Sentence Graph Research Articles

BioEGRE: a linguistic topology enhanced method for biomedical relation extraction based on BioELECTRA and graph pointer neural network

BackgroundAutomatic and accurate extraction of diverse biomedical relations from literature is a crucial component of bio-medical text mining. Currently, stacking various classification networks on pre-trained language models to perform fine-tuning is a common framework to end-to-end solve the biomedical relation extraction (BioRE) problem. However, the sequence-based pre-trained language models underutilize the graphical topology of language to some extent. In addition, sequence-oriented deep neural networks have limitations in processing graphical features.ResultsIn this paper, we propose a novel method for sentence-level BioRE task, BioEGRE (BioELECTRA and Graph pointer neural net-work for Relation Extraction), aimed at leveraging the linguistic topological features. First, the biomedical literature is preprocessed to retain sentences involving pre-defined entity pairs. Secondly, SciSpaCy is employed to conduct dependency parsing; sentences are modeled as graphs based on the parsing results; BioELECTRA is utilized to generate token-level representations, which are modeled as attributes of nodes in the sentence graphs; a graph pointer neural network layer is employed to select the most relevant multi-hop neighbors to optimize representations; a fully-connected neural network layer is employed to generate the sentence-level representation. Finally, the Softmax function is employed to calculate the probabilities. Our proposed method is evaluated on three BioRE tasks: a multi-class (CHEMPROT) and two binary tasks (GAD and EU-ADR). The results show that our method achieves F1-scores of 79.97% (CHEMPROT), 83.31% (GAD), and 83.51% (EU-ADR), surpassing the performance of existing state-of-the-art models.ConclusionThe experimental results on 3 biomedical benchmark datasets demonstrate the effectiveness and generalization of BioEGRE, which indicates that linguistic topology and a graph pointer neural network layer explicitly improve performance for BioRE tasks.

SR3: Sentence Ranking, Reasoning, and Replication for Scenario-Based Essay Question Answering

Scenario-based question answering is a trending research topic in artificial intelligence. While existing efforts are focused on multiple-choice questions, in this article, we consider scenario-based essay question answering (SEQA). This task requires generating a paragraph-long answer from both the scenario description that contextualizes the question and from external knowledge. To solve the task, our approach sentence ranking, reasoning, and replication (SR3) selects top-ranked sentences from the scenario and external knowledge to feed a novel sequence-to-sequence model, which enhances the synergy between sentences by reasoning over a sentence graph and then generates an answer with a new sentence-level copying mechanism. SR3 significantly outperforms a variety of strong baseline methods on GeoSEQA, a dataset containing 4003 scenario-based essay questions collected from China’s high-school geography exams.

Automatic Text Summarization by Providing Coverage, Non-Redundancy, and Novelty Using Sentence Graph

The day-to-day growth of online information necessitates intensive research in automatic text summarization (ATS). The ATS software produces summary text by extracting important information from the original text. With the help of summaries, users can easily read and understand the documents of interest. Most of the approaches for ATS used only local properties of text. Moreover, the numerous properties make the sentence selection difficult and complicated. So this article uses a graph based summarization to utilize structural and global properties of text. It introduces maximal clique based sentence selection (MCBSS) algorithm to select important and non-redundant sentences that cover all concepts of the input text for summary. The MCBSS algorithm finds novel information using maximal cliques (MCs). The experimental results of recall oriented understudy for gisting evaluation (ROUGE) on Timeline dataset show that the proposed work outperforms the existing graph algorithms Bushy Path (BP), Aggregate Similarity (AS), and TextRank (TR).

Single document summarization using the information from documents with the same topic

The essence of extractive summarization is to measure the importance of sentences in the document. When extracting summary from a single document, it is difficult to comprehensively and effectively evaluate the importance of sentences due to the lack of information. In this paper, we propose a kind of single document summarization method using information from documents under the same topic. This method integrates the topic information from neighborhood documents and statistical information from the target document to calculate the score of sentences. Then the scoring results are used as a prior scores for each sentence in the target document. After the target document is represented by the sentence graph, the final score of the sentences are obtained by the biased random walk algorithm. Finally, the Maximal Marginal Relevance (MMR) algorithm is used to select the sentences to form summary. The experimental results on the DUC2001 and DUC2002 datasets show that the effect of extracting summary is improved by incorporating information from the documents under the same topic.

HGEED: Hierarchical graph enhanced event detection

Existing methods that use document-level information for event detection ignore the dependencies between sentences and also have shortcomings in modeling the dependencies among words. In this paper, we propose a novel Hierarchical Graph Enhanced Event Detection (HGEED) framework to make full use of syntax and document information for the task of event detection. First, a sentence graph is used to model word-to-word dependencies, enriching the local information of words by incorporating syntactic features. Then, a document graph is built to model sentence-to-sentence dependencies, obtaining global semantic representations for word-level prediction. The experiment results on the widely used ACE 2005 and TAC KBP 2015 corpora show that our model can capture local and global information with dependencies and achieve significant improvements as compared to all baselines.

문장 랭킹 스코어와 그래프 기법을 사용한 질의 기반 생성 요약 모델

기본적인 생성 요약 모델은 문서 내 모든 중요 내용을 포함하는 짧은 요약문을 생성하는 것을 목표로 한다. 반면, 질의(Query) 기반 생성 요약 모델의 경우 문서 내에서 질의와 관련된 정보를 요약해야 한다. 기존의 질의 기반 요약 모델은 문서 내 단어들과 질의문 간의 어텐션(Attention) 메커니즘을 통해 단어의 가중치를 계산하고 이를 기반으로 문장의 중요도를 계산한다. 이러한 방식은 문서의 전체적인 문맥정보를 반영하기 어렵다는 단점이 있다. 본 논문에서는 이러한 문제를 문장 랭킹 스코어와 문장 단위 그래프 구조를 만들어 문장의 중요도뿐만 아니라 문맥 정보를 반영하여 생성 요약의 성능을 향상시킬 수 있는 새로운 생성 요약 기법을 제안한다. 실험으로 살펴본 최종 제안 모델의 성능은 같은 데이터를 사용하는 선행 모델 대비 ROUGE-1 1.44%p, ROUGE-L 0.52%p의 향상된 성능을 보인다.

MolGANの拡張による文章グラフを用いた文章生成手法の提案

MolGANの拡張による文章グラフを用いた文章生成手法の提案

Structure Learning for Headline Generation

Headline generation is an important problem in natural language processing, which aims to describe a document by a compact and informative headline. Some recent successes on this task have been achieved by advanced graph-based neural models, which marry the representational power of deep neural networks with the structural modeling ability of the relational sentence graphs. The advantages of graph-based neural models over traditional Seq2Seq models lie in that they can encode long-distance relationship between sentences beyond the surface linear structure. However, since documents are typically weakly-structured data, modern graph-based neural models usually rely on manually designed rules or some heuristics to construct the sentence graph a prior. This may largely limit the power and increase the cost of the graph-based methods. In this paper, therefore, we propose to incorporate structure learning into the graph-based neural models for headline generation. That is, we want to automatically learn the sentence graph using a data-driven way, so that we can unveil the document structure flexibly without prior heuristics or rules. To achieve this goal, we employ a deep & wide network to encode rich relational information between sentences for the sentence graph learning. For the deep component, we leverage neural matching models, either representation-focused or interaction-focused model, to learn semantic similarity between sentences. For the wide component, we encode a variety of discourse relations between sentences. A Graph Convolutional Network (GCN) is then applied over the sentence graph to generate high-level relational representations for headline generation. The whole model could be optimized end-to-end so that the structure and representation could be learned jointly. Empirical studies show that our model can significantly outperform the state-of-the-art headline generation models.

Coarse and Fine Granularity Graph Reasoning for Interpretable Multi-Hop Question Answering

Interpretable multi-hop question answering requires step-by-step reasoning over multiple documents and finding scattered supporting facts to answer the question. Prior works have proposed the entity graph method to aggregate the entity information to improve the ability of reasoning. However, the entity graph loses some non-entity information that is also important to understand the semantics. Moreover, the entities distributed in the noisy sentences may mislead the reasoning process. In this paper, we propose the Coarse and Fine Granularity Graph Network (CFGGN), a novel interpretable model that combines both sentence information and entity information to answer the multi-hop questions. The CFGGN consists of a coarse-grain module to perform sentence-level reasoning and a fine-grain module to make entity-level reference. In sentence-level reasoning, the sentence graph is constructed to filter out the noisy sentences and capture the sentence features. In entity-level reference, a dynamic entity graph is used for the entity-level reasoning. We design a fusion module to integrate information of different granularity. To enhance the interpretability of the overall process, we calculate the reasoning score for each step and present the reasoning path from the multiple documents to the final answer. Evaluation on the HotpotQA dataset in the distractor setting shows that our method outperforms the published SOTA entity-based method in five out of six metrics.

An unsupervised semantic sentence ranking scheme for text documents

This paper presents Semantic SentenceRank (SSR), an unsupervised scheme for automatically ranking sentences in a single document according to their relative importance. In particular, SSR extracts essential words and phrases from a text document, and uses semantic measures to construct, respectively, a semantic phrase graph over phrases and words, and a semantic sentence graph over sentences. It applies two variants of article-structure-biased PageRank to score phrases and words on the first graph and sentences on the second graph. It then combines these scores to generate the final score for each sentence. Finally, SSR solves a multi-objective optimization problem for ranking sentences based on their final scores and topic diversity through semantic subtopic clustering. An implementation of SSR that runs in quadratic time is presented, and it outperforms, on the SummBank benchmarks, each individual judge’s ranking and compares favorably with the combined ranking of all judges.

Research on partitioning algorithm based on RDF graph

SummaryWith the increasing size of the RDF dataset, the application of parallel computing frameworks is applying more and more widely in big data. In order to realize the parallel query of data, an edge partitioning algorithm is proposed based on RDF sentence graph. Firstly, the algorithm transforms the RDF graph into an RDF sentence graph using coarsening and partitioning. Secondly, the minimum degree vertex partitioning algorithm is put forward to partition the RDF sentence graph. Finally, according to the equivalence thought between edge segmentation of RDF sentence and vertex segmentation of RDF graph, the intersection between RDF subgraphs is the vertex cut set of RDF graph to achieve parallel query of RDF data. The experimental results show that the algorithm's partitioning time and efficiency are better than the traditional algorithms.

Chinese–Vietnamese bilingual news event summarization based on distributed graph ranking

Multi-language news event summarization aims to quickly obtain the important information from lots of related news texts written in different languages automatically. Considering that the main expressed information for a same event is similar no matter what language it is presented, the paper proposes a novel unified approach to summarize important information from the monolingual and Chinese–Vietnamese bilingual news sets simultaneously. Firstly, analyzing the sentence dependence relationship, making rules to segment sentence into different grammatical parts, a bilingual dictionary is used to set up bilingual feature space. Secondly, Chinese–Vietnamese sentence graph model is calculated distributively. Finally, using the features that graph nodes can boost each other and fusing context information, the sentences are ranked based on whether they can represent the important information. The experimental result shows that our method is effective.

Automatic Multi-Document Summarization Based on Keyword Density and Sentence-Word Graphs

As a fundamental and effective tool for document understanding and organization, multi-document summarization enables better information services by creating concise and informative reports for large collections of documents. In this paper, we propose a sentence-word two layer graph algorithm combining with keyword density to generate the multi-document summarization, known as Graph & Keywordρ. The traditional graph methods of multi-document summarization only consider the influence of sentence and word in all documents rather than individual documents. Therefore, we construct multiple word graph and extract right keywords in each document to modify the sentence graph and to improve the significance and richness of the summary. Meanwhile, because of the differences in the words importance in documents, we propose to use keyword density for the summaries to provide rich content while using a small number of words. The experiment results show that the Graph & Keywordρ method outperforms the state of the art systems when tested on the Duc2004 data set.

Using the local context for the definition and implementation of visual languages

In general, visual languages need to be simple in order to be easily used and understood. As a result, many of them have simple constructs that can be defined by simply describing local constraints on the constituent elements. Based on this assumption, in a previous research, we developed a local context methodology for the specification of the syntax of simple visual languages such as flowcharts, entity-relationship diagrams, use-case diagrams. In this paper, we extend the methodology by defining a new technique for a local context based semantic translation of a visual language. The technique uses XPath-like expressions, called SGPath, together with a data flow model of execution. As for the case of local syntax checks, attributes and rules to calculate them are defined for each element of the language. For a given element in the abstract sentence graph, the SGPath expressions are used to gather values from its neighbors in order to allow the rules to calculate its semantic attributes. The new methodology has been implemented in the tool LoCoMoTiVe and been tested on visual languages such as entity-relationship diagrams, flowcharts, trees.

Graph Clustering System for Text-Based Records in a Clinical Pathway.

The progressive digitization of medical records has resulted in the accumulation of large amounts of data. Electronic medical data include structured numerical data and unstructured text data. Although text-based medical record processing has been researched, few studies contribute to medical practice. The analysis of unstructured text data can improve medical processes. Hence, this study presents a clustering approach for detecting typical patient's condition from text-based medical record of clinical pathway. In this approach, the sentences in a cluster are merged to generate a "sentence graph" of the cluster after classified feature word by Louvain method. An analysis of real text-based medical records indicates that sentence graphs can represent the medical treatment and patient's condition in a medical process. This method could help the standardization of text-based medical records and the recognition of feature medical processes for improving medical treatment.

Update Summarization via Graph-Based Sentence Ranking

Due to the fast evolution of the information on the Internet, update summarization has received much attention in recent years. It is to summarize an evolutionary document collection at current time supposing the users have read some related previous documents. In this paper, we propose a graph-ranking-based method. It performs constrained reinforcements on a sentence graph, which unifies previous and current documents, to determine the salience of the sentences. The constraints ensure that the most salient sentences in current documents are updates to previous documents. Since this method is NP-hard, we then propose its approximate method, which is polynomial time solvable. Experiments on the TAC 2008 and 2009 benchmark data sets show the effectiveness and efficiency of our method.

Approximate Subgraph Matching-Based Literature Mining for Biomedical Events and Relations

The biomedical text mining community has focused on developing techniques to automatically extract important relations between biological components and semantic events involving genes or proteins from literature. In this paper, we propose a novel approach for mining relations and events in the biomedical literature using approximate subgraph matching. Extraction of such knowledge is performed by searching for an approximate subgraph isomorphism between key contextual dependencies and input sentence graphs. Our approach significantly increases the chance of retrieving relations or events encoded within complex dependency contexts by introducing error tolerance into the graph matching process, while maintaining the extraction precision at a high level. When evaluated on practical tasks, it achieves a 51.12% F-score in extracting nine types of biological events on the GE task of the BioNLP-ST 2011 and an 84.22% F-score in detecting protein-residue associations. The performance is comparable to the reported systems across these tasks, and thus demonstrates the generalizability of our proposed approach.

Pattern Recognition System for Translating the English Sentence into Hindi

In the present work a model is proposed which deals with specifying the pattern for translating the English sentences into Hindi. Here a Vector Space based translation model has been proposed that transforms a Vector Space by graphical representation of text that addresses the issues of manual, automatic and adaptive strategies by incorporating the selection preferences for word argument positions. Vector Space Model (VSM) represents documents and queries usually as Vectors, Matrices or Tuples. The similarity of the Query Vector and Document Vector is represented as a scalar value. This model constructs a sentence graph for a given sentence and applies structural parsing on this sentence. The quality of a system is measured by considering its usefulness for typical users of the system. The recent development of related techniques stimulates new modeling and estimation methods that are beyond the scope of the traditional approaches.

Learning the “Whys”: Discovering design rationale using text mining — An algorithm perspective

Collecting design rationale (DR) and making it available in a well-organized manner will better support product design, innovation and decision-making. Many DR systems have been developed to capture DR since the 1970s. However, the DR capture process is heavily human involved. In addition, with the increasing amount of DR available in archived design documents, it has become an acute problem to research a new computational approach that is able to capture DR from free textual contents effectively. In our previous study, we have proposed an ISAL (issue, solution and artifact layer) model for DR representation. In this paper, we focus on algorithm design to discover DR from design documents according to the ISAL modeling. For the issue layer of the ISAL model, we define a semantic sentence graph to model sentence relationships through language patterns. Based on this graph, we improve the manifold-ranking algorithm to extract issue-bearing sentences. To discover solution–reason bearing sentences for the solution layer, we propose building up two sentence graphs based on candidate solution-bearing sentences and reason-bearing sentences respectively, and propagating information between them. For artifact information extraction, we propose two term relations, i.e. positional term relation and mutual term relation. Using these relations, we extend our document profile model to score the candidate terms. The performance and scalability of the algorithms proposed are tested using patents as research data joined with an example of prior art search to illustrate its application prospects.

La Grammaire en Chaîne Revisitée ou le Système de L'araignée

A syntactic analyzer based on a string grammar is presented. The handling of idioms — a difficult problem for parsers — is more satisfactory than what has been accomplished until now. It appears that it is necessary to distinguish the lexical and syntactic phases of the analysis. Moreover, using a sentence graph structure makes this system really powerfull. There are four main points to this paper: — the architecture of the parser: — the identification of idioms based upon a new categorization of those forms; — the use of a sentence graph structure; — the description of the string grammar analyzer.