1,720,990 research outputs found
Towards Syntax-aware Compositional Distributional Semantic Models
Get PDFCompositional Distributional Semantics Models (CDSMs) are traditionally seen as an entire different
world with respect to Tree Kernels (TKs). In this paper, we show that under a suitable
regime these two approaches can be regarded as the same and, thus, structural information and
distributional semantics can successfully cooperate in CSDMs for NLP tasks. Leveraging on
distributed trees, we present a novel class of CDSMs that encode both structure and distributional
meaning: the distributed smoothed trees (DSTs). By using DSTs to compute the similarity
among sentences, we implicitly define the distributed smoothed tree kernels (DSTKs). Experiment
with our DSTs show that DSTKs approximate the corresponding smoothed tree kernels
(STKs). Thus, DSTs encode both structural and distributional semantics of text fragments as
STKs do. Experiments on RTE and STS show that distributional semantics encoded in DSTKs
increase performance over structure-only kernels
Linear Compositional Distributional Semantics and Structural Kernels
Get PDFIn this paper, we want to start the analysis of the models for compositional distributional semantics (CDS) with respect to the distributional similarity. We believe that this simple analysis of the properties of the similarity can help to better investigate new CDS models. We show that, looking at CDS models from this point of view, these models are strictly related with convolution kernels (Haussler, 1999), e.g.: tree kernels (Collins and Duffy, 2002).
We will then examine how the distributed tree kernels (Zanzotto and Dell’Arciprete, 2012) are an interesting result to draw a stronger link between CDS models and convolution kernels
Symbolic, Distributed and Distributional Representations for Natural Language Processing in the Era of Deep Learning: a Survey
Get PDFNatural language is inherently a discrete symbolic representation of human knowledge. Recent advances in machine learning (ML) and in natural language processing (NLP) seem to contradict the above intuition: discrete symbols are fading away, erased by vectors or tensors called distributed and distributional representations. However, there is a strict link between distributed/distributional representations and discrete symbols, being the first an approximation of the second. A clearer understanding of the strict link between distributed/distributional representations and symbols may certainly lead to radically new deep learning networks. In this paper we make a survey that aims to renew the link between symbolic representations and distributed/distributional representations. This is the right time to revitalize the area of interpreting how discrete symbols are represented inside neural networks
Can we explain natural language inference decisions taken with neural networks? Inference rules in distributed representations
No full textNatural Language Inference (NLI) is a key, complex task where machine learning (ML) is playing an important role. However, ML has progressively obfuscated the role of linguistically-motivated inference rules, which should be the core of NLI systems. In this paper, we introduce distributed inference rules as a novel way to encode linguistically-motivated inference rules in learning interpretable NLI classifiers. We propose two encoders: the Distributed Partial Tree Encoder and the Distributed Smoothed Partial Tree Encoder. These encoders allow modeling syntactic and syntactic-semantic inference rules as distributed representations ready to be used in ML models over large datasets. Although far from the state-of-the-art of end-to-end deep learning systems on large datasets, our shallow networks positively exploit inference rules for NLI, improving over baseline systems. This is a first positive step towards interpretable and explainable end-to-end deep learning systems
Have you lost the thread? Discovering on-going conversations in scattered dialog blocks
No full textFinding threads in textual dialogs is emerging as a need to better organize stored knowledge. We capture this need
by introducing the novel task of discovering on-going conversations in scattered dialog blocks. Our aim in this paper is
twofold. First, we propose a publicly available testbed for the task by solving the insurmountable problem of privacy of Big
Personal Data. In fact, we showed that personal dialogs can be surrogated with theatrical plays. Second, we propose a suite
of computationally light learning models that can use syntactic and semantic features. With this suite, we showed that models
for this challenging task should include features capturing shifts in language use and, possibly, modeling underlying scripts
Distributed Smoothed Tree Kernel
Get PDFIn this paper we explore
the possibility to merge the world of
Compositional Distributional Semantic
Models (CDSM) with Tree Kernels
(TK). In particular, we will introduce a
specific tree kernel (smoothed tree kernel,
or STK) and then show that is
possibile to approximate such kernel
with the dot product of two vectors
obtained compositionally from the sentences,
creating in such a way a new
CDSM
Hexokinase 2 in Cancer: A Prima Donna Playing Multiple Characters
Get PDFHexokinases are a family of ubiquitous exose-phosphorylating enzymes that prime glucose for intracellular utilization. Hexokinase 2 (HK2) is the most active isozyme of the family, mainly expressed in insulin-sensitive tissues. HK2 induction in most neoplastic cells contributes to their metabolic rewiring towards aerobic glycolysis, and its genetic ablation inhibits malignant growth in mouse models. HK2 can dock to mitochondria, where it performs additional functions in autophagy regulation and cell death inhibition that are independent of its enzymatic activity. The recent definition of HK2 localization to contact points between mitochondria and endoplasmic reticulum called Mitochondria Associated Membranes (MAMs) has unveiled a novel HK2 role in regulating intracellular Ca2+ fluxes. Here, we propose that HK2 localization in MAMs of tumor cells is key in sustaining neoplastic progression, as it acts as an intersection node between metabolic and survival pathways. Disrupting these functions by targeting HK2 subcellular localization can constitute a promising anti-tumor strategy
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
- …
