Distributional Semantics 2017


Linguistic items with similar distributions have similar meanings.


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



See also:

JoBimText Distributional Semantics 2015

Representational similarity mapping of distributional semantics in left inferior frontal, middle temporal, and motor cortex
F Carota, N Kriegeskorte, H Nili… – Cerebral Cortex, 2017 – academic.oup.com
Abstract Language comprehension engages a distributed network of frontotemporal, parietal, and sensorimotor regions, but it is still unclear how meaning of words and their semantic relationships are represented and processed within these regions and to which

Using distributional semantics in loanword research: A concept-based approach to quantifying semantic specificity of Anglicisms in Spanish
J Serigos – International Journal of Bilingualism, 2017 – journals.sagepub.com
Aims and objectives: This study aims to redress the paucity of research on the semantics of loanwords, by extending and empirically testing Backus’s ((2001). The role of semantic specificity in insertional codeswitching: Evidence from Dutch-Turkish. Jacobson, Rodolfo

Measuring content overlap during handoff communication using distributional semantics: An exploratory study
J Abraham, TG Kannampallil, V Srinivasan… – Journal of biomedical …, 2017 – Elsevier
Abstract Objective We develop and evaluate a methodological approach to measure the degree and nature of overlap in handoff communication content within and across clinical professions. This extensible, exploratory approach relies on combining techniques from

Modelling the Meaning of Argument Constructions with Distributional Semantics
GE Lebani, A Lenci – Proceedings of the AAAI 2017 Spring …, 2017 – colinglab.humnet.unipi.it
Abstract Current computational models of argument constructions typically represent their semantic content with hand-made formal structures. Here we present a distributional model implementing the idea that the meaning of a construction is intimately related to the

Towards Holistic Concept Representations: Embedding Relational Knowledge, Visual Attributes, and Distributional Word Semantics
S Thoma, A Rettinger, F Both – International Semantic Web Conference, 2017 – Springer
Abstract Knowledge Graphs (KGs) effectively capture explicit relational knowledge about individual entities. However, visual attributes of those entities, like their shape and color and pragmatic aspects concerning their usage in natural language are not covered. Recent

Incremental Distributional Semantics for Dynamic Syntax
M Sadrzadeh, M Purver, R Kempson – dynamicsyntax.org
Distributional semantics is inspired by ideas of Firth and Harris, the former of which said ‘you shall know a word by the company it keeps'[Fir57]. Natural Language Processing researchers used this idea to turn corpora of documents into co-occurrence matrices to

Comparison of Word Embedding Models in the Task of Modeling Compositional Distributional Semantics
A Bakarov – 2017 – romip.ru
ABSTRACT This study considers the problem of automatic detection of semantic similarity of message pairs from the Russian imageboard 2ch and researches the approach of resolving it with a model that encodes every word in a message with a vector and then learns the sum

ICD-10 code retrieval based on distributional semantics of diagnosis descriptions
T Akiba, B Sy, A Zeidan – Advanced Informatics, Concepts …, 2017 – ieeexplore.ieee.org
In this paper, we propose a method for extracting ICD-10 codes from the natural language description of a patient illness complaint. The proposed method is based on distributional semantics of terms that appeared in the two natural language expressions: a patient’s

Indonesian unseen words explained by form, morphology and distributional semantics at the same time
R Fam, Y Lepage, S Gojali, A Purwarianti – 2017 – anlp.jp
Abstract We address the issue of explaining previously unseen words on different levels at the same time. We explain unseen words on the level of form by using analogical clusters extracted from a given training set by relying on formal relations between words. The

Non-commutative Logic for Compositional Distributional Semantics
K Cvetko-Vah, M Sadrzadeh, D Kartsaklis… – … Workshop on Logic …, 2017 – Springer
Abstract Distributional models of natural language use vectors to provide a contextual foundation for meaning representation. These models rely on large quantities of real data, such as corpora of documents, and have found applications in natural language tasks, such

The role of syntactic dependencies in compositional distributional semantics
P Gamallo – Corpus Linguistics and Linguistic Theory, 2017 – degruyter.com
Abstract This article provides a preliminary semantic framework for Dependency Grammar in which lexical words are semantically defined as contextual distributions (sets of contexts) while syntactic dependencies are compositional operations on word distributions. More

Replacing OOV Words For Dependency Parsing With Distributional Semantics
P Kolachina, M Riedl, C Biemann – … of the 21st Nordic Conference on …, 2017 – aclweb.org
Abstract Lexical information is an important feature in syntactic processing like part-ofspeech (POS) tagging and dependency parsing. However, there is no such information available for out-of-vocabulary (OOV) words, which causes many classification errors. We propose to

Non-commutative Logic for Compositional Distributional Semantics
B Blundell – Logic, Language, Information, and Computation: 24th …, 2017 – books.google.com
Abstract. Distributional models of natural language use vectors to provide a contextual foundation for meaning representation. These models rely on large quantities of real data, such as corpora of documents, and have found applications in natural language tasks, such

Learning Word Embeddings for Hyponymy with Entailment-Based Distributional Semantics
J Henderson – arXiv preprint arXiv:1710.02437, 2017 – arxiv.org
Abstract: Lexical entailment, such as hyponymy, is a fundamental issue in the semantics of natural language. This paper proposes distributional semantic models which efficiently learn word embeddings for entailment, using a recently-proposed framework for modelling

SEPIR: a semantic and personalised information retrieval tool for the public administration based on distributional semantics
P Basile, A Caputo, MD Ciano… – International …, 2017 – inderscienceonline.com
This paper introduces a semantic and personalised information retrieval (SEPIR) tool for the public administration of Apulia Region. SEPIR, through semantic search and visualisation tools, enables the analysis of a large amount of unstructured data and the intelligent access

Distributional Semantics Of The Partitive A Argument Construction In Finnish
T HUUMO, AKIJ KYRÖLÄINEN… – … : Analyzing Real-Life …, 2017 – books.google.com
Abstract In Standard Finnish, the case marking of the S argument in existential clauses alternates between the nominative and the partitive, while A arguments of transitive clauses are always in the nominative. In actual usage, however, the partitive is used occasionally to

Disambiguation of newly derived nominalizations in context: A Distributional Semantics approach.
G Lapesa, L Kawaletz, I Plag, M Andreou, M Kisselew… – 2017 – sfb991.uni-duesseldorf.de
Abstract One of the central problems in the semantics of derived words is polysemy (see, for example, the recent contributions by Lieber 2016 and Plag et al. 2017). In this paper, we tackle the problem of disambiguating newly derived words in context by applying

Identifying lexical relationships and entailments with distributional semantics
SC Roller – 2017 – repositories.lib.utexas.edu
Many modern efforts in Natural Language Understanding depend on rich and powerful semantic representations of words. Systems for sophisticated logical and textual reasoning often depend heavily on lexical resources to provide critical information about relationships

Holographic Declarative Memory: Using Distributional Semantics within ACT-R
MA Kelly, D Reitter – david-reitter.com
Abstract We explore replacing the declarative memory system of the ACT-R cognitive architecture with a distributional semantics model. ACT-R is a widely used cognitive architecture, but scales poorly to big data applications and lacks a robust model for learning

Compositional Distributional Semantics: Present Participle and Relative Clause Structures in Dutch
CS de Jong – 2017 – dspace.library.uu.nl
In this essay a Compositional Distributional Semantic approach is researched for studying two separate phenomena in the Dutch language. Firstly a theoretical outline for the Compositional Distributional Semantics is drawn, starting with the beginning of Distributional

Distributional semantics for diachronic search
P Gamallo, I Rodríguez-Torres, M Garcia – Computers & Electrical …, 2017 – Elsevier
Abstract This article describes a system aimed at searching for word similarity over different time periods. The strategy is based on distributional models obtained from a chronologically structured language resource, namely Google Books Syntactic Ngrams. The models were

Coherent Diagrammatic Reasoning in Compositional Distributional Semantics
GJ Wijnholds – … Workshop on Logic, Language, Information, and …, 2017 – Springer
Abstract The framework of Categorical Compositional Distributional models of meaning [3], inspired by category theory, allows one to compute the meaning of natural language phrases, given basic meaning entities assigned to words. Composing word meanings is the

Distributional Semantics
R Bernardi – 2017 – disi.unitn.it
The “language as use” school has focused on content words meaning. vs. Formal semantics school has focused mostly on the grammatical words and in particular on the behaviour of the “logical words”.? content words: are words that carry the content or the meaning of a

Leveraging Distributional Semantics for Multi-Label Learning
R Wadbude, V Gupta, P Rai, N Natarajan… – arXiv preprint arXiv …, 2017 – arxiv.org
Abstract: We present a novel and scalable label embedding framework for large-scale multi-label learning aka ExMLDS (Extreme Multi-Label Learning using Distributional Semantics). Our approach draws inspiration from ideas rooted in distributional semantics, specifically the

Polish evaluation dataset for compositional distributional semantics models
A Wróblewska, K Krasnowska-Kiera? – … of the 55th Annual Meeting of the …, 2017 – aclweb.org
Abstract The paper presents a procedure of building an evaluation dataset1. for the validation of compositional distributional semantics models estimated for languages other than English. The procedure generally builds on steps designed to assemble the SICK

Is Structure Necessary for Modeling Argument Expectations in Distributional Semantics?
E Chersoni, E Santus, P Blache, A Lenci – arXiv preprint arXiv:1710.00998, 2017 – arxiv.org
Abstract: Despite the number of NLP studies dedicated to thematic fit estimation, little attention has been paid to the related task of composing and updating verb argument expectations. The few exceptions have mostly modeled this phenomenon with structured

Distributional Semantics and Neural Network based Improvements to Dependency Parsing
S Kanneganti – 2017 – web2py.iiit.ac.in
Abstract Natural language processing is a field of artificial intelligence and computational linguistics that aims at bridging the gap between human beings and computers. It deals with processing natural languages in various forms like speech and text. Processing a natural

The Challenge of Composition in Distributional and Formal Semantics
R Tian, K Mineshima, P Martínez-Gómez – Proceedings of the IJCNLP …, 2017 – aclweb.org
• Vector-based approach–Vector-based composition models–Theory of additive composition–Vector-based reasoning• Symbolic approach–ccg2lambda: compositionality for your favorite semantic theory–Logic systems for RTE–RTE datasets for formal semantics: Fra-CaS and