Distributional semantics and linguistic theory
G Boleda - Annual Review of Linguistics, 2020 - annualreviews.org
Distributional semantics provides multidimensional, graded, empirically induced word
representations that successfully capture many aspects of meaning in natural languages, as …
representations that successfully capture many aspects of meaning in natural languages, as …
Learning to compose neural networks for question answering
We describe a question answering model that applies to both images and structured
knowledge bases. The model uses natural language strings to automatically assemble …
knowledge bases. The model uses natural language strings to automatically assemble …
[PDF][PDF] Injecting logical background knowledge into embeddings for relation extraction
Matrix factorization approaches to relation extraction provide several attractive features: they
support distant supervision, handle open schemas, and leverage unlabeled data …
support distant supervision, handle open schemas, and leverage unlabeled data …
Nlprolog: Reasoning with weak unification for question answering in natural language
Rule-based models are attractive for various tasks because they inherently lead to
interpretable and explainable decisions and can easily incorporate prior knowledge …
interpretable and explainable decisions and can easily incorporate prior knowledge …
Hyperlex: A large-scale evaluation of graded lexical entailment
We introduce HyperLex—a data set and evaluation resource that quantifies the extent of the
semantic category membership, that is, type-of relation, also known as hyponymy …
semantic category membership, that is, type-of relation, also known as hyponymy …
Language models as models of language
R Millière - arXiv preprint arXiv:2408.07144, 2024 - arxiv.org
This chapter critically examines the potential contributions of modern language models to
theoretical linguistics. Despite their focus on engineering goals, these models' ability to …
theoretical linguistics. Despite their focus on engineering goals, these models' ability to …
Reading and thinking: Re-read lstm unit for textual entailment recognition
Abstract Recognizing Textual Entailment (RTE) is a fundamentally important task in natural
language processing that has many applications. The recently released Stanford Natural …
language processing that has many applications. The recently released Stanford Natural …
Towards a visual turing challenge
M Malinowski, M Fritz - arXiv preprint arXiv:1410.8027, 2014 - arxiv.org
As language and visual understanding by machines progresses rapidly, we are observing
an increasing interest in holistic architectures that tightly interlink both modalities in a joint …
an increasing interest in holistic architectures that tightly interlink both modalities in a joint …
[HTML][HTML] Inducing semantic relations from conceptual spaces: a data-driven approach to plausible reasoning
J Derrac, S Schockaert - Artificial Intelligence, 2015 - Elsevier
Commonsense reasoning patterns such as interpolation and a fortiori inference have proven
useful for dealing with gaps in structured knowledge bases. An important difficulty in …
useful for dealing with gaps in structured knowledge bases. An important difficulty in …
Building a shared world: Mapping distributional to model-theoretic semantic spaces
A Herbelot, EM Vecchi - … 2015: Conference on Empirical Methods in …, 2015 - iris.unitn.it
In this paper, we introduce an approach to automatically map a standard distributional
semantic space onto a set-theoretic model. We predict that there is a functional relationship …
semantic space onto a set-theoretic model. We predict that there is a functional relationship …