Distributional Semantics 2015


Notes:

Linguistic items with similar distributions have similar meanings.

Resources:

  • s-space .. highly-scalable library for designing new distributional semantics algorithms

Wikipedia:

See also:

Distributional Semantics 2014 | JoBimText Distributional Semantics 2015


Compositional distributional semantics with long short term memory P Le, W Zuidema – arXiv preprint arXiv:1503.02510, 2015 – arxiv.org Abstract: We are proposing an extension of the recursive neural network that makes use of a variant of the long short-term memory architecture. The extension allows information low in parse trees to be stored in a memory register (thememory cell’) and used much later higher Cited by 22 Related articles All 11 versions

Compositional Distributional Semantics with Compact Closed Categories and Frobenius Algebras D Kartsaklis – arXiv preprint arXiv:1505.00138, 2015 – arxiv.org Abstract: This thesis contributes to ongoing research related to the categorical compositional model for natural language of Coecke, Sadrzadeh and Clark in three ways: Firstly, I propose a concrete instantiation of the abstract framework based on Frobenius algebras (joint work Cited by 16 Related articles All 6 versions

Affixation in semantic space: Modeling morpheme meanings with compositional distributional semantics. M Marelli, M Baroni – Psychological review, 2015 – psycnet.apa.org Abstract 1. The present work proposes a computational model of morpheme combination at the meaning level. The model moves from the tenets of distributional semantics, and assumes that word meanings can be effectively represented by vectors recording their co- Cited by 10 Related articles All 6 versions

Low-Rank Tensors for Verbs in Compositional Distributional Semantics. D Fried, T Polajnar, S Clark – ACL (2), 2015 – anthology.aclweb.org Abstract Several compositional distributional semantic methods use tensors to model multi- way interactions between vectors. Unfortunately, the size of the tensors can make their use impractical in large-scale implementations. In this paper, we investigate whether we can Cited by 8 Related articles All 14 versions

A Single Word is not Enough: Ranking Multiword Expressions Using Distributional Semantics. M Riedl, C Biemann – EMNLP, 2015 – informatik.tu-darmstadt.de Abstract We present a new unsupervised mechanism, which ranks word n-grams according to their multiwordness. It heavily relies on a new uniqueness measure that computes, based on a distributional thesaurus, how often an n-gram could be replaced in context by a single- Cited by 7 Related articles All 15 versions

The Forest Convolutional Network: Compositional Distributional Semantics with a Neural Chart and without Binarization. P Le, W Zuidema – EMNLP, 2015 – aclweb.org Abstract According to the principle of compositionality, the meaning of a sentence is computed from the meaning of its parts and the way they are syntactically combined. In practice, however, the syntactic structure is computed by automatic parsers which are far- Cited by 7 Related articles All 10 versions

Sentence entailment in compositional distributional semantics E Balkir, D Kartsaklis, M Sadrzadeh – arXiv preprint arXiv:1512.04419, 2015 – arxiv.org Abstract: Distributional semantic models provide vector representations for words by gathering co-occurrence frequencies from corpora of text. Compositional distributional models extend these representations from words to phrases and sentences. In categorical Cited by 6 Related articles All 6 versions

An exploration of discourse-based sentence spaces for compositional distributional semantics T Polajnar, L Rimell, S Clark – Workshop on Linking Models …, 2015 – anthology.aclweb.org Abstract This paper investigates whether the wider context in which a sentence is located can contribute to a distributional representation of sentence meaning. We compare a vector space for sentences in which the features are words occurring within the sentence, with two Cited by 6 Related articles All 12 versions

From distributional semantics to conceptual spaces: A novel computational method for concept creation S McGregor, K Agres, M Purver… – Journal of Artificial …, 2015 – degruyter.com Abstract We investigate the relationship between lexical spaces and contextually-defined conceptual spaces, offering applications to creative concept discovery. We define a computational method for discovering members of concepts based on semantic spaces: Cited by 6 Related articles All 10 versions

Conceptualizing creativity: From distributional semantics to conceptual spaces K Agres, S McGregor, M Purver… – Proceedings of the Sixth …, 2015 – researchgate.net Abstract This paper puts forth a method for discovering computationally-derived conceptual spaces that reflect human conceptualization of musical and poetic creativity. We describe a lexical space that is defined through co-occurrence statistics, and compare the dimensions Cited by 5 Related articles All 10 versions

Leveraging preposition ambiguity to assess compositional distributional models of semantics S Ritter, C Long, D Paperno, M Baroni… – Lexical and …, 2015 – anthology.aclweb.org … 2014a. Frege in space: A program of compo- sitional distributional semantics. Linguistic Issues in Language Technology, 9. Marco Baroni, Georgiana Dinu, and Germán Kruszewski. 2014b. … 2013. Multi-step regression learning for composi- tional distributional semantics. … Cited by 4 Related articles All 8 versions

Dcu: Using distributional semantics and domain adaptation for the semantic textual similarity semeval-2015 task 2 P Arora, C Hokamp, J Foster, GJF Jones – Proceedings of the 9th …, 2015 – aclweb.org Abstract We describe the work carried out by the DCU team on the Semantic Textual Similarity task at SemEval-2015. We learn a regression model to predict a semantic similarity score between a sentence pair. Our system exploits distributional semantics in Cited by 4 Related articles All 10 versions

A Frobenius model of information structure in categorical compositional distributional semantics D Kartsaklis, M Sadrzadeh – arXiv preprint arXiv:1505.06294, 2015 – arxiv.org Abstract: The categorical compositional distributional model of Coecke, Sadrzadeh and Clark provides a linguistically motivated procedure for computing the meaning of a sentence as a function of the distributional meaning of the words therein. The theoretical framework Cited by 4 Related articles All 13 versions

From visual attributes to adjectives through decompositional distributional semantics A Lazaridou, G Dinu, A Liska, M Baroni – arXiv preprint arXiv:1501.02714, 2015 – arxiv.org Abstract: As automated image analysis progresses, there is increasing interest in richer linguistic annotation of pictures, with attributes of objects (eg, furry, brown…) attracting most attention. By building on the recent” zero-shot learning” approach, and paying attention to Cited by 4 Related articles All 10 versions

When the whole is not greater than the combination of its parts: A “decompositional” look at compositional distributional semantics FM Zanzotto, L Ferrone, M Baroni – Computational Linguistics, 2015 – MIT Press 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 Cited by 3 Related articles All 13 versions

Distributional semantics for ontology verification J Corman, N Aussenac-Gilles… – 4th Joint Conference on …, 2015 – hal.archives-ouvertes.fr As they grow in size, OWL ontologies tend to comprise intuitively incompatible statements, even when they remain logically consistent. This is true in particular of lightweight ontologies, especially the ones which aggregate knowledge from different sources. The Cited by 3 Related articles All 13 versions

Ensembles of semantic spaces: On combining models of distributional semantics with applications in healthcare A Henriksson – 2015 – diva-portal.org Background: Terminologies that account for variation in language use by linking synonyms and abbreviations to their corresponding concept are important enablers of high-quality information extraction from medical texts. Due to the use of specialized sub-languages in the Cited by 2 Related articles

Distributional semantics in use R Bernardi, G Boleda, R Fernández… – Workshop on Linking …, 2015 – aclweb.org Abstract In this position paper we argue that an adequate semantic model must account for language in use, taking into account how discourse context affects the meaning of words and larger linguistic units. Distributional semantic models are very attractive models of Cited by 2 Related articles All 15 versions

Encoding Distributional Semantics into Triple-Based Knowledge Ranking for Document Enrichment. M Zhang, B Qin, M Zheng, G Hirst, T Liu – ACL (1), 2015 – db.toronto.edu Abstract Document enrichment focuses on retrieving relevant knowledge from external resources, which is essential because text is generally replete with gaps. Since conventional work primarily relies on special resources, we instead use triples of Subject, Predicate, Cited by 2 Related articles All 22 versions

Distributional Semantics for Resolving Bridging Mentions. T Feuerbach, M Riedl, C Biemann – RANLP, 2015 – anthology.aclweb.org Abstract We explore the impact of adding distributional knowledge to a state-of-the-art coreference resolution system. By integrating features based on word and context expansions from a distributional thesaurus (DT), automatically mined IS-A relationships and Cited by 2 Related articles All 10 versions

Approximate and selective reasoning on knowledge graphs: A distributional semantics approach A Freitas, JCP da Silva, E Curry, P Buitelaar – Data & Knowledge …, 2015 – Elsevier Abstract Tasks such as question answering and semantic search are dependent on the ability of querying and reasoning over large-scale commonsense knowledge bases (KBs). However, dealing with commonsense data demands coping with problems such as the Cited by 2 Related articles All 4 versions

Semi-Supervised Bootstrapping of Relationship Extractors with Distributional Semantics. DS Batista, B Martins, MJ Silva – EMNLP, 2015 – aclweb.org Abstract Semi-supervised bootstrapping techniques for relationship extraction from text iteratively expand a set of initial seed relationships while limiting the semantic drift. We research bootstrapping for relationship extraction using word embeddings to find similar Cited by 2 Related articles All 13 versions

From distributional semantics to distributional pragmatics M Purver, M Sadrzadeh – … of the IWCS 2015 Workshop on …, 2015 – iwcs2015.github.io To model meaning in dialogue, we must go beyond individual sentence meanings to look at their role in, and contribution to, a wider structure which emerges through the interaction. Formal models of dialogue tend to account for this dialogue structure in terms of either the Cited by 1 Related articles All 4 versions

Linse: A distributional semantics entity search engine JE Sales, A Freitas, S Handschuh, B Davis – Proceedings of the 38th …, 2015 – dl.acm.org Abstract Entering’Football Players from United States’ when searching for’American Footballers’ is an example of vocabulary mismatch, which occurs when different words are used to express the same concepts. In order to address this phenomenon for entity search Cited by 1 Related articles All 4 versions

Distributional-relational models: Scalable semantics for databases A Freitas, S Handschuh, E Curry – 2015 AAAI Spring Symposium Series, 2015 – Citeseer … Distributional semantics provides a complementary perspec- tive to the formal perspective of database semantics, which supports semantic approximation as a first-class database operation. A distributional semantics approach … Cited by 1 Related articles All 5 versions

Finding infrequent phenomena in large corpora using distributional semantics M Skeppstedta, C Paradisc, A Kerrena… – Poster Abstracts of …, 2015 – researchgate.net The abundance of text published on the Internet makes it possible to harvest a large number of samples of linguistic phenomena, also of phenomena that are less frequently occurring. This is useful for qualitative and quantitative linguistic studies, as well as for training Cited by 1 Related articles All 5 versions

Dissecting the practical lexical function model for compositional distributional semantics A Gupta, J Utt, S Padó – Lexical and Computational Semantics (* SEM …, 2015 – aclweb.org Abstract The Practical Lexical Function model (PLF) is a recently proposed compositional distributional semantic model which provides an elegant account of composition, striking a balance between expressiveness and robustness and performing at the state-of-the-art. In Cited by 1 Related articles All 9 versions

Distributional Semantics Today Introduction to the special issue C Fabre, A Lenci – Traitement Automatique des Langues, 2015 – hal.archives-ouvertes.fr This introduction to the special issue of the TAL journal on distributional semantics provides an overview of the current topics of this field and gives a brief summary of the contributions. RÉSUMÉ. Cette introduction au numéro spécial de la revue TAL consacré à la sémantique Cited by 1 Related articles All 10 versions

Expanding a dictionary of marker words for uncertainty and negation using distributional semantics A Alfalahi, M Skeppstedt, R Ahlbom, R Baskalayci… – 2015 – diva-portal.org Abstract Approaches to determining the factuality of diagnoses and findings in clinical text tend to rely on dictionaries of marker words for uncertainty and negation. Here, a method for semi-automatically expanding a dictionary of marker words using distributional semantics is Cited by 1 Related articles All 3 versions

Exploratory topic modeling with distributional semantics S Rönnqvist – International Symposium on Intelligent Data Analysis, 2015 – Springer Abstract As we continue to collect and store textual data in a multitude of domains, we are regularly confronted with material whose largely unknown thematic structure we want to uncover. With unsupervised, exploratory analysis, no prior knowledge about the content is Cited by 1 Related articles All 4 versions

A Generalisation of Lexical Functions for Composition in Distributional Semantics. A Bride, T Van de Cruys, N Asher – ACL (1), 2015 – aclweb.org Abstract Over the last two decades, numerous algorithms have been developed that successfully capture something of the semantics of single words by looking at their distribution in text and comparing these distributions in a vector space model. However, it is Cited by 2 Related articles All 5 versions

A Hybrid Distributional and Knowledge-based Model of Lexical Semantics N Aletras, M Stevenson – Lexical and Computational …, 2015 – anthology.aclweb.org … This issue has lead to signif- icant exploration of the problem of Word Sense Dis- ambiguation (Ide and Véronis, 1998; Navigli, 2009). More recently distributional semantics has become a popular approach to representing lexical semantics (Turney and Pantel, 2010; Erk, 2012). … Cited by 1 Related articles All 12 versions

Proposing distributional semantics as a tool for medical vocabulary expansion M Rahman, L Asker, M Skeppstedt – International Workshop on …, 2015 – prhlt.upv.es Abstract: A tool that extends a given vocabulary by automatically extracting new term candidates from a corpus could facilitate vocabulary expansion, as well as ensure that extracted terms correspond to those actually used in a specific text genre. We here propose Related articles All 3 versions

Distributional Semantics in Language Modeling T Brychcín – 2015 – researchgate.net Abstract Language models are crucial for many tasks in natural language processing and n- grams are probably the best way to build them. Huge effort is being invested in improving the n-gram language models. By introducing external knowledge (morphology, syntax, etc.) Related articles

[BOOK] Modeling Idiom Variability with Entropy and Distributional Semantics GE Lebani, M Senaldi, A Lenci – 2015 – bibliographie.uni-tuebingen.de Abstract—In this paper we assessed the cognitive plausibility of corpus-based flexibility measures for a sample of Italian idioms taken from the normative data by Tabossi et al.(2011). We found that psycholinguistic judgments on idiom predictability, literality and Related articles All 3 versions

Distributional semantics for Child-Directed Speech D Master – 2015 – clips.ua.ac.be Then feed a vector of a new image and a semantic space with new concepts, have the mapping function ‘reconstruct’the linguistic vector for the given image and retrieve the nearest neighbors for this ‘reconstructed’vector in the semantic space. Hopefully it will be the All 4 versions

Enhancing the Accuracy of Ancient Greek WordNet by Multilingual Distributional Semantics Y Bizzoni, R Del Gratta, F Boschetti, M Reboul – CLiC it, 2015 – iris.unito.it 47 Enhancing the Accuracy of Ancient Greek WordNet by Multilingual Distributional Semantics Yuri Bizzoni1, Riccardo Del Gratta1, Federico Boschetti1, Marianne Reboul2 1ILC-CNR, Pisa 2Université de Paris 4, Paris {yuri. bizzoni, riccardo. delgratta}@ gmail. com, federico. Related articles All 3 versions

Exploring Distributional Semantics with the Spacexplorer Tool Á Tóth – BAS British and American Studies, 2015 – ceeol.com Summary/Abstract: Distributional studies quantify the similarity of words by collecting word co-occurrence frequency information from large text corpora. According to the distributional hypothesis, this similarity is a semantic phenomenon. This paper aims to introduce the Related articles All 3 versions

Schema-agnostic queries for large-schema databases: A distributional semantics approach A Freitas – 2015 – aran.library.nuigalway.ie The evolution of data environments towards the growth in the size, complexity, dynamicity and decentralisation (SCoDD) of schemas drastically impacts contemporary data management. The SCoDD trend emerges as a central data management concern in Big Related articles All 2 versions

Distributional semantics and unsupervised clustering for sensor relevancy prediction M Leggieri, B Davis, JG Breslin – … Communications and Mobile …, 2015 – ieeexplore.ieee.org Abstract: The logging of Activities of Daily Living (ADLs) is becoming increasingly popular mainly thanks to wearable devices. Currently, most sensors used for ADLs logging are queried and filtered mainly by location and time. However, in an Internet of Things future, a Related articles All 2 versions

A Multitask Objective to Inject Lexical Contrast into Distributional Semantics NTPAL MarcoBaroni – Volume 2: Short Papers – pdfs.semanticscholar.org Abstract Distributional semantic models have trouble distinguishing strongly contrasting words (such as antonyms) from highly compatible ones (such as synonyms), because both kinds tend to occur in similar contexts in corpora. We introduce the multitask Lexical Contrast Related articles All 9 versions

Type-driven distributional semantics for prepositional phrase attachment A Delpeuch – 2015 – eleves.ens.fr Abstract Combining the strengths of distributional and logical semantics of natural language is a problem that has gained a lot of attention recently. We focus here on the distributional compositional framework of Coecke et al.(2011), which brings syntax-driven Related articles All 6 versions

On Quantum Generalizations of Information-Theoretic Measures and their Contribution to Distributional Semantics W Blacoe – arXiv preprint arXiv:1506.00578, 2015 – arxiv.org Abstract: Information-theoretic measures such as relative entropy and correlation are extremely useful when modeling or analyzing the interaction of probabilistic systems. We survey the quantum generalization of 5 such measures and point out some of their Related articles All 4 versions

Learning Grasping Possibilities for Artifacts: Dimensions, Weights and Distributional Semantics I Russo, I De Felice – CLiC it, 2015 – iris.unito.it Abstract English. In this paper we want to test how grasping possibilities for concrete objects can be automatically classified. To discriminate between objects that can be manipulated with one hand and the ones that require two hands, we combine conceptual knowledge Related articles All 2 versions

Distributional Semantics and Authorship Differences M Gritta – 2015 – academia.edu Abstract In Computational Linguistics, distributional semantic methods depend on the idea that words with similar meanings will appear in similar contexts. However, nearly all work in this area has used very large corpora, combining the data from many genres and many Related articles

The Verbiverse: Creating a Verb Space with Comparative Methods of Distributional Semantics AJ Blodgett – 2015 – etd.library.emory.edu By Austin James Blodgett Computational semantics as a field includes many of the unsolved problems of Natural Language Processing. The need for innovation in this field has motivated much research in developing word and language models that better represent Related articles

Concept Extensions as the Basis for Vector-Space Semantics: Combining Distributional and Ontological Information about Entities JCK Cheung – ACL-IJCNLP 2015, 2015 – anthology.aclweb.org … Distributional semantics is a potential solution to this problem. … Our model, which we call Ontological Distributional Semantics, employs a simple feedforward neural network architecture to learn interactions between these two sources of in- formation. … Related articles All 8 versions