Güneş Erkan

LexRank: graph-based lexical centrality as salience in text summarization

We introduce a stochastic graph-based method for computing relative importance of textual units for Natural Language Processing. We test the technique on the problem of Text Summarization (TS). Extractive TS relies on the concept of sentence salience to identify the most important sentences in a document or set of documents. Salience is typically defined in terms of the presence of particular important words or in terms of similarity to a centroid pseudo-sentence. We consider a new approach, LexRank, for computing sentence importance based on the concept of eigenvector centrality in a graph representation of sentences. In this model, a connectivity matrix based on intra-sentence cosine similarity is used as the adjacency matrix of the graph representation of sentences. Our system, based on LexRank ranked in first place in more than one task in the recent DUC 2004 evaluation. In this paper we present a detailed analysis of our approach and apply it to a larger data set including data from earlier DUC evaluations. We discuss several methods to compute centrality using the similarity graph. The results show that degree-based methods (including LexRank) outperform both centroid-based methods and other systems participating in DUC in most of the cases. Furthermore, the LexRank with threshold method outperforms the other degree-based techniques including continuous LexRank. We also show that our approach is quite insensitive to the noise in the data that may result from an imperfect topical clustering of documents.

Identifying gene-disease associations using centrality on a literature mined gene-interaction network

Motivation: Understanding the role of genetics in diseases is one of the most important aims of the biological sciences. The completion of the Human Genome Project has led to a rapid increase in the number of publications in this area. However, the coverage of curated databases that provide information manually extracted from the literature is limited. Another challenge is that determining disease-related genes requires laborious experiments. Therefore, predicting good candidate genes before experimental analysis will save time and effort. We introduce an automatic approach based on text mining and network analysis to predict gene-disease associations. We collected an initial set of known disease-related genes and built an interaction network by automatic literature mining based on dependency parsing and support vector machines. Our hypothesis is that the central genes in this disease-specific network are likely to be related to the disease. We used the degree, eigenvector, betweenness and closeness centrality metrics to rank the genes in the network. Results: The proposed approach can be used to extract known and to infer unknown gene-disease associations. We evaluated the approach for prostate cancer. Eigenvector and degree centrality achieved high accuracy. A total of 95% of the top 20 genes ranked by these methods are confirmed to be related to prostate cancer. On the other hand, betweenness and closeness centrality predicted more genes whose relation to the disease is currently unknown and are candidates for experimental study. Availability: A web-based system for browsing the disease-specific gene-interaction networks is available at: http://gin.ncibi.org Contact: radev@umich.edu

Biased LexRank: Passage retrieval using random walks with question-based priors

We present Biased LexRank, a method for semi-supervised passage retrieval in the context of question answering. We represent a text as a graph of passages linked based on their pairwise lexical similarity. We use traditional passage retrieval techniques to identify passages that are likely to be relevant to a users natural language question. We then perform a random walk on the lexical similarity graph in order to recursively retrieve additional passages that are similar to other relevant passages. We present results on several benchmarks that show the applicability of our work to question answering and topic-focused text summarization.

Language Model-Based Document Clustering Using Random Walks

We propose a new document vector representation specifically designed for the document clustering task. Instead of the traditional term-based vectors, a document is represented as an n-dimensional vector, where n is the number of documents in the cluster. The value at each dimension of the vector is closely related to the generation probability based on the language model of the corresponding document. Inspired by the recent graph-based NLP methods, we reinforce the generation probabilities by iterating random walks on the underlying graph representation. Experiments with k-means and hierarchical clustering algorithms show significant improvements over the alternative tf·idf vector representation.

Adding Syntax to Dynamic Programming for Aligning Comparable Texts for the Generation of Paraphrases

Multiple sequence alignment techniques have recently gained popularity in the Natural Language community, especially for tasks such as machine translation, text generation, and paraphrase identification. Prior work falls into two categories, depending on the type of input used: (a) parallel corpora (e.g., multiple translations of the same text) or (b) comparable texts (non-parallel but on the same topic). So far, only techniques based on parallel texts have successfully used syntactic information to guide alignments. In this paper, we describe an algorithm for incorporating syntactic features in the alignment process for non-parallel texts with the goal of generating novel paraphrases of existing texts. Our method uses dynamic programming with alignment decision based on the local syntactic similarity between two sentences. Our results show that syntactic alignment outrivals syntax-free methods by 20% in both grammaticality and fidelity when computed over the novel sentences generated by alignment-induced finite state automata.

LexNet: A Graphical Environment for Graph-Based NLP

This interactive presentation describes LexNet, a graphical environment for graph-based NLP developed at the University of Michigan. LexNet includes LexRank (for text summarization), biased LexRank (for passage retrieval), and TUMBL (for binary classification). All tools in the collection are based on random walks on lexical graphs, that is graphs where different NLP objects (e.g., sentences or phrases) are represented as nodes linked by edges proportional to the lexical similarity between the two nodes. We will demonstrate these tools on a variety of NLP tasks including summarization, question answering, and prepositional phrase attachment.