This paper contains a large literature review in the research field of Text Summarisation (TS) based on Human Language Technologies (HLT). TS helps users manage the vast amount of information available, by condensing documents' content and extracting the most relevant facts or topics included in them. The rapid development of emerging technologies poses new challenges to this research field, which still need to be solved. Therefore, it is essential to analyse its progress over the years, and provide an overview of the past, present and future directions, highlighting the main advances achieved and outlining remaining limitations. With this purpose, several important aspects are addressed within the scope of this survey. On the one hand, the paper aims at giving a general perspective on the state-of-the-art, describing the main concepts, as well as different summarisation approaches, and relevant international forums. Furthermore, it is important to stress upon the fact that the birth of new requirements and scenarios has led to new types of summaries with specific purposes (e.g. sentiment-based summaries), and novel domains within which TS has proven to be also suitable for (e.g. blogs). In addition, TS is successfully combined with a number of intelligent systems based on HLT (e.g. information retrieval, question answering, and text classification). On the other hand, a deep study of the evaluation of summaries is also conducted in this paper, where the existing methodologies and systems are explained, as well as new research that has emerged concerning the automatic evaluation of summaries' quality. Finally, some thoughts about TS in general and its future will encourage the reader to think of novel approaches, applications and lines to conduct research in the next years. The analysis of these issues allows the reader to have a wide and useful background on the main important aspects of this research field.

Text summarisation in progress: a literature review

In this paper we present a survey of various techniques available in text mining for keyword and keyphrase extraction.

/pdf/keyword-and-keyphrase-extraction-techniques-a-literature-5i7hbc18g4.pdf

Keyword and Keyphrase Extraction Techniques: A Literature Review

This paper describes the organization and results of the automatic keyphrase extraction task held at the Workshop on Semantic Evaluation 2010 (SemEval-2010). The keyphrase extraction task was specifically geared towards scientific articles. Systems were automatically evaluated by matching their extracted keyphrases against those assigned by the authors as well as the readers to the same documents. We outline the task, present the overall ranking of the submitted systems, and discuss the improvements to the state-of-the-art in keyphrase extraction.

/pdf/automatic-keyphrase-extraction-from-scientific-articles-18iojxgg3d.pdf

Automatic keyphrase extraction from scientific articles

CT alone has conventionally informed radiotherapy planning. It provides anatomical information for delineation and electron density for dose calculation. Integrating PET-CT for radiotherapy planning offers the opportunity to individualize treatment and improve patient outcome. PET-CT’s molecular insight of tumour biology could facilitate a move away from ‘one-size-fits-all’ prescription to more accurate personalized radiotherapy [1].

Advantages and Limitations

Subgraph matching (or subgraph isomorphism) is one of the fundamental problems in graph analysis. Extensive research has been done to develop practical solutions for subgraph matching. The state-of-the-art algorithms such as \textsfCFL-Match and \textsfTurbo\textsubscriptiso convert a query graph into a spanning tree for obtaining candidates for each query vertex and obtaining a good matching order with the spanning tree. However, by using the spanning tree instead of the original query graph, it could lead to lower pruning power and a sub-optimal matching order. Another limitation is that they perform redundant computation in search without utilizing the knowledge learned from past computation. In this paper, we introduce three novel concepts to address these inherent limitations: 1) dynamic programming between a directed acyclic graph (DAG) and a graph, 2) adaptive matching order with DAG ordering, and 3) pruning by failing sets, which together lead to a much faster algorithm \textsfDAF for subgraph matching. Extensive experiments with real datasets show that \textsfDAF outperforms the fastest existing solution by up to orders of magnitude in terms of recursive calls as well as in terms of the elapsed time.

Efficient Subgraph Matching: Harmonizing Dynamic Programming, Adaptive Matching Order, and Failing Set Together

It is a fundamental and important task to extract key phrases from documents. Generally, phrases in a document are not independent in delivering the content of the document. In order to capture and make better use of their relationships in key phrase extraction, we suggest exploring the Wikipedia knowledge to model a document as a semantic network, where both n-ary and binary relationships among phrases are formulated. Based on a commonly accepted assumption that the title of a document is always elaborated to reflect the content of a document and consequently key phrases tend to have close semantics to the title, we propose a novel semi-supervised key phrase extraction approach in this paper by computing the phrase importance in the semantic network, through which the influence of title phrases is propagated to the other phrases iteratively. Experimental results demonstrate the remarkable performance of this approach.

A Semi-Supervised Key Phrase Extraction Approach: Learning from Title Phrases through a Document Semantic Network

This paper proposes a verb-driven approach to extract 5W1H (Who, What, Whom, When, Where and How) event semantic information from Chinese online news. The main contributions of our work are two-fold: First, given the usual structure of a news story, we propose a novel algorithm to extract topic sentences by stressing the importance of news headline; Second, we extract event facts (i.e. 5W1H) from these topic sentences by applying a rule-based method (verb-driven) and a supervised machine-learning method (SVM). This method significantly improves the predicate-argument structure used in Automatic Content Extraction (ACE) Event Extraction (EE) task by considering valency (dominant capacity to noun phrases) of a Chinese verb. Extensive experiments on ACE 2005 datasets confirm its effectiveness and it also shows a very high scalability, since we only consider the topic sentences and surface text features. Based on this method, we build a prototype system named Chinese News Fact Extractor (CNFE). CNFE is evaluated on a real world corpus containing 30,000 newspaper documents. Experiment results show that CNFE can extract event facts efficiently.

Extracting 5W1H event semantic elements from Chinese online news

Graph based sentence ranking algorithms such as PageRank and HITS have been successfully used in query-oriented summarization. With these algorithms, the documents to be summarized are often modeled as a text graph where nodes represent sentences and edges represent pairwise similarity relationships between two sentences. A deficiency of conventional graph modeling is its incapability of naturally and effectively representing complex group relationships shared among multiple objects. Simply squeezing complex relationships into pairwise ones will inevitably lead to loss of information which can be useful for ranking and learning. In this paper, we propose to take advantage of hypergraph, i.e. a generalization of graph, to remedy this defect. In a text hypergraph, nodes still represent sentences, yet hyperedges are allowed to connect more than two sentences. With a text hypergraph, we are thus able to integrate both group relationships formulated among multiple sentences and pairwise relationships formulated between two sentences in a unified framework. As essential work, it is first addressed in the paper that how a text hypergraph can be built for summarization by applying clustering techniques. Then, a hypergraph based semi-supervised sentence ranking algorithm is developed for query-oriented extractive summarization, where the influence of query is propagated to sentences through the structure of the constructed text hypergraph. When evaluated on DUC data sets, performance of the proposed approach is remarkable.

HyperSum: hypergraph based semi-supervised sentence ranking for query-oriented summarization

To relieve "News Information Overload", classification, summarization and recommendation techniques have been proposed. However, these techniques fail to provide sufficient semantic information about news events. In this paper, considering5W1H (Who, What, Whom, When, Where and How), the full list of elements of a news article, we propose a novel approach to extract event semantic elements. The approach comprises a key event identification step and an event element extraction step. We first use machine learning method to identify the key events of Chinese news stories. Then we employ semantic role labeling (SRL) enhanced by heuristic rules to extract event 5W1Helements. A prototype system is implemented based on proposed approach. Extensive experiments on real online news data sets confirm the reasonability and feasibility of our approach.

Wei Wang

Papers

A Semi-Supervised Key Phrase Extraction Approach: Learning from Title Phrases through a Document Semantic Network

Extracting 5W1H event semantic elements from Chinese online news

HyperSum: hypergraph based semi-supervised sentence ranking for query-oriented summarization

Chinese News Event 5W1H Elements Extraction Using Semantic Role Labeling

SQBC: An efficient subgraph matching method over large and dense graphs