Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 42 for “"Natural languages"”.
-
Joint multilingual learning for coreference resolution
Natural language is a pervasive human skill not yet fully achievable by automated computing systems. The main challenge is understanding how to computationally model both the depth and the breadth of natural languages. In this thesis, I present two probabilistic models that systematically model …
-
On the Optimality of the Lexicon
… pressure towards communicative efficiency shapes natural languages. In this thesis, we investigate the existence, the nature, and the impact of such a pressure in natural languages' lexicons. We investigate the existence of this pressure by (i) estimating what optimal word lengths would be using …
-
Anaphora Resolution Algorithms With Category: English and Korean
… which is one of the important phenomena that natural languages demonstrate.
-
An intelligent question: answering system for natural language
… be able to communicate with these systems in a natural way. Natural Language applications in the 1990s, as well as in the foreseeable future, have more demanding requirements. Current Natural Language Processing approaches alone have proven to be insufficient as they lack to obtain linguistic …
-
Language: what it's for and why we have it
… this thesis, I agree with the notion that human natural languages are underpinned by an innate faculty of language which predisposes us to acquire the structural aspects of language. Theories pertaining to its primary function, however, are lacking as they are either out of touch with the bigger …
-
Learning common sense knowledge from user interaction and principal component analysis
… with common sense knowledge in multiple natural languages, as part of the Open Mind Common Sense project. The knowledge that Open Mind collects from volunteer contributors is represented as a semantic network called ConceptNet. Using principal component analysis on the graph structure of …
-
Going Deeper with Images and Natural Language
… to interact with us about its surroundings in natural languages. Thanks to the progress made in deep learning, we've seen huge breakthroughs towards this goal over the last few years. The developments have been extremely rapid in visual recognition, in which machines now can categorize images …
-
A consideration of two attacks upon the sharp analytic-synthetic distinction
… methods can be used to explain analytically in natural languages. The two attacks are, in effect, attacks upon the conception of the analytic as being definitely different from the synthetic. Quine's attack is directed primarily at three of Carnap's basic concepts -- state-description, …
-
The Music of Language
Spoken languages are musical. Tonal languages from East Asia and Africa use pitch to convey meaning. Clicking languages from southern Africa use percussive consonants not found in other languages. Constructed languages such as whistled languages from the Canary Islands, and drumming and xylophone …
-
Truth in sentential structure: a critical analysis of standard semantic accounts of context sensitivity
… view that the formal properties of sentences of natural languages encode truth-conditions. The question I pursue is whether truth-conditional semantic theories are capable of accounting for the various ways in which contextual factors contribute to the determination of the truth-conditional …
-
Partitive Structures
Natural languages have various ways of referring to a part of an entity denoted by a nominal phrase. One of these ways is to use common nouns that are described as relational nouns denoting part-whole relations between two entities. There is another method, however, to express a part of the entity …
-
Data Driven Models for Language Evolution
Natural languages that originate from a common ancestor are genetically related, words are the core of any language and cognates are words sharing the same ancestor and etymology. Cognate identification, therefore, represents the foundation upon which the evolutionary history of languages may be …
-
Event quantification and plurality
… hypothesis that the domain of entities on which natural language interpretation relies includes a partially ordered sub-domain of events. In this sub-domain, we can identify singular and plural elements, the latter being characterizable as mereological sums having singular events as their minimal …
-
A computational model of quantification in natural language
Natural languages have various ways of expressing quantification, such as the English words "some" and "all." Different such words exist in different languages, and the same word can communicate quite different quantities depending on the context. This thesis presents a computational framework for …
-
Towards an explanatory division of competence and performance : a language-independent parsing scheme
… that there is a universal parsing model for natural languages. Such a model will apply, without change, cross-linguistically. The defense of this thesis proceeds by finding solutions to some apparently insurmountable problems which arise from the interaction of a set of basic and seemingly …
-
The Lexicon is Shaped for Incremental Processing in a Noisy Channel
… of evidence that the lexicons of the world’s languages are structured to be similar to abstract, maximally efficient communicative codes (e.g., Zipf 1935; Ferrer-i Cancho and Solé 2003; Piantadosi et al. 2009, 2011; Mahowald et al. 2018. In this dissertation, I will present additional evidence …
-
The semantics of the future
Natural languages use a number of different methods to refer to future eventualities: among them are futurates, as in (la), and futures, as in (lb) and (c). (1) a. The Red Sox (are) play(ing) the Yankees tomorrow. b. We'll change your oil in Madera. c. We're going to change your oil in Madera. This …
-
A corpus based approach to generalise a chatbot system
… programs which interact with users using natural languages. Most developers built their systems aiming to fool users that they are talking with real humans. Up to now most chatbots serve as a tool to amuse users through chatting with a robot. However, the knowledge bases of almost all …
-
On Impact of Network Architecture for Deep Learning
… a range of fields, including computer vision and natural language processing (NLP). Specific architectures are tailored to address particular tasks, and the selection of architecture can significantly affect the training process, model performance, and robustness. </p><p>In the field of NLP, we …
-
Transforming Free-Form Sentences into Sequence of Unambiguous Sentences with Large Language Model
In the realm of natural language programming, translating free-form sentences in natural language into a functional, machine-executable program remains difficult due to the following 4 challenges. First, the inherent ambiguity of natural languages. Second, the high-level verbose nature in user …
Page 1 of 3