Distributional Semantics 2014


See also:

100 Best GitHub: Collocation | Abstractive Summarization 2014 | Alchemy Open Source AI | AlchemyAPI 2014 | Autoencoder & Natural Language 2014 | Automatic Summarization & Neural Networks 2014 | CLE (Core Language Engine) | CNN (Convolutional Neural Network) & Natural Language 2014 | Dialog Systems 2013 | Dialog Systems 2014 | Discourse Parser 2014 | Distributional Semantics 2015MaltParser Dependency Parser | Neural Language Models | OpenCalais 2013 | RNN (Recurrent Neural Network) & Dialog Systems 2014 | Semantic Fingerprint | SkipGram & Deep Learning 2014 | Treebank & Dialog Systems 2014 | Word2vec Neural Network


Frege in Space: A Program of Compositional Distributional Semantics M Baroni, R Bernardi, R Zamparelli – Linguistic Issues in Language …, 2014 – elanguage.net Abstract The lexicon of any natural language encodes a huge number of distinct word meanings. Just to understand this article, you will need to know what thousands of words mean. The space of possible sentential meanings is infinite: In this article alone, you will … Cited by 38 Related articles All 3 versions

Multimodal Distributional Semantics. E Bruni, NK Tran, M Baroni – J. Artif. Intell. Res.(JAIR), 2014 – clic.cimec.unitn.it Abstract Distributional semantic models derive computational representations of word meaning from the patterns of co-occurrence of words in text. Such models have been a success story of computational linguistics, being able to provide reliable estimates of … Cited by 18 Related articles All 12 versions

Semantic parsing using distributional semantics and probabilistic logic I Beltagy, K Erk, R Mooney – ACL 2014, 2014 – acl2014.org Abstract We propose a new approach to semantic parsing that is not constrained by a fixed formal ontology and purely logical inference. Instead, we use distributional semantics to generate only the relevant part of an on-the-fly ontology. Sentences and the on-the-fly … Cited by 5 Related articles All 11 versions

How to make words with vectors: Phrase generation in distributional semantics G Dinu, M Baroni – Proceedings of the 52nd Annual Meeting of the …, 2014 – acl2014.org Abstract We introduce the problem of generation in distributional semantics: Given a distributional vector representing some meaning, how can we generate the phrase that best expresses that meaning? We motivate this novel challenge on theoretical and practical … Cited by 5 Related articles All 5 versions

Is this a wampimuk? cross-modal mapping between distributional semantics and the visual world A Lazaridou, E Bruni, M Baroni – Proceedings of ACL, 2014 – clic.cimec.unitn.it Abstract Following up on recent work on establishing a mapping between vector-based semantic embeddings of words and the visual representations of the corresponding objects from natural images, we first present a simple approach to cross-modal vector-based … Cited by 5 Related articles All 6 versions

Compositional operators in distributional semantics D Kartsaklis – Springer Science Reviews, 2014 – Springer Abstract This survey presents in some detail the main advances that have been recently taking place in Computational Linguistics towards the unification of the two prominent semantic paradigms: the compositional formal semantics view and the distributional … Cited by 4 Related articles All 8 versions

A Distributional Semantics Approach for Selective Reasoning on Commonsense Graph Knowledge Bases A Freitas, JCP da Silva, E Curry, P Buitelaar – … Language Processing and …, 2014 – Springer Abstract Tasks such as question answering and semantic search are dependent on the ability of querying & reasoning over large-scale commonsense knowledge bases (KBs). However, dealing with commonsense data demands coping with problems such as the … Cited by 3 Related articles All 4 versions

Medical vocabulary mining using distributional semantics on Japanese patient blogs M Ahltorp, M Skeppstedt, S Kitajima… – Semantic Mining in …, 2014 – diva-portal.org Random indexing has previously been successfully used for medical vocabulary expansion for Germanic languages. In this study, we used this approach to ex-tract medical terms from a Japanese pa-tient blog corpus. The corpus was seg-mented into semantic units by a … Cited by 2 Related articles

Distributional Semantics in R with the wordspace Package S Evert – Proceedings of COLING, 2014 – anthology.aclweb.org Abstract This paper introduces the wordspace package, which turns Gnu R into an interactive laboratory for research in distributional semantics. The package includes highly efficient implementations of a carefully chosen set of key functions, allowing it to scale up … Cited by 2 Related articles All 9 versions

UTexas: Natural Language Semantics using Distributional Semantics and Probabilistic Logic I Beltagy, S Roller, G Boleda, K Erk… – SemEval 2014, 2014 – anthology.aclweb.org Abstract We represent natural language semantics by combining logical and distributional information in probabilistic logic. We use Markov Logic Networks (MLN) for the RTE task, and Probabilistic Soft Logic (PSL) for the STS task. The system is evaluated on the SICK … Cited by 2 Related articles All 8 versions

Natural language queries over heterogeneous linked data graphs: A distributional-compositional semantics approach A Freitas, E Curry – Proceedings of the 19th international conference on …, 2014 – dl.acm.org … distributional-compositional semantics approach. Distributional semantics focuses on the automatic construction of a semantic model based on the statistical dis- tribution of co-occurring words in large-scale texts. The pro- posed … Cited by 6 Related articles All 14 versions

Combining Formal and Distributional Models of Temporal and Intensional Semantics M Lewis, M Steedman – ACL 2014, 2014 – ling.uni-potsdam.de … 1 Combined Distributional and Logical Semantics Distributional semantics aims to induce the mean- ing of language from unlabelled text. Traditional approaches to distributional semantics have repre- sented semantics in vector spaces (Baroni et al., 2013). … Cited by 1 Related articles All 11 versions

Combining distributional semantics and entity linking for context-aware content-based recommendation C Musto, G Semeraro, P Lops, M de Gemmis – User Modeling, Adaptation, …, 2014 – Springer Abstract The effectiveness of content-based recommendation strategies tremendously depends on the representation formalism adopted to model both items and user profiles. As a consequence, techniques for semantic content representation emerged thanks to their … Cited by 1 Related articles All 4 versions

A Markovian approach to distributional semantics with application to semantic compositionality E Grave, G Obozinski, F Bach – International Conference on …, 2014 – hal.inria.fr In this article, we describe a new approach to distributional semantics. This approach relies on a generative model of sentences with latent variables, which takes the syntax into account by using syntactic dependency trees. Words are then represented as posterior … Cited by 1 Related articles All 34 versions

Wikipedia-based Distributional Semantics for Entity Relatedness N Aggarwal, P Buitelaar – 2014 AAAI Fall Symposium Series, 2014 – deri.ie Abstract Wikipedia provides an enormous amount of background knowledge to reason about the semantic relatedness between two entities. We propose Wikipedia-based Distributional Semantics for Entity Relatedness (DiSER), which represents the semantics … Cited by 1 Related articles All 8 versions

Detecting learner errors in the choice of content words using compositional distributional semantics E Kochmar, T Briscoe – … of the 25th International Conference on …, 2014 – cl.cam.ac.uk Abstract We describe a novel approach to error detection in adjective–noun combinations. We present and release a new dataset of annotated errors where the examples are extracted from learner texts and annotated with error types. We show how compositional … Cited by 1 Related articles All 5 versions

Semantics at Scale: When Distributional Semantics meets Logic Programming A Freitas, JCP da Silva – cs.nmsu.edu Abstract. Distributional semantic models (DSMs) are semantic models which are automatically built from co-occurrence patterns in unstructured text. These semantic models trade representation structure for volume of semantic and commonsense knowledge, and … Related articles

Method for extracting single-word translation correspondences from parallel texts using distributional semantics models YI Morozova, EB Kozerenko, MM Sharnin – Sistemy i Sredstva Informatiki …, 2014 – mathnet.ru Abstract: The paper deals with problems of corpus research of linguistic units. The task of extracting translation correspondences from a parallel corpus is defined. An overview of existing approaches to this task is provided. The paper focuses on the approach to …

ThinkMiners: Disorder Recognition using Conditional Random Fields and Distributional Semantics A Parikh, A PVS, J Mustafi, L Agarwalla, A Mungi – SemEval 2014, 2014 – aclweb.org Abstract In 2014, SemEval organized multiple challenges on natural language processing and information retrieval. One of the task was analysis of the clinical text. This challenge is further divided into two tasks. The task A of the challenge was to extract disorder mention … Related articles All 6 versions

Medical vocabulary mining using distributional semantics on Japanese patient blogs MAMSS Kitajima, RRK Araki – researchgate.net Abstract Random indexing has previously been successfully used for medical vocabulary expansion for Germanic languages. In this study, we used this approach to extract medical terms from a Japanese patient blog corpus. The corpus was segmented into semantic … Related articles All 2 versions

Beyond Vision: Multi-Modal Distributional Semantics with Audio Data D Kiela, S Clark – cl.cam.ac.uk Abstract Multi-modal distributional models often rely on raw image data for their perceptual input. In this study we show that using auditory information instead of visual information also improves results. We use a bag-of-audio-words approach to obtain auditory …

Entity-Augmented Distributional Semantics for Discourse Relations Y Ji, J Eisenstein – arXiv preprint arXiv:1412.5673, 2014 – arxiv.org Abstract: Discourse relations bind smaller linguistic elements into coherent texts. However, automatically identifying discourse relations is difficult, because it requires understanding the semantics of the linked sentences. A more subtle challenge is that it is not enough to … Related articles All 3 versions

A Markovian approach to distributional semantics FBI DIRECTEUR – 2014 – hal.archives-ouvertes.fr … A Markovian approach to distributional semantics Directeurs de thèse : FRANCIS BACH ET GUILLAUME OBOZINSKI. … Page 7. ABSTRACT THIS THESIS, which is organized in two independent parts, presents work on distributional semantics and on variable selection. … Related articles All 6 versions

Leveraging Frame Semantics and Distributional Semantics for Unsupervised Semantic Slot Induction in Spoken Dialogue Systems YN Chen, WY Wang, AI Rudnicky – cs.cmu.edu ABSTRACT Distributional semantics and frame semantics are two representative views on language understanding in the statistical world and the linguistic world, respectively. In this paper, we combine the best of two worlds to automatically induce the semantic slots for … Cited by 3 Related articles All 3 versions

Incorporating Both Distributional and Relational Semantics in Word Representations D Fried, K Duh – arXiv preprint arXiv:1412.4369, 2014 – arxiv.org … Although many kinds of representation learning algorithms have been proposed so far, they are all essentially based on the same premise of distributional semantics (Harris, 1954), embodied by J. R. Firth’s dictum: ”You shall know a word by the company it keeps.” For example … Related articles All 4 versions

One Vector is Not Enough: Entity-Augmented Distributional Semantics for Discourse Relations Y Ji, J Eisenstein – arXiv preprint arXiv:1411.6699, 2014 – arxiv.org Abstract: Discourse relations bind smaller linguistic units into coherent texts. However, automatically identifying discourse relations is difficult, because it requires understanding the semantics of the linked arguments. A more subtle challenge is that it is not enough to … Related articles All 3 versions

When the whole is not greater than the combination of its parts: A “decompositional” look at compositional distributional semantics F Zanzotto, L Ferrone, M Baroni – Computational linguistics, 2014 – clic.cimec.unitn.it Distributional semantics has been extended to phrases and sentences by means of composition operations. We look at how these operations affect similarity measurements, showing that similarity equations of an important class of composition methods can be … Related articles All 2 versions

Probabilistic distributional semantics with latent variable models DO Séaghdha, A Korhonen – Computational Linguistics, 2014 – MIT Press We describe a probabilistic framework for acquiring selectional preferences of linguistic predicates and for using the acquired representations to model the effects of context on word meaning. Our framework uses Bayesian latent-variable models inspired by, and extending … Related articles All 5 versions

A Markovian approach to distributional semantics E Grave – 2014 – tel.archives-ouvertes.fr This thesis, which is organized in two independent parts, presents work on distributional semantics and on variable selection. In the first part, we introduce a new method for learning good word representations using large quantities of unlabeled sentences. The method is … Related articles All 9 versions

Nominal Coercion in Space: Mass/Count Nouns and Distributional Semantics EM LCT, R Bernardi, D Paperno – disi.unitn.it Abstract English Theoretical linguists analyse all nouns as either mass or count, but admit that noun meanings can be shifted from one class to the other and classify these shifts. We use distributional semantic models to check how the theoretical analysis of mass-count … Related articles All 3 versions

Will Distributional Semantics Ever Become Semantic? A Lenci – Language, 2014 – gwc2014.ut.ee To be relevant [linguistic] elements must be set up on a distributional basis: x and y are included in the same element A if the distribution of x relative to the other elements B, C, etc. is in some sense the same as the distribution of y.(Harris 1951: 7) Related articles

Compositional Distributional Semantics Models in Chunk-based Smoothed Tree Kernels L Ferrone, F Zanzotto – * SEM 2014: Third Joint Conference on …, 2014 – art.torvergata.it The field of compositional distributional semantics has proposed very interesting and reliable models for accounting the distributional meaning of simple phrases. These models however tend to disregard the syntactic structures when they are applied to larger … Related articles All 5 versions

Vector spaces for historical linguistics: Using distributional semantics to study syntactic productivity in diachrony F Perek – acl2014.org Abstract This paper describes an application of distributional semantics to the study of syntactic productivity in diachrony, ie, the property of grammatical constructions to attract new lexical items over time. By providing an empirical measure of semantic similarity … Related articles All 8 versions

Distributional Semantics meets Embodied Cognition: Flickr as a database of semantic features M BOLOGNESI – 2014 – uk-cla.org.uk Abstract Distributional models such as Latent Semantic Analysis (LSA, Landauer, Dumais 1997) generate semantic spaces based on the co-occurrences of words in linguistic contexts. The semantic representations that emerge from these models are based solely … Related articles All 2 versions

Predicting sense convergence with distributional semantics: an application to the CogALex-IV 2014 shared task L Sitbon, L De Vine – Proceedings of the 4th Workshop on …, 2014 – eprints.qut.edu.au This paper presents our system to address the CogALex-IV 2014 shared task of identifying a single word most semantically related to a group of 5 words (queries). Our system uses an implementation of a neural language model and identifies the answer word by finding the … Related articles All 4 versions

Distributional Semantics For Robust Automatic Summarization JCK Cheung – 2014 – cs.mcgill.ca Page 1. DISTRIBUTIONAL SEMANTICS FOR ROBUST AUTOMATIC SUMMARIZATION by Jackie Chi Kit Cheung … Page 2. Abstract Distributional Semantics for Robust Automatic Summarization Jackie Chi Kit Cheung Doctor of Philosophy …

Inducing Latent Semantic Relations for Structured Distributional Semantics SK Jauhar, E Hovy – anthology.aclweb.org Abstract Structured distributional semantic models aim to improve upon simple vector space models of semantics by hypothesizing that the meaning of a word is captured more effectively through its relational—rather than its raw distributional—signature. In … Related articles All 3 versions

“Distributional Semantics for Philosophy” Distributional semantics is a linguistic approach to the representation of meaning which has its origins in the 1950s, … A Herbelot – ifpp.fk14.tu-dortmund.de In this talk, I will briefly present three applications of distributional semantics to philosophy: 1. The analysis of ‘discourse’in critical theory. Being typically obtained on large amounts of actual utterances from thousands of different speakers, distributions are appropriate to … Related articles

Distributional Semantics in a Word-Space for Opinions of the Swedish Web S Albertsson, P Fallgren, M Liw, A Persson, J Rittfeldt… – ida.liu.se Abstract. The amount of data available on the Internet these days makes it possible to perform intriguing analyses to conclude such things as expressed opinions from looking at text in social networks, such as forums or blogs. We implement the word-space model built … Related articles All 4 versions

Using Distributional Semantics to Trace Influence and Imitation in Romantic Orientalist Poetry N Aggarwal, J Tonra… – AHA!-Workshop 2014 on …, 2014 – aran.library.nuigalway.ie In this paper, we investigate whether textual analysis can yield evidence of shared vocabulary orformal textual characteristics in the works of 19th century poets Lord Byron and Thomas Moorein the genre of Romantic Orientalism. In particular, we identify and trace … Related articles All 17 versions

Using distributional semantics to study syntactic productivity in diachrony: A case study F Perek – fperek.net Grammars are in constant change. 1 Over time, different ways are created in which words can be combined into phrases and sentences, while others fall into disuse. For example, in English, the basic word order used to be SOV at the onset of the Old English period, … Related articles

Distributional Semantics: A Montagovian View R Bernardi – Categories and Types in Logic, Language, and Physics, 2014 – Springer Abstract This paper describes the current status of research in Distributional Semantics looking at the results from the Montagovian tradition stand point. It considers the main aspects of the Montagovian view as binoculars to observe those results, in particular: … Related articles All 3 versions

Exploiting distributional semantics for content-based and context-aware recommendation V Codina Busquet – 2014 – tdx.cesca.es Abstract: During the last decade, the use of recommender systems has been increasingly growing to the point that, nowadays, the success of many well-known services depends on these technologies. Recommenders Systems help people to tackle the choice overload … Related articles All 9 versions

Reducing Dimensions of Tensors in Type-Driven Distributional Semantics TPLF StephenClark – aclweb.org Abstract Compositional distributional semantics is a subfield of Computational Linguistics which investigates methods for representing the meanings of phrases and sentences. In this paper, we explore implementations of a framework based on Combinatory Categorial … Related articles All 5 versions

The semantics of poetry: A distributional reading A Herbelot – Literary and Linguistic Computing, 2014 – ALLC … Distributional semantics provides a theoretical and experimental basis for this exploration. First, the notion of a specific ‘semantics of poetry’ is discussed, with some help from literary criticism and philosophy. … 2.2 Distributional semantics and poetry. … Related articles All 2 versions