Qiaoming Zhu

Soochow University (PRC) | SUDA · Department of Computer Science and Technology

Discourse parsing aims to comprehend the structure and semantics of a document. Some previous studies have taken multiple levels of granularity methods to parse documents while disregarding the connection between granularity levels. Additionally, almost all the Chinese discourse parsing approaches concentrated on a single granularity due to lacking...

Discourse functional pragmatics recognition focuses on identifying the functions of discourse paragraphs, which is a significant research direction in natural language processing. To obtain better paragraph representation and alleviate the issue of imbalanced data distribution, we propose a Chinese discourse Functional Pragmatics Recognition model...

Due to the rapid spread of rumors on social media and their negative impact on society, real-time rumor detection is of utmost importance. Although some rumor detection methods have applied the structure of temporal or graphic information, they do not consider multiple structures to obtain better representation. Besides, since the authors maybe onl...

The study of discourse functional pragmatic structure attaches importance to the function of discourse units. Existing models have poor performance in the functional pragmatics recognition of minority categories and ignore discourse dependency structure to enhance the representation of discourse units. To address the above issues, we propose a Func...

The goal of dialogue topic shift detection is to identify whether the current topic in a conversation has changed or needs to change. Previous work focused on detecting topic shifts using pre-trained models to encode the utterance, failing to delve into the various levels of topic granularity in the dialogue and understand dialogue contents. To add...

Topic segmentation and outline generation strive to divide a document into coherent topic sections and generate corresponding subheadings. Such a process unveils the discourse topic structure of a document that benefits quickly grasping and understanding the overall context of the document from a higher level. However, research and applications in...

Discourse parsing, the task of analyzing the internal rhetorical structure of texts, is a challenging problem in natural language processing. Despite the recent advances in neural models, the lack of large-scale, high-quality corpora for training remains a major obstacle. Recent studies have attempted to overcome this limitation by using distant su...

The goal of dialogue topic shift detection is to identify whether the current topic in a conversation has changed or needs to change. Previous work focused on detecting topic shifts using pre-trained models to encode the utterance, failing to delve into the various levels of topic granularity in the dialogue and understand dialogue contents. To add...

As a key sub-task in the field of speculation and negation extraction, Speculation and Negation Scope Resolution (SpNeSR) focuses on extracting speculative and negative texts within sentences, i.e., distinguishing between factual and non-factual information, which means it is an important and fundamental task in Natural Language Processing (NLP) co...

Identifying temporal relationship between events is crucial to text understanding. Recent work on temporal relation extraction only focuses on single Event-Event (E-E) relations, ignoring the other Event-DCT (E-D) and Event-Timex (E-T) relations and suffering from imbalanced annotation. Moreover, few previous work can directly learn time intervals...

Document-level Event Factuality Identification (DEFI) predicts the event factuality according to the current document, and mainly depends on event-related tokens and sentences. However, previous studies relied on annotated information and did not filter irrelevant and noisy texts. Therefore, this paper proposes a novel end-to-end model, i.e., Reinf...

Currently, more and more individuals tend to publish texts and images on social media to express their views. Inevitably, social media platform has become a media for a large number of rumors. There are a few studies on multi-modal rumor detection. However, most of them simplified the fusion strategy of texts and images and ignored the rich knowled...

The existing event coreference resolution models is hard to identify the coreferent relation between non-verb-triggered event mention and verb-triggered event mention, due to their different expressions. Motivated by the recent successful application of the sentence rewriting models on information extraction and the fact that event triggers and arg...

Event coreference resolution is an important task in natural language processing. An event coreference resolution system is often divided into two tasks: Event Detection and Event Coreference Resolution. The common pipelined approaches detect the events first and then complete the event coreference resolution. However, this kind of system will brin...

Discourse relation recognition is to identify the logical relations between discourse units (DUs). Previous work on discourse relation recognition only considered the loss of prediction and ground truth before back-propagation in the form of a one-hot vector, which cannot reflect the relation coherence. To remedy this deficiency, we propose a macro...

Most previous studies on event coreference resolution usually focused on measuring the similarity between two event sentences. However, a sentence may contain more than one event and the redundant event information will interfere with the calculation of event similarity. To address the above issue, this paper proposes an event coreference resolutio...

The macro-level discourse parsing, as a fundamental task of macro discourse analysis, mainly focuses on converting a document into a hierarchical discourse tree at paragraph level. Most existing methods follow micro-level studies and suffer from the issues of semantic representation and the semantic interaction of the larger macro discourse units....

Temporal relation classification is a challenging task in Natural Language Processing (NLP) that faces many difficulties, such as imbalanced distribution of instances, and ambiguity of the vague instances. To address the above issues, this paper proposes a novel data augmentation method on the TimeBank-Dense (TBD) corpus to distinguish those vague...

As an important research issue in affective computing community, multi-modal emotion recognition has become a hot topic in the last few years. However, almost all existing studies perform multiple binary classification for each emotion with focus on complete time series data. In this paper, we focus on multi-modal emotion recognition in a multi-lab...

Hierarchically constructing micro (i.e., intra-sentence or inter-sentence) discourse structure trees using explicit boundaries (e.g., sentence and paragraph boundaries) has been proved to be an effective strategy. However, it is difficult to apply this strategy to document-level macro (i.e., inter-paragraph) discourse parsing, the more challenging...

Multi-modal named entity recognition (MNER) aims to discover named entities in free text and classify them into pre-defined types with images. However, dominant MNER models do not fully exploit fine-grained semantic correspondences between semantic units of different modalities, which have the potential to refine multi-modal representation learning...

Event factuality identification (EFI) is a task to judge the factuality of events in texts, and is also the basic task of many related applications in the field of Natural Language Processing (NLP), such as information extraction and rumor detection. Previous research on EFI relied on annotated information, which cannot be applied to real world app...

Event factuality represents the factual nature of events in texts, and describes whether an event is a fact, a possibility, or an impossible situation. Previous work usually used the embedding of event sentence to represent the event factuality, ignoring the other helpful evidence, such as negative words, speculative words and time words. To addres...

Temporal relation classification, an important branch of relation extraction, aims to identify the time sequence among events. Currently, Shortest Dependency Path (SDP) is widely used in various kinds of neural network models to capture the crucial information from sentences. However, while eliminating irrelevant words in event sentences, SDP will...

Most previous studies used various sequence learning models to represent discourse arguments, which not only limit the model to perceive global information, but also make it difficult to deal with long-distance dependencies when the discourse arguments are paragraph-level or document-level. To address the above issues, we propose a GCN-based neural...

Social media has developed rapidly due to its openness and freedom, and people can post information on Internet anytime and anywhere. However, social media has also become the main way for rumors to spread largely and quickly. Hence, it has become a huge challenge to automatically detect rumors among such a huge amount of information. Currently, th...

The enhancement of the carrying capacity of high-speed railway and the acceleration of train speed lead to the proliferation of signal interference in the communication network, which leads to the degradation of network performance and user service quality. To address the issue, we first classify the cell users in high-speed railway wireless commun...

Multi-modal sentiment analysis extends conventional text-based definition of sentiment analysis to a multi-modal setup where multiple relevant modalities are leveraged to perform sentiment analysis. In real applications, however, acquiring annotated multi-modal data is normally labor expensive and time-consuming. In this paper, we aim to reduce the...

Stance detection aims to assign a stance label (i.e., favor or against ) to a post towards a specific target. Recently, there is a growing interest in adopting neural models to detect stance of a document. However, most of these works focus on modeling the sequence of words to learn document representation, though other linguistic information,...

Computational modeling of human spoken language is an emerging research area in multimedia analysis spanning across the text and acoustic modalities. Multi-modal sentiment analysis is one of the most fundamental tasks in human spoken language understanding. In this paper, we propose a novel approach to selecting effective sentiment-relevant words f...

Nowadays, in the Natural Language Processing field, with the object of research gradually shifting from the word to sentence, paragraph and higher semantic units, discourse analysis is one crucial step toward a better understanding of how these articles are structured. Compared with micro-level, this has rarely been investigated in macro Chinese di...

Macro-discourse structure recognition is an important task in macro-discourse analysis. At present, the research on macro-discourse analysis mostly uses the manual features (e.g., the position features), and ignores the semantic information in topic level. In this paper, we first propose a multi-view neural network to construct Chinese macro discou...

Recently, emotion detection in conversations becomes a hot research topic in the Natural Language Processing community. In this paper, we focus on emotion detection in multi-speaker conversations instead of traditional two-speaker conversations in existing studies. Different from non-conversation text, emotion detection in conversation text has one...

We study implicit discourse relation detection, which is one of the most challenging tasks in the field of discourse analysis. We specialize in ambiguous implicit discourse relation, which is an imperceptible linguistic phenomenon and therefore difficult to identify and eliminate. In this paper, we first create a novel task named implicit discourse...

This paper focuses on automatic question generation (QG) that transforms a narrative sentence into an interrogative sentence. Recently, neural networks have been used in this task due to its extraordinary ability of semantics encoding and decoding. We propose an approach which incorporates semantics of the possible question type. We utilize the Con...

Discourse structure analysis is an important task in Natural Language Processing (NLP) and it is helpful to many NLP tasks, such as automatic summarization and information extraction. However, there are only a few researches on Chinese macro discourse structure analysis due to the lack of annotated corpora. In this paper, combining structure recogn...

Stance detection aims to automatically determine whether the author is in favor of or against a given target. In principle, the sentiment information of a post highly influences the stance. In this study, we aim to leverage the sentiment information of a post to improve the performance of stance detection. However, conventional discretemodels with...

Event factuality identification is an important semantic task in NLP. Traditional research heavily relies on annotated texts. This paper proposes a two-step framework, first extracting essential factors related with event factuality from raw texts as the input, and then identifying the factuality of events via a Generative Adversarial Network with...

This paper helps in study of the relationship between the photovoltaic power generation of large scale "fishing and PV complementary" grid-tied photovoltaic system and meteorological parameters, with multi-time scale power data from the photovoltaic power station and meteorological data over the same period of a whole year. The result indicates tha...

Most previous approaches used various kinds of plain similarity features to represent the similarity of a sentence pair, and one of its limitations is its weak representation ability. This paper introduces the relational structures representation (shallow syntactic tree, dependency tree) to compute sentence similarity. Experimental results manifest...

Active learning is an effective machine learning paradigm which can significantly reduce the amount of labor for manually annotating NLP corpora while achieving competitive performance. Previous studies on active learning are focused on corpora in one single language or two languages translated from each other. This paper proposes a Bilingual Paral...

In this paper, we describe our participation in the fourth shared task (NLPCC-ICCPOL 2016 Shared Task 4) on the stance detection in Chinese Micro-blogs (subtask A). Different from ordinary features, we explore four linguistic features including lexical features, morphology features, semantic features and syntax features in Chinese micro-blogs in st...

Event co-reference and event temporal relations are two important types of event relations, which are widely used in many NLP applications, such as information extraction, text summarization, question answering system, etc. Event temporal relations provide much useful semantic and discourse information for more accurate co-reference resolution. How...

Although several semi-supervised learning models have been proposed for English event extraction, there are few successful stories in Chinese due to its special characteristics. In this article, we propose a novel minimally supervised model for Chinese event extraction from multiple views. Besides the traditional pattern similarity view (PSV), a se...

Speculation and negation are important information to identify text factuality. In this paper, we propose a Convolutional Neural Network (CNN)-based model with probabil-istic weighted average pooling to address speculation and negation scope detection. In particular, our CNN-based model extracts those meaningful features from various syntactic path...

Lack of large scale training data is a challenge for conventional supervised relation extraction approach. Although distant supervision has been proposed to address this issue, it suffers from massive noise and the trained model cannot be applied to unseen relations. We present a novel approach for relation extraction which uses the relation defini...

Supervised event extraction methods suffer from the lack of high-quality event corpora. Active learning is applied to improve the efficiency of manual annotation. In particular, we introduce the uncertainty of argument classification into the active learning for pipeline and joint extraction models. For the pipeline model, we drive active learning...

Previous researches on event relation classification primarily rely on lexical and syntactic features. In this paper, we use a Shallow Convolutional Neural Network (SCNN) to extract event-level and cross-event semantic features for event relation classification. On the one hand, the shallow structure alleviates the over-fitting problem caused by th...

Identifying negative or speculative narrative fragments from facts is crucial for deep understanding on natural language processing (NLP). In this paper, we firstly construct a Chinese corpus which consists of three sub-corpora from different resources. We also present a general framework for Chinese negation and speculation identification. In our...

Micro-blog, a new social networking service is being widely used by the public to share ideas, disseminate information, and communicate with each other. Due to the large volume of information involved, it is a challenge to understand the retweet and diffusion process and find different pattern or characteristic on micro-blogs. How do we track the p...

Co-reference events occur frequently in texts and recognizing the co-reference events correctly is helpful for many NLP applications, including information extraction and text summarization. This paper presents an approach to Chinese event co-reference resolution. Due to the arbitrariness and polysemy of Chinese language, more effective features ar...

Currently, Chinese argument extraction mainly focuses on feature engineering, which cannot exploit inner relationships between event mentions in the same document. To address this issue, this paper learns the probabilities of entities fulfilling a specific role from the training set and the relationship among events to infer more arguments using Ma...

The research on temporal relations between events plays an important role in natural language processing tasks, such as information extraction, question answering and text summarization. In this paper, we first annotate a document-level corpus to be used for the recognition of temporal relations between Chinese events. We then introduce several eff...

Identifying negative or speculative narrative fragments from fact is crucial for natural language processing (NLP) applications. Previous studies on negation and speculation identification in Chinese language suffers much from two problems: corpus scarcity and the bottleneck in fundamental Chinese information processing. To resolve these problems,...

Linguistically informed features are provably useful in classifying implicit discourse relations among adjacent text spans. However the state of the art methods in this area suffer from either sparse natively implicit relation corpus or counter-intuitive artificially implicit one, and consequently either insufficient or distorted training in automa...

The event detection is one of the fundamental researches in wireless sensor networks (WSNs). Due to the consideration of various properties that reflect events status, the Composite event is more consistent with the objective world. Thus, the research of the Composite event becomes more realistic. In this paper, we analyze the characteristics of th...

Active learning (AL) has been proven effective to reduce human annotation efforts in NLP. However, previous studies on AL are limited to applications in a single language. This paper proposes a bilingual active learning paradigm for relation classification, where the unlabeled instances are first jointly chosen in terms of their prediction uncertai...

Negative expressions are common in natural language text and play a critical role in information extraction. However, the performances of current systems are far from satisfaction, largely due to its focus on intrasentence information and its failure to consider inter-sentence information. In this paper, we propose a graph model to enrich intrasent...

Negation and speculation are common in natural language text. Many applications, such as biomedical text mining and clinical information extraction, seek to distinguish positive/factual objects from negative/speculative ones (i.e., to determine what is negated or speculated) in biomedical texts. This paper proposes a novel task, called negation and...

By preventing attacks which exploit stack buffer overflow vulnerabilities, address space layout randomization is an effective way for embedded systems protection. However, ASLR will probably suffer exhaustive attacks because the pertinence is not strong. At present only coarse-grained randomization has been implemented because one of the key bottle...

Argument extraction is a challenging task in event extraction. However, most of previous studies focused on intra-sentence information and failed to extract inter-sentence arguments. This paper proposes a discourse-level joint model of argument identification and role determination to infer those inter-sentence arguments in a discourse. Moreover, t...

As a paratactic language, sentence-level argument extraction in Chinese suffers much from the frequent occurrence of ellipsis with regard to inter-sentence arguments. To resolve such problem, this paper proposes a novel global argument inference model to explore specific relationships, such as Coreference, Sequence and Parallel, among relevant even...