arXiv subjects

Jizhong Han

Publications and source records attributed to Jizhong Han.

64 records · Page 4Linked to original sources

arXiv2020

TransSent: Towards Generation of Structured Sentences with Discourse Marker

Structured sentences are important expressions in human writings and dialogues. Previous works on neural text generation fused semantic and structural information by encoding the entire sentence into a mixed hidden representation. However, when a generated sentence becomes complicated, the structure is difficult to be properly maintained. To alleviate this problem, we explicitly separate the modeling process of semantic and structural information. Intuitively, humans generate structured sentences by directly connecting discourses with discourse markers (such as and, but, etc.). Therefore, we propose a task that mimics this process, called discourse transfer. This task represents a structured sentence as (head discourse, discourse marker, tail discourse), and aims at tail discourse generation based on head discourse and discourse marker. We also propose a corresponding model called TransSent, which interprets the relationship between two discourses as a translation1 from the head discourse to the tail discourse in the embedding space. We experiment TransSent not only in discourse transfer task but also in free text generation and dialogue generation tasks. Automatic and human evaluation results show that TransSent can generate structured sentences with high quality, and has certain scalability in different tasks.

cs.CL↗

arXiv2020

Data Augmentation for Copy-Mechanism in Dialogue State Tracking

While several state-of-the-art approaches to dialogue state tracking (DST) have shown promising performances on several benchmarks, there is still a significant performance gap between seen slot values (i.e., values that occur in both training set and test set) and unseen ones (values that occur in training set but not in test set). Recently, the copy-mechanism has been widely used in DST models to handle unseen slot values, which copies slot values from user utterance directly. In this paper, we aim to find out the factors that influence the generalization ability of a common copy-mechanism model for DST. Our key observations include: 1) the copy-mechanism tends to memorize values rather than infer them from contexts, which is the primary reason for unsatisfactory generalization performance; 2) greater diversity of slot values in the training set increase the performance on unseen values but slightly decrease the performance on seen values. Moreover, we propose a simple but effective algorithm of data augmentation to train copy-mechanism models, which augments the input dataset by copying user utterances and replacing the real slot values with randomly generated strings. Users could use two hyper-parameters to realize a trade-off between the performances on seen values and unseen ones, as well as a trade-off between overall performance and computational cost. Experimental results on three widely used datasets (WoZ 2.0, DSTC2, and Multi-WoZ 2.0) show the effectiveness of our approach.

cs.CL↗

arXiv2019

Jointly embedding the local and global relations of heterogeneous graph for rumor detection

The development of social media has revolutionized the way people communicate, share information and make decisions, but it also provides an ideal platform for publishing and spreading rumors. Existing rumor detection methods focus on finding clues from text content, user profiles, and propagation patterns. However, the local semantic relation and global structural information in the message propagation graph have not been well utilized by previous works. In this paper, we present a novel global-local attention network (GLAN) for rumor detection, which jointly encodes the local semantic and global structural information. We first generate a better integrated representation for each source tweet by fusing the semantic information of related retweets with the attention mechanism. Then, we model the global relationships among all source tweets, retweets, and users as a heterogeneous graph to capture the rich structural information for rumor detection. We conduct experiments on three real-world datasets, and the results demonstrate that GLAN significantly outperforms the state-of-the-art models in both rumor detection and early detection scenarios.

cs.CL↗

arXiv2019

Learning review representations from user and product level information for spam detection

Opinion spam has become a widespread problem in social media, where hired spammers write deceptive reviews to promote or demote products to mislead the consumers for profit or fame. Existing works mainly focus on manually designing discrete textual or behavior features, which cannot capture complex semantics of reviews. Although recent works apply deep learning methods to learn review-level semantic features, their models ignore the impact of the user-level and product-level information on learning review semantics and the inherent user-review-product relationship information. In this paper, we propose a Hierarchical Fusion Attention Network (HFAN) to automatically learn the semantics of reviews from the user and product level. Specifically, we design a multi-attention unit to extract user(product)-related review information. Then, we use orthogonal decomposition and fusion attention to learn a user, review, and product representation from the review information. Finally, we take the review as a relation between user and product entity and apply TransH to jointly encode this relationship into review representation. Experimental results obtained more than 10\% absolute precision improvement over the state-of-the-art performances on four real-world datasets, which show the effectiveness and versatility of the model.

cs.CL↗

arXiv2019

"Mask and Infill" : Applying Masked Language Model to Sentiment Transfer

This paper focuses on the task of sentiment transfer on non-parallel text, which modifies sentiment attributes (e.g., positive or negative) of sentences while preserving their attribute-independent content. Due to the limited capability of RNNbased encoder-decoder structure to capture deep and long-range dependencies among words, previous works can hardly generate satisfactory sentences from scratch. When humans convert the sentiment attribute of a sentence, a simple but effective approach is to only replace the original sentimental tokens in the sentence with target sentimental expressions, instead of building a new sentence from scratch. Such a process is very similar to the task of Text Infilling or Cloze, which could be handled by a deep bidirectional Masked Language Model (e.g. BERT). So we propose a two step approach "Mask and Infill". In the mask step, we separate style from content by masking the positions of sentimental tokens. In the infill step, we retrofit MLM to Attribute Conditional MLM, to infill the masked positions by predicting words or phrases conditioned on the context1 and target sentiment. We evaluate our model on two review datasets with quantitative, qualitative, and human evaluations. Experimental results demonstrate that our models improve state-of-the-art performance.

cs.CL↗

arXiv2019

AccUDNN: A GPU Memory Efficient Accelerator for Training Ultra-deep Neural Networks

Typically, Ultra-deep neural network(UDNN) tends to yield high-quality model, but its training process is usually resource intensive and time-consuming. Modern GPU's scarce DRAM capacity is the primary bottleneck that hinders the trainability and the training efficiency of UDNN. In this paper, we present "AccUDNN", an accelerator that aims to make the utmost use of finite GPU memory resources to speed up the training process of UDNN. AccUDNN mainly includes two modules: memory optimizer and hyperparameter tuner. Memory optimizer develops a performance-model guided dynamic swap out/in strategy, by offloading appropriate data to host memory, GPU memory footprint can be significantly slashed to overcome the restriction of trainability of UDNN. After applying the memory optimization strategy, hyperparameter tuner is designed to explore the efficiency-optimal minibatch size and the matched learning rate. Evaluations demonstrate that AccUDNN cuts down the GPU memory requirement of ResNet-152 from more than 24GB to 8GB. In turn, given 12GB GPU memory budget, the efficiency-optimal minibatch size can reach 4.2x larger than original Caffe. Benefiting from better utilization of single GPU's computing resources and fewer parameter synchronization of large minibatch size, 7.7x speed-up is achieved by 8 GPUs' cluster without any communication optimization and no accuracy losses.

cs.LG↗

arXiv2019

Imbalanced Sentiment Classification Enhanced with Discourse Marker

Imbalanced data commonly exists in real world, espacially in sentiment-related corpus, making it difficult to train a classifier to distinguish latent sentiment in text data. We observe that humans often express transitional emotion between two adjacent discourses with discourse markers like "but", "though", "while", etc, and the head discourse and the tail discourse 3 usually indicate opposite emotional tendencies. Based on this observation, we propose a novel plug-and-play method, which first samples discourses according to transitional discourse markers and then validates sentimental polarities with the help of a pretrained attention-based model. Our method increases sample diversity in the first place, can serve as a upstream preprocessing part in data augmentation. We conduct experiments on three public sentiment datasets, with several frequently used algorithms. Results show that our method is found to be consistently effective, even in highly imbalanced scenario, and easily be integrated with oversampling method to boost the performance on imbalanced sentiment classification.

cs.CL↗

arXiv2018

Conditional BERT Contextual Augmentation

We propose a novel data augmentation method for labeled sentences called conditional BERT contextual augmentation. Data augmentation methods are often applied to prevent overfitting and improve generalization of deep neural network models. Recently proposed contextual augmentation augments labeled sentences by randomly replacing words with more varied substitutions predicted by language model. BERT demonstrates that a deep bidirectional language model is more powerful than either an unidirectional language model or the shallow concatenation of a forward and backward model. We retrofit BERT to conditional BERT by introducing a new conditional masked language model\footnote{The term "conditional masked language model" appeared once in original BERT paper, which indicates context-conditional, is equivalent to term "masked language model". In our paper, "conditional masked language model" indicates we apply extra label-conditional constraint to the "masked language model".} task. The well trained conditional BERT can be applied to enhance contextual augmentation. Experiments on six various different text classification tasks show that our method can be easily applied to both convolutional or recurrent neural networks classifier to obtain obvious improvement.

cs.CL↗

arXiv2018

Cross-domain Human Parsing via Adversarial Feature and Label Adaptation

Human parsing has been extensively studied recently due to its wide applications in many important scenarios. Mainstream fashion parsing models focus on parsing the high-resolution and clean images. However, directly applying the parsers trained on benchmarks to a particular application scenario in the wild, e.g., a canteen, airport or workplace, often gives non-satisfactory performance due to domain shift. In this paper, we explore a new and challenging cross-domain human parsing problem: taking the benchmark dataset with extensive pixel-wise labeling as the source domain, how to obtain a satisfactory parser on a new target domain without requiring any additional manual labeling? To this end, we propose a novel and efficient cross-domain human parsing model to bridge the cross-domain differences in terms of visual appearance and environment conditions and fully exploit commonalities across domains. Our proposed model explicitly learns a feature compensation network, which is specialized for mitigating the cross-domain differences. A discriminative feature adversarial network is introduced to supervise the feature compensation to effectively reduce the discrepancy between feature distributions of two domains. Besides, our model also introduces a structured label adversarial network to guide the parsing results of the target domain to follow the high-order relationships of the structured labels shared across domains. The proposed framework is end-to-end trainable, practical and scalable in real applications. Extensive experiments are conducted where LIP dataset is the source domain and 4 different datasets including surveillance videos, movies and runway shows are evaluated as target domains. The results consistently confirm data efficiency and performance advantages of the proposed method for the cross-domain human parsing problem.

cs.CV↗

arXiv2011

Anomaly Sequences Detection from Logs Based on Compression

Mining information from logs is an old and still active research topic. In recent years, with the rapid emerging of cloud computing, log mining becomes increasingly important to industry. This paper focus on one major mission of log mining: anomaly detection, and proposes a novel method for mining abnormal sequences from large logs. Different from previous anomaly detection systems which based on statistics, probabilities and Markov assumption, our approach measures the strangeness of a sequence using compression. It first trains a grammar about normal behaviors using grammar-based compression, then measures the information quantities and densities of questionable sequences according to incrementation of grammar length. We have applied our approach on mining some real bugs from fine grained execution logs. We have also tested its ability on intrusion detection using some publicity available system call traces. The experiments show that our method successfully selects the strange sequences which related to bugs or attacking.

cs.LG↗