Developing adaptable, extensible, and accurate task bots with minimal or zero human intervention is a significant challenge in dialog research. This thesis examines the obstacles and potential solutions for creating such bots, focusing on innovative techniques that enable bots to learn and adapt autonomously in constantly changing environments.
We use Lambek's pregroups and the framework of compositional distributional models of language ("DisCoCat") to study translations from Japanese to English as pairs of functors. Adding decorations to pregroups we show how to handle word order changes between languages.
The TransCoder system translates source code between Java, C++, and Python 3. The test set that was used to evaluate its quality is missing important features of Java, including the ability to define and use classes and the ability to call user-defined functions other than recursively. Therefore, the accuracy of TransCoder over programs with those features remains unknown.
Four packages in R are analyzed to carry out sentiment analysis. All packages allow to define custom dictionaries. Just one - Sentiment R - properly accounts for the presence of negators.
We critically review the smooth inverse frequency sentence embedding method of Arora, Liang, and Ma (2017), and show inconsistencies in its setup, derivation, and evaluation.
We propose a chatbot, namely Mocha to make good use of relevant entities when generating responses. Augmented with meta-path information, Mocha is able to mention proper entities following the conversation flow.
We consider the problem of recognizing mentions of human senses in text. Our contribution is a method for acquiring labeled data, and a learning method that is trained on this data. Experiments show the effectiveness of our proposed data labeling approach and our learning model on the task of sense recognition in text.
This is a preprint of the article "Identifying Phrasemes via Interlingual Association Measures" that was presented in February 2016 at the LeKo (Lexical combinations and typified speech in a multilingual context) conference in Innsbruck.
This paper proposes the use of dependent types for pragmatic phenomena such as pronoun binding and presupposition resolution as a type-theoretic alternative to formalisms such as Discourse Representation Theory and Dynamic Semantics.
A simple review by a linguist, citing many articles by physicists: Quantitative methods, agent-based computer simulations, language dynamics, language typology, historical linguistics
AbstractAIn2Cl9 (A = Cs, Rb, Ti, In) sowie Cs3In2Br9−x Clx (x = 7,8) kristallisieren isotyp mit Cs3Tl2Cl9. Die Kristallstruktur wurde an Einkristallen von Cs3In2Cl9 bis R = 0,039 verfeinert. Cs3In2Br9–xClx (x = 3, 6, 7) gehören dem Cs3Cr2Cl9‐Typ an; Cs3In2Br2Cl7 ist dimorph.
Phase transitions in (NH4, M)Cl with M=Tl, Rb or Cs and (ND4, Tl)Cl as well as (NH4, M)Br and (ND4, M)Br are measured using birefringence or differential thermal analysis. The phase diagrams of the mixed systems with M=Tl having decreasing lattice constant with increasing amount of Tl are similar to the well known T(P) diagrams. Therefore the diagrams of the systems with M=Rb or Cs having increasing lattice constants correspond to T(P) diagrams in the range of fictitious negative pressure P. Substitution of D for H produces an effect similar to reducing the lattice constant. The extraordinary large negative isotope effect of II-III transitions and the appearance of the birefringent phase III in the chlorides are now understood.
Local grammars can be represented in a very convenient way by automata. This paper describes and illustrates an efficient algorithm for the application of local grammars put in this form to lemmatized texts.