encoding tasks: one reconstructs the input sentence on top of the [CLS] embedding; the other one predicts the bag-of-words feature of the input sentence based on the ordinary tokens' embeddings. The two tasks are jointly conducted to train a unified encoder, where the whole contextualized embeddings are aggregated in a compact way to produce the final semantic representation. DupMAE is simple but empirically competitive: it substantially improves the pre-trained model's representation capability and transferability, where superior retrieval performances can be achieved on popular benchmarks, like MS MARCO and BEIR.

cs.CL↗

arXiv2022

Efficient Graph Neural Network Inference at Large Scale

Graph neural networks (GNNs) have demonstrated excellent performance in a wide range of applications. However, the enormous size of large-scale graphs hinders their applications under real-time inference scenarios. Although existing scalable GNNs leverage linear propagation to preprocess the features and accelerate the training and inference procedure, these methods still suffer from scalability issues when making inferences on unseen nodes, as the feature preprocessing requires the graph is known and fixed. To speed up the inference in the inductive setting, we propose a novel adaptive propagation order approach that generates the personalized propagation order for each node based on its topological information. This could successfully avoid the redundant computation of feature propagation. Moreover, the trade-off between accuracy and inference latency can be flexibly controlled by simple hyper-parameters to match different latency constraints of application scenarios. To compensate for the potential inference accuracy loss, we further propose Inception Distillation to exploit the multi scale reception information and improve the inference performance. Extensive experiments are conducted on four public datasets with different scales and characteristics, and the experimental results show that our proposed inference acceleration framework outperforms the SOTA graph inference acceleration baselines in terms of both accuracy and efficiency. In particular, the advantage of our proposed method is more significant on larger-scale datasets, and our framework achieves $75\times$ inference speedup on the largest Ogbn-products dataset.

cs.LG↗

arXiv2022

Web Page Content Extraction Based on Multi-feature Fusion

With the rapid development of Internet technology, people have more and more access to a variety of web page resources. At the same time, the current rapid development of deep learning technology is often inseparable from the huge amount of Web data resources. On the other hand, NLP is also an important part of data processing technology, such as web page data extraction. At present, the extraction technology of web page text mainly uses a single heuristic function or strategy, and most of them need to determine the threshold manually. With the rapid growth of the number and types of web resources, there are still problems to be solved when using a single strategy to extract the text information of different pages. This paper proposes a web page text extraction algorithm based on multi-feature fusion. According to the text information characteristics of web resources, DOM nodes are used as the extraction unit to design multiple statistical features, and high-order features are designed according to heuristic strategies. This method establishes a small neural network, takes multiple features of DOM nodes as input, predicts whether the nodes contain text information, makes full use of different statistical information and extraction strategies, and adapts to more types of pages. Experimental results show that this method has a good ability of web page text extraction and avoids the problem of manually determining the threshold.

cs.IR↗

arXiv2022

RetroMAE: Pre-Training Retrieval-oriented Language Models Via Masked Auto-Encoder

Despite pre-training's progress in many important NLP tasks, it remains to explore effective pre-training strategies for dense retrieval. In this paper, we propose RetroMAE, a new retrieval oriented pre-training paradigm based on Masked Auto-Encoder (MAE). RetroMAE is highlighted by three critical designs. 1) A novel MAE workflow, where the input sentence is polluted for encoder and decoder with different masks. The sentence embedding is generated from the encoder's masked input; then, the original sentence is recovered based on the sentence embedding and the decoder's masked input via masked language modeling. 2) Asymmetric model structure, with a full-scale BERT like transformer as encoder, and a one-layer transformer as decoder. 3) Asymmetric masking ratios, with a moderate ratio for encoder: 15~30%, and an aggressive ratio for decoder: 50~70%. Our framework is simple to realize and empirically competitive: the pre-trained models dramatically improve the SOTA performances on a wide range of dense retrieval benchmarks, like BEIR and MS MARCO. The source code and pre-trained models are made publicly available at https://github.com/staoxiao/RetroMAE so as to inspire more interesting research.

cs.CL↗

arXiv2022

Adaptive Dual Channel Convolution Hypergraph Representation Learning for Technological Intellectual Property

In the age of big data, the demand for hidden information mining in technological intellectual property is increasing in discrete countries. Definitely, a considerable number of graph learning algorithms for technological intellectual property have been proposed. The goal is to model the technological intellectual property entities and their relationships through the graph structure and use the neural network algorithm to extract the hidden structure information in the graph. However, most of the existing graph learning algorithms merely focus on the information mining of binary relations in technological intellectual property, ignoring the higherorder information hidden in non-binary relations. Therefore, a hypergraph neural network model based on dual channel convolution is proposed. For the hypergraph constructed from technological intellectual property data, the hypergraph channel and the line expanded graph channel of the hypergraph are used to learn the hypergraph, and the attention mechanism is introduced to adaptively fuse the output representations of the two channels. The proposed model outperforms the existing approaches on a variety of datasets.

cs.IR↗

arXiv2022

A Relational Triple Extraction Method Based on Feature Reasoning for Technological Patents

The relation triples extraction method based on table filling can address the issues of relation overlap and bias propagation. However, most of them only establish separate table features for each relationship, which ignores the implicit relationship between different entity pairs and different relationship features. Therefore, a feature reasoning relational triple extraction method based on table filling for technological patents is proposed to explore the integration of entity recognition and entity relationship, and to extract entity relationship triples from multi-source scientific and technological patents data. Compared with the previous methods, the method we proposed for relational triple extraction has the following advantages: 1) The table filling method that saves more running space enhances the speed and efficiency of the model. 2) Based on the features of existing token pairs and table relations, reasoning the implicit relationship features, and improve the accuracy of triple extraction. On five benchmark datasets, we evaluated the model we suggested. The result suggest that our model is advanced and effective, and it performed well on most of these datasets.

cs.IR↗

arXiv2022

A Rare Topic Discovery Model for Short Texts Based on Co-occurrence word Network

We provide a simple and general solution for the discovery of scarce topics in unbalanced short-text datasets, namely, a word co-occurrence network-based model CWIBTD, which can simultaneously address the sparsity and unbalance of short-text topics and attenuate the effect of occasional pairwise occurrences of words, allowing the model to focus more on the discovery of scarce topics. Unlike previous approaches, CWIBTD uses co-occurrence word networks to model the topic distribution of each word, which improves the semantic density of the data space and ensures its sensitivity in identify-ing rare topics by improving the way node activity is calculated and normal-izing scarce topics and large topics to some extent. In addition, using the same Gibbs sampling as LDA makes CWIBTD easy to be extended to vari-ous application scenarios. Extensive experimental validation in the unbal-anced short text dataset confirms the superiority of CWIBTD over the base-line approach in discovering rare topics. Our model can be used for early and accurate discovery of emerging topics or unexpected events on social platforms.

cs.IR↗

arXiv2022

Social Network Community Detection Based on Textual Content Similarity and Sentimental Tendency

Shared travel has gradually become one of the hot topics discussed on social networking platforms such as Micro Blog. In a timely manner, deeper network community detection on the evaluation content of shared travel in social networks can effectively conduct research and analysis on the public opinion orientation related to shared travel, which has great application prospects. The existing community detection algorithms generally measure the similarity of nodes in the network from the perspective of spatial distance. This paper proposes a Community detection algorithm based on Textual content Similarity and sentimental Tendency (CTST), considering the network structure and node attributes at the same time. The content similarity and sentimental tendency of network community users are taken as node attributes, and on this basis, an undirected weighted network is constructed for community detection. This paper conducts experiments with actual data and analyzes the experimental results. It is found that the modularity of the community detection results is high and the effect is good.

cs.SI↗

arXiv2022

A sentiment analysis model for car review texts based on adversarial training and whole word mask BERT

In the field of car evaluation, more and more netizens choose to express their opinions on the Internet platform, and these comments will affect the decision-making of buyers and the trend of car word-of-mouth. As an important branch of natural language processing (NLP), sentiment analysis provides an effective research method for analyzing the sentiment types of massive car review texts. However, due to the lexical professionalism and large text noise of review texts in the automotive field, when a general sentiment analysis model is applied to car reviews, the accuracy of the model will be poor. To overcome these above challenges, we aim at the sentiment analysis task of car review texts. From the perspective of word vectors, pre-training is carried out by means of whole word mask of proprietary vocabulary in the automotive field, and then training data is carried out through the strategy of an adversarial training set. Based on this, we propose a car review text sentiment analysis model based on adversarial training and whole word mask BERT(ATWWM-BERT).

cs.CL↗

arXiv2022

Sentiment Analysis of Online Travel Reviews Based on Capsule Network and Sentiment Lexicon

With the development of online travel services, it has great application prospects to timely mine users' evaluation emotions for travel services and use them as indicators to guide the improvement of online travel service quality. In this paper, we study the text sentiment classification of online travel reviews based on social media online comments and propose the SCCL model based on capsule network and sentiment lexicon. SCCL model aims at the lack of consideration of local features and emotional semantic features of the text in the language model that can efficiently extract text context features like BERT and GRU. Then make the following improvements to their shortcomings. On the one hand, based on BERT-BiGRU, the capsule network is introduced to extract local features while retaining good context features. On the other hand, the sentiment lexicon is introduced to extract the emotional sequence of the text to provide richer emotional semantic features for the model. To enhance the universality of the sentiment lexicon, the improved SO-PMI algorithm based on TF-IDF is used to expand the lexicon, so that the lexicon can also perform well in the field of online travel reviews.

cs.CL↗

arXiv2022

Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network

Heterogeneous Graph Neural Network (HGNN) has been successfully employed in various tasks, but we cannot accurately know the importance of different design dimensions of HGNNs due to diverse architectures and applied scenarios. Besides, in the research community of HGNNs, implementing and evaluating various tasks still need much human effort. To mitigate these issues, we first propose a unified framework covering most HGNNs, consisting of three components: heterogeneous linear transformation, heterogeneous graph transformation, and heterogeneous message passing layer. Then we build a platform Space4HGNN by defining a design space for HGNNs based on the unified framework, which offers modularized components, reproducible implementations, and standardized evaluation for HGNNs. Finally, we conduct experiments to analyze the effect of different designs. With the insights found, we distill a condensed design space and verify its effectiveness.

cs.LG↗

arXiv2022

Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense Embeddings

Vector quantization (VQ) based ANN indexes, such as Inverted File System (IVF) and Product Quantization (PQ), have been widely applied to embedding based document retrieval thanks to the competitive time and memory efficiency. Originally, VQ is learned to minimize the reconstruction loss, i.e., the distortions between the original dense embeddings and the reconstructed embeddings after quantization. Unfortunately, such an objective is inconsistent with the goal of selecting ground-truth documents for the input query, which may cause severe loss of retrieval quality. Recent works identify such a defect, and propose to minimize the retrieval loss through contrastive learning. However, these methods intensively rely on queries with ground-truth documents, whose performance is limited by the insufficiency of labeled data. In this paper, we propose Distill-VQ, which unifies the learning of IVF and PQ within a knowledge distillation framework. In Distill-VQ, the dense embeddings are leveraged as "teachers", which predict the query's relevance to the sampled documents. The VQ modules are treated as the "students", which are learned to reproduce the predicted relevance, such that the reconstructed embeddings may fully preserve the retrieval result of the dense embeddings. By doing so, Distill-VQ is able to derive substantial training signals from the massive unlabeled data, which significantly contributes to the retrieval quality. We perform comprehensive explorations for the optimal conduct of knowledge distillation, which may provide useful insights for the learning of VQ based ANN index. We also experimentally show that the labeled data is no longer a necessity for high-quality vector quantization, which indicates Distill-VQ's strong applicability in practice.

cs.IR↗

arXiv2022

Scientific and Technological Text Knowledge Extraction Method of based on Word Mixing and GRU

The knowledge extraction task is to extract triple relations (head entity-relation-tail entity) from unstructured text data. The existing knowledge extraction methods are divided into "pipeline" method and joint extraction method. The "pipeline" method is to separate named entity recognition and entity relationship extraction and use their own modules to extract them. Although this method has better flexibility, the training speed is slow. The learning model of joint extraction is an end-to-end model implemented by neural network to realize entity recognition and relationship extraction at the same time, which can well preserve the association between entities and relationships, and convert the joint extraction of entities and relationships into a sequence annotation problem. In this paper, we propose a knowledge extraction method for scientific and technological resources based on word mixture and GRU, combined with word mixture vector mapping method and self-attention mechanism, to effectively improve the effect of text relationship extraction for Chinese scientific and technological resources.

cs.CL↗

arXiv2022

An I/O-Efficient Disk-based Graph System for Scalable Second-Order Random Walk of Large Graphs

Random walk is widely used in many graph analysis tasks, especially the first-order random walk. However, as a simplification of real-world problems, the first-order random walk is poor at modeling higher-order structures in the data. Recently, second-order random walk-based applications (e.g., Node2vec, Second-order PageRank) have become attractive. Due to the complexity of the second-order random walk models and memory limitations, it is not scalable to run second-order random walk-based applications on a single machine. Existing disk-based graph systems are only friendly to the first-order random walk models and suffer from expensive disk I/Os when executing the second-order random walks. This paper introduces an I/O-efficient disk-based graph system for the scalable second-order random walk of large graphs, called GraSorw. First, to eliminate massive light vertex I/Os, we develop a bi-block execution engine that converts random I/Os into sequential I/Os by applying a new triangular bi-block scheduling strategy, the bucket-based walk management, and the skewed walk storage. Second, to improve the I/O utilization, we design a learning-based block loading model to leverage the advantages of the full-load and on-demand load methods. Finally, we conducted extensive experiments on six large real datasets as well as several synthetic datasets. The empirical results demonstrate that the end-to-end time cost of popular tasks in GraSorw is reduced by more than one order of magnitude compared to the existing disk-based graph systems.

cs.DB↗

arXiv2022

An Intellectual Property Entity Recognition Method Based on Transformer and Technological Word Information

Patent texts contain a large amount of entity information. Through named entity recognition, intellectual property entity information containing key information can be extracted from it, helping researchers to understand the patent content faster. Therefore, it is difficult for existing named entity extraction methods to make full use of the semantic information at the word level brought about by professional vocabulary changes. This paper proposes a method for extracting intellectual property entities based on Transformer and technical word information , and provides accurate word vector representation in combination with the BERT language method. In the process of word vector generation, the technical word information extracted by IDCNN is added to improve the understanding of intellectual property entities Representation ability. Finally, the Transformer encoder that introduces relative position encoding is used to learn the deep semantic information of the text from the sequence of word vectors, and realize entity label prediction. Experimental results on public datasets and annotated patent datasets show that the method improves the accuracy of entity recognition.

cs.CL↗

arXiv2022

Progressively Optimized Bi-Granular Document Representation for Scalable Embedding Based Retrieval

Ad-hoc search calls for the selection of appropriate answers from a massive-scale corpus. Nowadays, the embedding-based retrieval (EBR) becomes a promising solution, where deep learning based document representation and ANN search techniques are allied to handle this task. However, a major challenge is that the ANN index can be too large to fit into memory, given the considerable size of answer corpus. In this work, we tackle this problem with Bi-Granular Document Representation, where the lightweight sparse embeddings are indexed and standby in memory for coarse-grained candidate search, and the heavyweight dense embeddings are hosted in disk for fine-grained post verification. For the best of retrieval accuracy, a Progressive Optimization framework is designed. The sparse embeddings are learned ahead for high-quality search of candidates. Conditioned on the candidate distribution induced by the sparse embeddings, the dense embeddings are continuously learned to optimize the discrimination of ground-truth from the shortlisted candidates. Besides, two techniques: the contrastive quantization and the locality-centric sampling are introduced for the learning of sparse and dense embeddings, which substantially contribute to their performances. Thanks to the above features, our method effectively handles massive-scale EBR with strong advantages in accuracy: with up to +4.3% recall gain on million-scale corpus, and up to +17.5% recall gain on billion-scale corpus. Besides, Our method is applied to a major sponsored search platform with substantial gains on revenue (+1.95%), Recall (+1.01%) and CTR (+0.49%). Our code is available at https://github.com/microsoft/BiDR.

cs.IR↗

arXiv2022

Uni-Retriever: Towards Learning The Unified Embedding Based Retriever in Bing Sponsored Search

Embedding based retrieval (EBR) is a fundamental building block in many web applications. However, EBR in sponsored search is distinguished from other generic scenarios and technically challenging due to the need of serving multiple retrieval purposes: firstly, it has to retrieve high-relevance ads, which may exactly serve user's search intent; secondly, it needs to retrieve high-CTR ads so as to maximize the overall user clicks. In this paper, we present a novel representation learning framework Uni-Retriever developed for Bing Search, which unifies two different training modes knowledge distillation and contrastive learning to realize both required objectives. On one hand, the capability of making high-relevance retrieval is established by distilling knowledge from the ``relevance teacher model''. On the other hand, the capability of making high-CTR retrieval is optimized by learning to discriminate user's clicked ads from the entire corpus. The two training modes are jointly performed as a multi-objective learning process, such that the ads of high relevance and CTR can be favored by the generated embeddings. Besides the learning strategy, we also elaborate our solution for EBR serving pipeline built upon the substantially optimized DiskANN, where massive-scale EBR can be performed with competitive time and memory efficiency, and accomplished in high-quality. We make comprehensive offline and online experiments to evaluate the proposed techniques, whose findings may provide useful insights for the future development of EBR systems. Uni-Retriever has been mainstreamed as the major retrieval path in Bing's production thanks to the notable improvements on the representation and EBR serving quality.

cs.IR↗

arXiv2021

Efficient Diversity-Driven Ensemble for Deep Neural Networks

The ensemble of deep neural networks has been shown, both theoretically and empirically, to improve generalization accuracy on the unseen test set. However, the high training cost hinders its efficiency since we need a sufficient number of base models and each one in the ensemble has to be separately trained. Lots of methods are proposed to tackle this problem, and most of them are based on the feature that a pre-trained network can transfer its knowledge to the next base model and then accelerate the training process. However, these methods suffer a severe problem that all of them transfer knowledge without selection and thus lead to low diversity. As the effect of ensemble learning is more pronounced if ensemble members are accurate and diverse, we propose a method named Efficient Diversity-Driven Ensemble (EDDE) to address both the diversity and the efficiency of an ensemble. To accelerate the training process, we propose a novel knowledge transfer method which can selectively transfer the previous generic knowledge. To enhance diversity, we first propose a new diversity measure, then use it to define a diversity-driven loss function for optimization. At last, we adopt a Boosting-based framework to combine the above operations, such a method can also further improve diversity. We evaluate EDDE on Computer Vision (CV) and Natural Language Processing (NLP) tasks. Compared with other well-known ensemble methods, EDDE can get highest ensemble accuracy with the lowest training cost, which means it is efficient in the ensemble of neural networks.

cs.LG↗