2,349 research outputs found

    Embeddings for word sense disambiguation: an evaluation study

    No full text
    Recent years have seen a dramatic growth in the popularity of word embeddings mainly owing to their ability to capture semantic information from massive amounts of textual content. As a result, many tasks in Natural Language Processing have tried to take advantage of the potential of these distributional models. In this work, we study how word embeddings can be used in Word Sense Disambiguation, one of the oldest tasks in Natural Language Processing and Artificial Intelligence. We propose different methods through which word embeddings can be leveraged in a state-of-the-art supervised WSD system architecture, and perform a deep analysis of how different parameters affect performance. We show how a WSD system that makes use of word embeddings alone, if designed properly, can provide significant performance improvement over a state-of-the-art WSD system that incorporates several standard WSD features

    Neural-grounded semantic representations and word sense disambiguation: a mutually beneficial relationship

    No full text
    Language, in both the written and the oral forms, is the ground basis of living in society. The same basic kinds of rules and representations are shared across all the languages. Understand those rules is the objective of Natural Language Processing (NLP), the computerized discipline responsible to analyze and generate language. Building complex computational systems that mimic the human language and are capable to interact and collaborate with us is the holy grail of Natural Language Processing. Semantic representations are the rock-solid foundation on which many successful applications of NLP depend. Their main purpose is to extract and highlight the most important semantic features of textual data. Whereas over the years different approaches have been presented, lately, embeddings have become the dominant paradigm on vectorial representation of items. Currently, many outstanding NLP tasks rely on embeddings to achieve their performance. Embeddings are semantic spaces that carry valuable syntactic and semantic information. The name groups a set of feature learning techniques based on neural networks. Concretely, these techniques are capable to learn semantic spaces that effectively represent words as low-dimensional continuous vectors. They also maintain the structure of language by representing diverse lexical and semantic relations by a relation-specific vector offset. With the increasing amount of available text, as well as the increased computing power, techniques which take advantage of large volumes of unstructured data, as word embeddings, have become the prevailing approach of semantic representation of natural language. However, despite their enormous success, common word-embeddings approaches came with two inherent flaws: these representations are incapable to handle ambiguity, as senses of polysemous words are aggregated into single vectors. In addition, most word embeddings rely only on statistical information of word occurrences, leaving aside existing rich knowledge of structured data. To tackle the problem of polysemy, a fundamental task of Natural Language Processing (NLP), Word Sense Disambiguation (WSD), seems particularly suitable. The task, an open problem in the discipline, aims at identifying the correct meaning of word based given its context. Concretely, it links each word occurrence to a sense from a predefined inventory. Most successful approaches for WSD combine the use of unstructured data, manually annotated datasets and semantic resources. In the present thesis we address the issue of of ambiguity in semantic representations from a multimodal perspective. Firstly, we introduce and investigate new neural-based approaches to build better word and sense embeddings relying on both statistical data and prior semantic knowledge. We employ diverse techniques of WSD for linking word occurrences to their correct meaning on large amounts of raw corpora. Then, we use the resulting data as training input for learning the embeddings. We show the quality of these representations by evaluating them on standard semantic similarity frameworks reporting state-of-the-art performance on multiple datasets. Secondly, we show how these representations are capable to create better WSD systems. We introduce a new way to leverage word representations which outperforms current WSD approaches in both supervised and unsupervised configurations. We show that our WSD framework, based solely on embeddings, is capable to surpass WSD approaches based on standard features. Thirdly, we propose two new technique for leveraging semantic-annotated data. We incorporate more semantic features resulting in an increment in the performance compared with our initial approaches. We close the loop by showing that our semantic representations enhanced with WSD are also suitable for improving the task of WSD itself

    Embedding Words and Senses Together via Joint Knowledge-Enhanced Training

    No full text
    Word embeddings are widely used in Nat-ural Language Processing, mainly due totheir success in capturing semantic infor-mation from massive corpora. However,their creation process does not allow thedifferent meanings of a word to be auto-matically separated, as it conflates theminto a single vector. We address this issueby proposing a new model which learnsword and sense embeddings jointly. Ourmodel exploits large corpora and knowl-edge from semantic networks in order toproduce a unified vector space of wordand sense embeddings. We evaluate themain features of our approach both qual-itatively and quantitatively in a variety oftasks, highlighting the advantages of theproposed method in comparison to state-of-the-art word- and sense-based models

    SensEmbed: Learning sense embeddings for word and relational similarity

    No full text
    Word embeddings have recently gained considerable popularity for modeling words in different Natural Language Processing (NLP) tasks including semantic similarity measurement. However, notwithstanding their success, word embeddings are by their very nature unable to capture polysemy, as different meanings of a word are conflated into a single representation. In addition, their learning process usually relies on massive corpora only, preventing them from taking advantage of structured knowledge. We address both issues by proposing a multifaceted approach that transforms word embeddings to the sense level and leverages knowledge from a large semantic network for effective semantic similarity measurement. We evaluate our approach on word similarity and relational similarity frameworks, reporting state-of-the-art performance on multiple datasets

    Paco Ignacio Taibo II.

    No full text
    Encyclopaedia entry on contemporary Mexican author Paco Ignacio Taibo II

    Jerónimo Nadal (1507-1580) und der "verschriftlichte" Ignatius. Die Konstruktion einer individuellen und kollektiven Identität

    No full text
    Libro de InvestigaciónNiemand ist mehr verantwortlich für die Entstehung jenes Denksystems, das auf Ignatius von Loyola (1491-1556) und seinen Exerzitien basiert, als Jerónimo Nadal. Ignacio Ramos legt in seiner Studie Jerónimo Nadal (1507-1580) und der verschriftlichte Ignatius: Die Konstruktion einer individuellen und kollektiven Identität die ursprünglichen Konturen der sogenannten ignatianischen Spiritualität dar. Es wird deutlich, wieviel Einfluss Nadal auf die Herausbildung des Ignatianischen hatte. Anhand Nadals lange verkannten Selbstzeugnisses (Chronicon Natalis) wird hermeneutisch herausgearbeitet, wie der gequälte Reifeprozess von Nadal originales Denken erzeugte insbesondere in Bezug auf Ignatius. An diese europäische Schlüsselgestalt des jungen Jesuitenordens heranzutreten, gewährt einen existentiell vermittelten Einblick in manche der gesellschaftlichen und philosophischen Spannungen (converso-Frage, Rolle der Vermittlungen...) z. Zt. des Humanismus und der großen Reformen.Jerónimo Nadal plays a key role in the creation of the tradition of thought based on the person of Ignatius of Loyola (1491-1556) and his Spiritual Exercises. Ignacio Ramos book Jerónimo Nadal (1507-1580) und der verschriftlichte Ignatius unveils the large percentage of too often overlooked Nadalian moments in the origins of Ignatian Spirituality. Leaning on Nadal s autobiographical account ( Chronicon Natalis, fully translated) the author deploys a hermeneutical method to show how Nadal´s stressful maturation process became a source of original thought, especially regarding Ignatius. The reader will gain an existentially mediated insight into some of the social and philosophical hot spots (converso question, role of mediations...) of Humanism and the reformation era.info:eu-repo/semantics/publishedVersio

    Ignacio Ribera's Tree of Life

    No full text
    Supplementary Data with phylogenetic trees built with the COI sequences from Coleoptera that were uploaded to GenBank by studies including Ignacio Ribera as author. Those trees also include sequences from other studies to highlight the impressive work done Ignacio Ribera to contribute to the Coleoptera Tree of Life. This upload also includes the python scripts written to parse GenBank entries and the files to upload in iTOL webpage to highlight on trees the samples coming from Ignacio’s studies. Finally, we also include the 17,499 entries for nucleotide sequences deposited from Ignacio’s articles

    La "marcha" de San Ignacio

    No full text
    En un artículo anterior se mencionaba que el texto de la "Marcha" de San Ignacio se iba a transcribir con la puntuación de los signos rítmicos, sien embargo en el texto no aparecieron. Se transcribe la letra con la puntuaciónIn a previous article mention was made to the fact that the lyrics of the "March" of San Ignacio was going to be transcribed with the punctuation of the rhythmic signs, however, such signs did not appear in the text. The author transcribes the lyrics with the punctuatio

    Why (not) national party systems?

    No full text
    [Electronic resource] / Ignacio Lago. 26 p. : ill. Available through the CEACS Web site (http://www.march.es) Includes bibliographical references (p.20-22)
    corecore