Rejection Recall FAQFinder with sense tagging FAQFinder without sense tagging Figure 4: Recall vs. Rejection for FAQFinder with and without WordNet Sense Tagging search. In FAQFinder, sense tagging and calculation of semantic similarity are much more computationally intensive than term vector processing. However, since FAQFinder matches single questions rather than entire documents, the computa...

Word Segmentation is usually considered an essential step for many Chinese and Japanese Natural Language Processing tasks, such as name tagging. This paper presents several new observations and analysis on the impact of word segmentation on name tagging; (1). Due to the limitation of current state-of-the-art Chinese word segmentation performance, a character-based name tagger can outperform its...

This paper separates conditional parameter estimation, which consistently raises test set accuracy on statistical NLP tasks, from conditional model structures, such as the conditional Markov model used for maximum-entropy tagging, which tend to lower accuracy. Error analysis on the POS tagging task shows that the actual tagging errors made by the conditionally structured model derive principall...

Social tagging has been applied to many applications including image sharing, bookmarking and music recommendations. We have developed a application for the social tagging of people to support contact management and browsing profiles in an enterprise directory. As we expected, we found that users tag people for personal organization and for “social” motivations just as in other systems. However...

The goal of part-of-speech tagging is to assign to each word in a sentence its morphosyntactic category. Annotating a text with part-of-speech tags is a standard low-level text preprocessing step before further analysis. An interesting novel approach to the tagging problem is proposed here, by modelling a language as a data source followed by a channel. The Shannon capacity of this simple sourc...

Joint extraction of entities and relations is an important task in information extraction. To tackle this problem, we firstly propose a novel tagging scheme that can convert the joint extraction task to a tagging problem. Then, based on our tagging scheme, we study different end-toend models to extract entities and their relations directly, without identifying entities and relations separately....

The focus of recent studies on Chinese word segmentation, part-of-speech (POS) tagging and parsing has been shifting from words to characters. However, existing methods have not yet fully utilized the potentials of Chinese characters. In this paper, we investigate the usefulness of character-level part-of-speech in the task of Chinese morphological analysis. We propose the first tagset designed...

Tagging has been popularized by Web 2.0 sites as a way to describe resources. Typically, tagging has been done in an explicit way in which users directly describe with tags the resources in which they are interested. However in today’s ubiquitous computing environments, it is possible to implicitly tag resources. This paper: (1) introduces the concept of explicit and implicit tagging for user m...

An objective of the Atlantic Ocean Tropical tuna Tagging Programme (AOTTP) was to estimate Type-I (immediate) and Type-II (long-term) tag-shedding rates for tropical tunas from double-tagging experiments. Historical information on studies conducted in different parts world incorporated as prior distributions using a Bayesian approach new parameters. were respectively estimated at 0.007 0.084/yr...

Background: An ongoing assessment of the literature is difficult with the rapidly increasing volume of research publications and limited effective information extraction tools which identify entity relationships from text. A recent study reported development of Muscorian, a generic text processing tool for extracting proteinprotein interactions from text that achieved comparable performance to ...