Paraphrastic language models and combination with neural network language models

In natural languages multiple word sequences can represent the same underlying meaning. Only modelling the observed surface word sequence can result in poor context coverage, for example, when using n-gram language models (LM). To handle this issue, paraphrastic LMs were proposed in previous research and successfully applied to a US English conversational telephone speech transcription task. In order to exploit the complementary characteristics of paraphrastic LMs and neural network LMs (NNLM), the combination between the two is investigated in this paper. To investigate paraphrastic LMs' generalization ability to other languages, experiments are conducted on a Mandarin Chinese broadcast speech transcription task. Using a paraphrastic multi-level LM modelling both word and phrase sequences, significant error rate reductions of 0.9% absolute (9% relative) and 0.5% absolute (5% relative) were obtained over the baseline n-gram and NNLM systems respectively, after a combination with word and phrase level NNLMs. © 2013 IEEE.

Automatic construction and natural-language description of nonparametric regression models

Copyright © 2014, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved. This paper presents the beginnings of an automatic statistician, focusing on regression problems. Our system explores an open-ended space of statistical models to discover a good explanation of a data set, and then produces a detailed report with figures and natural- language text. Our approach treats unknown regression functions non- parametrically using Gaussian processes, which has two important consequences. First, Gaussian processes can model functions in terms of high-level properties (e.g. smoothness, trends, periodicity, changepoints). Taken together with the compositional structure of our language of models this allows us to automatically describe functions in simple terms. Second, the use of flexible nonparametric models and a rich language for composing them in an open-ended manner also results in state- of-the-art extrapolation performance evaluated over 13 real time series data sets from various domains.

Unified form language: A domain-specific language for weak formulations of partial differential equations

We present the Unified Form Language (UFL), which is a domain-specific language for representing weak formulations of partial differential equations with a view to numerical approximation. Features of UFL include support for variational forms and functionals, automatic differentiation of forms and expressions, arbitrary function space hierarchies formultifield problems, general differential operators and flexible tensor algebra. With these features, UFL has been used to effortlessly express finite element methods for complex systems of partial differential equations in near-mathematical notation, resulting in compact, intuitive and readable programs. We present in this work the language and its construction. An implementation of UFL is freely available as an open-source software library. The library generates abstract syntax tree representations of variational problems, which are used by other software libraries to generate concrete low-level implementations. Some application examples are presented and libraries that support UFL are highlighted. © 2014 ACM.

Ni(Pt)-silicide contacts on CMOS devices: Impact of substrate nature and Pt concentration on the phase formation

Ni silicides used as contacts in source/drain and gate of advanced CMOS devices were analyzed by atom probe tomography (APT) at atomic scale. These measurements were performed on 45 nm nMOS after standard self-aligned silicide (salicide) process using Ni(5 at.% Pt) alloy. After the first annealing (RTA1), δ-Ni2Si was the only phase formed on gate and source/drain while, after the second annealing (RTA2), two different Ni silicides have been formed: NiSi on the gate and δ-Ni2Si on the source and drain. This difference between source/drain and gate regions in nMOS devices has been related to the Si substrate nature (poly or mono-crystalline) and to the size of the contact. In fact, NiSi seems to have difficulties to nucleate in the narrow source/drain contact on mono-crystalline Si. The results have been compared to analysis performed on 28 nm nMOS where the Pt concentration is higher (10 at.% Pt). In this case, θ-Ni2Si is the first phase to form after RTA1 and NiSi is then formed at the same time on source (or drain) and gate after RTA2. The absence of the formation of NiSi from δ-Ni 2Si/Si(1 0 0) interface compared to θ-Ni2Si/Si(1 0 0) interface could be related to the difference of the interface energies. The redistributions of As and Pt in different silicides and interfaces were measured and discussed. In particular, it has been evidenced that Pt redistributions obtained on both 45 and 28 nm MOS transistors correspond to respective Pt distributions measured on blanket wafers. © 2013 Elsevier B.V. All rights reserved.