Comunicacio presentada a la 2016 Conference of the North American Chapter of the Association for Computational Linguistics, celebrada a San Diego (CA, EUA) els dies 12 a 17 de juny 2016.

/pdf/neural-architectures-for-named-entity-recognition-4xswt97nv2.pdf

Neural Architectures for Named Entity Recognition

Large-scale graph-structured computation is central to tasks ranging from targeted advertising to natural language processing and has led to the development of several graph-parallel abstractions including Pregel and GraphLab. However, the natural graphs commonly found in the real-world have highly skewed power-law degree distributions, which challenge the assumptions made by these abstractions, limiting performance and scalability.In this paper, we characterize the challenges of computation on natural graphs in the context of existing graph-parallel abstractions. We then introduce the PowerGraph abstraction which exploits the internal structure of graph programs to address these challenges. Leveraging the PowerGraph abstraction we introduce a new approach to distributed graph placement and representation that exploits the structure of power-law graphs. We provide a detailed analysis and experimental evaluation comparing PowerGraph to two popular graph-parallel systems. Finally, we describe three different implementation strategies for PowerGraph and discuss their relative merits with empirical evaluations on large-scale real-world problems demonstrating order of magnitude gains.

/pdf/powergraph-distributed-graph-parallel-computation-on-natural-kpa9ip3lyw.pdf

PowerGraph: distributed graph-parallel computation on natural graphs

https://people.mpi-inf.mpg.de/~kberberi/publications/2010-mpii-tra.pdf

YAGO2: A spatially and temporally enhanced knowledge base from Wikipedia

Uncovering the topics within short texts, such as tweets and instant messages, has become an important task for many content analysis applications. However, directly applying conventional topic models (e.g. LDA and PLSA) on such short texts may not work well. The fundamental reason lies in that conventional topic models implicitly capture the document-level word co-occurrence patterns to reveal topics, and thus suffer from the severe data sparsity in short documents. In this paper, we propose a novel way for modeling topics in short texts, referred as biterm topic model (BTM). Specifically, in BTM we learn the topics by directly modeling the generation of word co-occurrence patterns (i.e. biterms) in the whole corpus. The major advantages of BTM are that 1) BTM explicitly models the word co-occurrence patterns to enhance the topic learning; and 2) BTM uses the aggregated patterns in the whole corpus for learning topics to solve the problem of sparse word co-occurrence patterns at document-level. We carry out extensive experiments on real-world short text collections. The results demonstrate that our approach can discover more prominent and coherent topics, and significantly outperform baseline methods on several evaluation metrics. Furthermore, we find that BTM can outperform LDA even on normal texts, showing the potential generality and wider usage of the new topic model.

http://www.bigdatalab.ac.cn/~lanyanyan/papers/2013/WWW2013-yan.pdf

A biterm topic model for short texts

In the recent years, different Web knowledge graphs, both free and commercial, have been created. While Google coined the term "Knowledge Graph" in 2012, there are also a few openly available knowledge graphs, with DBpedia, YAGO, and Freebase being among the most prominent ones. Those graphs are often constructed from semi-structured knowledge, such as Wikipedia, or harvested from the web with a combination of statistical and linguistic methods. The result are large-scale knowledge graphs that try to make a good trade-off between completeness and correctness. In order to further increase the utility of such knowledge graphs, various refinement methods have been proposed, which try to infer and add missing knowledge to the graph, or identify erroneous pieces of information. In this article, we provide a survey of such knowledge graph refinement approaches, with a dual look at both the methods being proposed as well as the evaluation methodologies used.

Knowledge graph refinement: A survey of approaches and evaluation methods

Disambiguating named entities in natural-language text maps mentions of ambiguous names onto canonical entities like people or places, registered in a knowledge base such as DBpedia or YAGO. This paper presents a robust method for collective disambiguation, by harnessing context from knowledge bases and using a new form of coherence graph. It unifies prior approaches into a comprehensive framework that combines three measures: the prior probability of an entity being mentioned, the similarity between the contexts of a mention and a candidate entity, as well as the coherence among candidate entities for all mentions together. The method builds a weighted graph of mentions and candidate entities, and computes a dense subgraph that approximates the best joint mention-entity mapping. Experiments show that the new method significantly outperforms prior methods in terms of accuracy, with robust behavior across a variety of inputs.

/pdf/robust-disambiguation-of-named-entities-in-text-2nql8lmxop.pdf

Robust Disambiguation of Named Entities in Text

We live in a computerized and networked society where many of our actions leave a digital trace and affect other people’s actions. This has lead to the emergence of a new data-driven research field: mathematical methods of computer science, statistical physics and sociometry provide insights on a wide range of disciplines ranging from social science to human mobility. A recent important discovery is that search engine traffic (i.e., the number of requests submitted by users to search engines on the www) can be used to track and, in some cases, to anticipate the dynamics of social phenomena. Successful examples include unemployment levels, car and home sales, and epidemics spreading. Few recent works applied this approach to stock prices and market sentiment. However, it remains unclear if trends in financial markets can be anticipated by the collective wisdom of on-line users on the web. Here we show that daily trading volumes of stocks traded in NASDAQ-100 are correlated with daily volumes of queries related to the same stocks. In particular, query volumes anticipate in many cases peaks of trading by one day or more. Our analysis is carried out on a unique dataset of queries, submitted to an important web search engine, which enable us to investigate also the user behavior. We show that the query volume dynamics emerges from the collective but seemingly uncoordinated activity of many users. These findings contribute to the debate on the identification of early warnings of financial systemic risk, based on the activity of users of the www.

/pdf/web-search-queries-can-predict-stock-market-volumes-48kmld52ln.pdf

Web search queries can predict stock market volumes.

We present AIDA, a framework and online tool for entity detection and disambiguation. Given a natural-language text or a Web table, we map mentions of ambiguous names onto canonical entities like people or places, registered in a knowledge base like DBpedia, Freebase, or YAGO. AIDA is a robust framework centred around collective disambiguation exploiting the prominence of entities, similarity between the context of the mention and its candidates, and the coherence among candidate entities for all mentions. We have developed a Web-based online interface for AIDA where different formats of inputs can be processed on the fly, returning proper entities and showing intermediate steps of the disambiguation process.

AIDA: an online tool for accurate disambiguation of named entities in text and tables

The problem of mining frequent patterns in networks has many applications, including analysis of complex networks, clustering of graphs, finding communities in social networks, and indexing of graphical and biological databases. Despite this wealth of applications, the current state of the art lacks algorithmic tools for counting the number of subgraphs contained in a large network. In this paper we develop data-stream algorithms that approximate the number of all subgraphs of three and four vertices in directed and undirected networks. We use the frequency of occurrence of all subgraphs to prove their significance in order to characterize different kinds of networks: we achieve very good precision in clustering networks with similar structure. The significance of our method is supported by the fact that such high precision cannot be achieved when performing clustering based on simpler topological properties, such as degree, assortativity, and eigenvector distributions. We have also tested our techniques using swap randomization.

https://www.computer.org/csdl/pds/api/csdl/proceedings/download-article/12OmNyaGeEk/pdf

Mining Large Networks with Subgraph Counting

Defining a measure of similarity between queries is an interesting and difficult problem. A reliable query-similarity measure can be used in a variety of applications such as query recommendation, query expansion, and advertising. In this paper, we exploit the information present in query logs in order to develop a measure of semantic similarity between queries. Our approach relies on the concept of the query-flow graph. The query-flow graph aggregates query reformulations from many users: nodes in the graph represent queries, and two queries are connected if they are likely to appear as part of the same search goal. Our query similarity measure is obtained by projecting the graph (or appropriate subgraphs of it) on a low-dimensional Euclidean space. Our experiments show that the measure we obtain captures a notion of semantic similarity between queries and it is useful for diversifying query recommendations.

/pdf/query-similarity-by-projecting-the-query-flow-graph-4pnk27f9l8.pdf

Ilaria Bordino

Papers

Robust Disambiguation of Named Entities in Text

Web search queries can predict stock market volumes.

AIDA: an online tool for accurate disambiguation of named entities in text and tables

Mining Large Networks with Subgraph Counting

Query similarity by projecting the query-flow graph