177,144 research outputs found
A semantic-based system for querying personal digital libraries
No full textThis is the author's accepted manuscript. The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-540-28640-0_4. Copyright @ Springer 2004.The decreasing cost and the increasing availability of new technologies is enabling people to create their own digital libraries. One of the main topic in personal digital libraries is allowing people to select interesting information among all the different digital formats available today (pdf, html, tiff, etc.). Moreover the increasing availability of these on-line libraries, as well as the advent of the so called Semantic Web [1], is raising the demand for converting paper documents into digital, possibly semantically annotated, documents. These motivations drove us to design a new system which could enable the user to interact and query documents independently from the digital formats in which they are represented. In order to achieve this independence from the format we consider all the digital documents contained in a digital library as images. Our system tries to automatically detect the layout of the digital documents and recognize the geometric regions of interest. All the extracted information is then encoded with respect to a reference ontology, so that the user can query his digital library by typing free text or browsing the ontology
Natural language understanding: instructions for (Present and Future) use
No full textIn this paper I look at Natural Language Understanding, an area of Natural Language Processing aimed at making sense of text, through the lens of a visionary future: what do we expect a machine should be able to understand? and what are the key dimensions that require the attention of researchers to make this dream come true
CLEF 2013: Information Access Evaluation meets Multilinguality, Multimodality, and Visualization
No full textFerro, N.; Forner, P.; Müller, H.; Navigli, R.; Paredes Palacios, R.; Rosso, P.; Stein, B.... (2013). CLEF 2013: Information Access Evaluation meets Multilinguality, Multimodality, and Visualization. ACM SIGIR Forum. 47(2):15-20. doi:10.1145/2568388.2568392S152047
Train-O-Matic: Supervised Word Sense Disambiguation with no (manual) effort
No full textWord Sense Disambiguation (WSD) is the task of associating the correct meaning with a word in a given context. WSD provides explicit semantic information that is beneficial to several downstream applications, such as question answering, semantic parsing and hypernym extraction. Unfortunately, WSD suffers from the well-known knowledge acquisition bottleneck problem: it is very expensive, in terms of both time and money, to acquire semantic annotations for a large number of sentences. To address this blocking issue we present Train-O-Matic, a knowledge-based and language-independent approach that is able to provide millions of training instances annotated automatically with word meanings. The approach is fully automatic, i.e., no human intervention is required, and the only type of human knowledge used is a task-independent WordNet-like resource. Moreover, as the sense distribution in the training set is pivotal to boosting the performance of WSD systems, we also present two unsupervised and language-independent methods that automatically induce a sense distribution when given a simple corpus of sentences. We show that, when the learned distributions are taken into account for generating the training sets, the performance of supervised methods is further enhanced. Experiments have proven that Train-O-Matic on its own, and also coupled with word sense distribution learning methods, lead a supervised system to achieve state-of-the-art performance consistently across gold standard datasets and languages. Importantly, we show how our sense distribution learning techniques aid Train-O-Matic to scale well over domains, without any extra human effort. To encourage future research, we release all the training sets in 5 different languages and the sense distributions for each domain of SemEval-13 and SemEval-15 at http://trainomatic.org
An overview of word and sense similarity
No full textOver the last two decades, determining the similarity between words as well as between their meanings, that is, word senses, has been proven to be of vital importance in the field of Natural Language Processing. This paper provides the reader with an introduction to the tasks of computing word and sense similarity. These consist in computing the degree of semantic likeness between words and senses, respectively. First, we distinguish between two major approaches: the knowledge-based approaches and the distributional approaches. Second, we detail the representations and measures employed for computing similarity. We then illustrate the evaluation settings available in the literature and, finally, discuss suggestions for future research
FENICE: Factuality Evaluation of Summarization Based on Natural Language Inference and Claim Extraction
No full textRecent advancements in text summarization, particularly with the advent of Large Language Models (LLMs), have shown remarkable performance. However, a notable challenge persists as a substantial number of automatically-generated summaries exhibit factual inconsistencies, such as hallucinations. In response to this issue, various approaches for the evaluation of consistency for summarization have emerged. Yet, these newly-introduced metrics face several limitations, including lack of interpretability, focus on short document summaries (e.g., news articles), and computational impracticality, especially for LLM-based metrics. To address these shortcomings, we propose Factuality Evaluation of summarization based on Natural language Inference and Claim Extraction (FENICE), a more interpretable and efficient factuality-oriented metric. FENICE leverages an NLI-based alignment between information in the source document and a set of atomic facts, referred to as claims, extracted from the summary. Our metric sets a new state of the art on AGGREFACT, the de-facto benchmark for factuality evaluation. Moreover, we extend our evaluation to a more challenging setting by conducting a human annotation process of long-form summarization. In the hope of fostering research in summarization factuality evaluation, we release the code of our metric and our factuality annotations of long-form summarization at ity annotations of long-form summarization at https://github.com/Babelscape/FENICE
Ontology Learning and Its Application to Automated Terminology Translation
No full textOur OntoLearn system is an infrastructure for automated ontology learning from domain text. It is the only system, as far as we know, that uses natural language processing and machine learning techniques, and is part of a more general ontology engineering architecture. We describe the system and an experiment in which we used a machine-learned tourism ontology to automatically translate multiword terms from English to Italian. The method can apply to other domains without manual adaptation
AAA: Fair evaluation for abuse detection systems wanted
No full textUser-generated web content is rife with abusive language that can harm others and discourage participation. Thus, a primary research aim is to develop abuse detection systems that can be used to alert and support human moderators of online communities. Such systems are notoriously hard to develop and evaluate. Even when they appear to achieve satisfactory performance on current evaluation metrics, they may fail in practice on new data. This is partly because datasets commonly used in this field suffer from selection bias, and consequently, existing supervised models overrely on cue words such as group identifiers (e.g., gay and black) which are not inherently abusive. Although there are attempts to mitigate this bias, current evaluation metrics do not adequately quantify their progress. In this work, we introduce Adversarial Attacks against Abuse (AAA), a new evaluation strategy and associated metric that better captures a model's performance on certain classes of hard-to-classify microposts, and for example penalises systems which are biased on low-level lexical features. It does so by adversarially modifying the model developer's training and test data to generate plausible test samples dynamically. We make AAA available as an easy-to-use tool, and show its effectiveness in error analysis by comparing the AAA performance of several state-of-the-art models on multiple datasets. This work will inform the development of detection systems and contribute to the fight against abusive language online
Content-Based Social Network Analysis
No full textRelationships among actors in traditional social network analysis are modelled as a function of the quantity of relations (co-authorships, business relations, friendship, etc.). In contrast, within a business, social or research community, network analysts are interested in the communicative content exchanged by the community members, not merely in the number of relationships. In order to meet this need, this paper presents a novel social network model, in which the actors are not simply represented through the intensity of their mutual relationships, but also through the analysis and evolution of their shared interests. Text mining and clustering techniques are used to capture the content of communication and to identify the most popular topics
- …
