We explore the use of Wikipedia as external knowledge to improve named entity recognition (NER). Our method retrieves the corresponding Wikipedia entry for each candidate word sequence and extracts a category label from the first sentence of the entry, which can be thought of as a definition

Set expansion refers to expanding a given partial set of objects into a more complete set. A well-known example system that does set expansion using the web is Google Sets. In this paper, we propose a novel method for expanding sets of named entities. The approach can be applied to semi-structured documents written in any markup language and in any human language. We present experimental results on 36 benchmark sets in three languages, showing that our system is superior to Google Sets in terms of mean average precision. 1.

Many researchers are trying to use information extraction (IE) to create large-scale knowledge bases from natural language text on the Web. However, the primary approach (supervised learning of relation-specific extractors) requires manually-labeled training data for each relation and doesn’t scale to the thousands of relations encoded in Web text. This paper presents LUCHS, a self-supervised, relation-specific IE system which learns 5025 relations — more than an order of magnitude greater than any previous approach — with an average F1 score of 61%. Crucial to LUCHS’s performance is an automated system for dynamic lexicon learning, which allows it to learn accurately from heuristically-generated training data, which is often noisy and sparse. 1

Graph-based semi-supervised learning (SSL) algorithms have been successfully used to extract class-instance pairs from large unstructured and structured text collections. However, a careful comparison of different graph-based SSL algorithms on that task has been lacking. We compare three graph-based SSL algorithms for class-instance acquisition on a variety of graphs constructed from different domains. We find that the recently proposed MAD algorithm is the most effective. We also show that class-instance extraction can be significantly improved by adding semantic information in the form of instance-attribute edges derived from an independently developed knowledge base. All of our code and data will be made publicly available to encourage reproducible research in this area. 1

Understanding intents from search queries can improve a user’s search experience and boost a site’s advertising profits. Query tagging via statistical sequential labeling models has been shown to perform well, but annotating the training set for supervised learning requires substantial human effort. Domain-specific knowledge, such as semantic class lexicons, reduces the amount of needed manual annotations, but much human effort is still required to maintain these as search topics evolve over time. This paper investigates semi-supervised learning algorithms that leverage structured data (HTML lists) from the Web to automatically generate semantic-class lexicons, which are used to improve query tagging performance – even with far less training data. We focus our study on understanding

This paper deals with recognition of named entities in Czech texts. We present a recently released corpus of Czech sentences with manually annotated named entities, in which a rich two-level classification scheme was used. There are around 6000 sentences in the corpus with roughly 33000 marked named entity instances. We use the data for training and evaluating a named entity recognizer based on Support Vector Machine classification technique. The presented recognizer outperforms the results previously reported for NE recognition in Czech.

Abstract. In this paper, we address the problem of extracting relational information from the Web at a large scale. In particular we present a bootstrapping approach to relation extraction which starts with a few seed tuples of the target relation and induces patterns which can be used to extract further tuples. Our contribution in this paper lies in the formulation of the pattern induction task as a well-known machine learning problem, i.e. the one of determining frequent itemsets on the basis of a set of transactions representing patterns. The formulation of the extraction problem as the task of mining frequent itemsets is not only elegant, but also speeds up the pattern induction step considerably with respect to previous implementations of the bootstrapping procedure. We evaluate our approach in terms of standard measures with respect to seven datasets of varying size and complexity. In particular, by analyzing the extraction rate (extracted tuples per time) we show that our approach reduces the pattern induction complexity from quadratic to linear (in the size of the occurrences to be generalized), while mantaining extraction quality at similar (or even marginally better) levels. 1

Named entity recognition (NER) is a subtask of information extraction (IE) which can be used further on for different purposes. In this paper, we discuss named entity recognition for Ukrainian language, which is a Slavonic language with a rich morphology. The approach we follow uses a restricted number of features. We show that it is feasible to boost performance by considering several heuristics and patterns acquired from the Web data. 1

Abstract. In this paper an approach to automatically generating multilingual geographical name gazetteers via two bootstrapping loops on different corpora is presented. First, a small seed-list of geographical names is matched to an unannotated dataset in one language, and training data for a memory-based classifier is generated. Memory-based learning is applied to extend the gazetteer. Then a cross-over to a different language is made by matching this extended gazetteer to a corpus in a different language. Again, training data for a classifier is generated and the bootstrapping process is repeated in order to extend the gazetteer further. This process is quite similar to co-training, in which information from other sources is introduced to enhance classification. To estimate the difference between the initial seed-list and the final gazetteer and thereby to evaluate the performance of the algorithm, they were matched to three datasets with manually annotated geographical entities. 1