Ludovic Jean-Louis

An Assessment of Online Semantic Annotators for the Keyword Extraction Task

The task of keyword extraction aims at capturing expressions (or entities) that best represent the main topics of a document. Given the rapid adoption of these online semantic annotators and their contribution to the growth of the Semantic Web, one important task is to assess their quality. This article presents an evaluation of the quality and stability of semantic annotators on domain-specific and open domain corpora. We evaluate five semantic annotators and compare them to two state-of-the-art keyword extractors, namely KP-miner and Maui. Our evaluation demonstrates that semantic annotators are not able to outperform keyword extractors and that annotators perform best on domains having a high keyword density.

Can we use linked data semantic annotators for the extraction of domain-relevant expressions?

Semantic annotation is the process of identifying expressions in texts and linking them to some semantic structure. In particular, Linked data-based Semantic Annotators are now becoming the new Holy Grail for meaning extraction from unstructured documents. This paper presents an evaluation of the main linked data-based annotators available with a focus on domain topics and named entities. In particular, we compare the ability of each tool to annotate relevant domain expressions in text. The paper also proposes a combination of annotators through voting methods and machine learning. Our results show that some linked-data annotators, especially Alchemy, can be considered as a useful resource for topic extraction. They also show that a substantial increase in recall can be achieved by combining the annotators with a weighted voting scheme. Finally, an interesting result is that by removing Alchemy from the combination, or by combining only the more precise annotators, we get a significant increase in precision, at the cost of a lower recall.

Using Collaborative Tagging for Text Classification: From Text Classification to Opinion Mining

Numerous initiatives have allowed users to share knowledge or opinions using collaborative platforms. In most cases, the users provide a textual description of their knowledge, following very limited or no constraints. Here, we tackle the classification of documents written in such an environment. As a use case, our study is made in the context of text mining evaluation campaign material, related to the classification of cooking recipes tagged by users from a collaborative website. This context makes some of the corpus specificities difficult to model for machine-learning-based systems and keyword or lexical-based systems. In particular, different authors might have different opinions on how to classify a given document. The systems presented hereafter were submitted to the D´Efi Fouille de Textes 2013 evaluation campaign, where they obtained the best overall results, ranking first on task 1 and second on task 2. In this paper, we explain our approach for building relevant and effective systems dealing with such a corpus.

Mutual Disambiguation for Entity Linking

The disambiguation algorithm presented in this paper is implemented in SemLinker, an entity linking system. First, named entities are linked to candidate Wikipedia pages by a generic annotation engine. Then, the algorithm re-ranks candidate links according to mutual relations between all the named entities found in the document. The evaluation is based on experiments conducted on the test corpus of the TAC-KBP 2012 entity linking task.

An assessment of open relation extraction systems for the semantic web

Abstract Open relation extraction has been a growing field of research in the last few years. This paper compares some of the most prominent open relation extractors and explores their strength and weaknesses on standard datasets. In particular, we highlight the lack of formal guidelines that define a valid relation and state that open relation extractors must be situated in particular tasks and contexts. In this respect, we briefly analyze the role of open relation extractors for the semantic Web and linked data context.

Identification of Sensitive Content in Data Repositories to Support Personal Information Protection

This article presents a two-step approach focusing on the identification of sensitive data within documents. The proposed pipeline first detects the domain of a document, then identifies the sensitive information it contains. Detection of domains allows to better understand the context of a documents, hence supports the disambiguation of potentially sensitive information. The prototype considers three domains: health, business and “other”. The system developed for the domain detection step is built and evaluated on a corpus composed of clinical notes, and articles about business or art from Forbes, Reuters, and The New York Times. The identification of sensitive information relies on a Conditional Random Fields (CRF) model.

An open source and modular search engine for biomedical literature retrieval

This work presents the bioMine system, a full‐text natural language search engine for biomedical literature. bioMine provides search capabilities based on the full‐text content of documents belonging to a database composed of scientific articles and allows users to submit their search queries using natural language. Beyond the text content of articles, the system engine also uses article metadata, empowering the search by considering extra information from picture and table captions. bioMine is publicly released as an open‐source system under the MIT license.

A Machine Learning Filter for the Slot Filling Task

Slot Filling, a subtask of Relation Extraction, represents a key aspect for building structured knowledge bases usable for semantic-based information retrieval. In this work, we present a machine learning filter whose aim is to enhance the precision of relation extractors while minimizing the impact on the recall. Our approach consists in the filtering of relation extractors’ output using a binary classifier. This classifier is based on a wide array of features including syntactic, semantic and statistical features such as the most frequent part-of-speech patterns or the syntactic dependencies between entities. We experimented the classifier on the 18 participating systems in the TAC KBP 2013 English Slot Filling track. The TAC KBP English Slot Filling track is an evaluation campaign that targets the extraction of 41 pre-identified relations (e.g., title, date of birth, countries of residence, etc.) related to specific named entities (persons and organizations). Our results show that the classifier is able to improve the global precision of the best 2013 system by 20.5% and improve the F1-score for 20 relations out of 33 considered.

Mining Biomedical Literature: An Open Source and Modular Approach

This paper presents the ongoing development of a full-text natural language search engine for biomedical literature. The system aims to provide search on the full-text content of documents belonging to a database composed of scientific articles, while allowing users to submit their search queries using natural language. Beyond the text content of articles, the system engine also utilizes article metadata, empowering the search by considering extra information from picture and table captions. User queries can be submitted to the system in natural language, releasing the user from the burden of translating their search needs into a query language.