The present thesis investigates in how properties of a reader’s first language (L1) have an influence on syntactic processing in a second language (L2). While the Competition Model (Bates & MacWhinney, 1982, 1987, 1989, MacWhinney, 1997) predicts that syntactic properties of the L1 can have an influence on L2 processing, the Shallow-Structure Account (Clahsen & Felser, 2006) suggests that an L2 speaker’s representation of an L2 sentence is shallower, lacks syntactic detail, and is therefore not detailed enough for properties of the L1 to have an influence on L2 processing (Papadopoulou & Clahsen, 2003). In two sets of studies, I investigate whether L2 speakers of English activate syntactic information from their L1 while processing English sentences. In Experiments 1-4, native speakers of German, and control groups of native speakers of French and English, are confronted with English sentences consisting of a word order which exists in both English and German, but which represents different underlying syntactic structures in both languages. Results suggest that native speakers of German activate syntactic information from their L1 while reading such sentences. Experiments 5-7 represent an attempt to address both the issue of L1 influence and the issue of shallow processing within the context of the same experimental design. Native speakers of German, and a control group of native English speakers, read grammatically incorrect English sentences with a word order which would either be grammatically correct in German, or grammatically incorrect in both English and German. In this set of experiments, we found evidence against an influence of syntactic properties of the L1. Results also suggest that contrary to the predictions of the shallow-structure account, L2 speakers fully parse the syntactic structure of an L2 sentence, and compute detailed syntactic representations.

Nothing seems more obvious than that our words have meaning. When people speak to each other, they exchange information through the use of a particular set of words. The words they say to each other, moreover, are about something. Yet this relation of “aboutness,” known as “reference,” is not quite as simple as it appears. In this thesis I will present two opposing arguments about the nature of our words and how they relate to the things around us. First, I will present Hilary Putnam’s argument, in which he examines the indeterminacy of reference, forcing us to conclude that we must abandon metaphysical realism. While Putnam considers his argument to be a refutation of non-epistemicism, David Lewis takes it to be a reductio, claiming Putnam’s conclusion is incredible. I will present Lewis’s response to Putnam, in which he accepts the challenge of demonstrating how Putnam’s argument fails and rescuing us from the abandonment of realism. In order to explain the determinacy of reference, Lewis introduces the concept of “natural properties.” In the final chapter of this thesis, I will propose another use for Lewisian properties. Namely, that of helping to minimize the gap between natural language processing and human communication.

This project details the development of a novel and practical framework for the development of conversation agents (CAs), or conversation robots. CAs, are software programs which can be used to provide a natural interface between human and computers. In this study, ‘conversation’ refers to real-time dialogue exchange between human and machine which may range from web chatting to “on-the-go” conversation through mobile devices. In essence, the project proposes a “smart and effective” communication technology where an autonomous agent is able to carry out simulated human conversation via multiple channels. The CA developed in this project is termed “Artificial Intelligence Natural-language Identity” (AINI) and AINI is used to illustrate the implementation and testing carried out in this project. Up to now, most CAs have been developed with a short term objective to serve as tools to convince users that they are talking with real humans as in the case of the Turing Test. The traditional designs have mainly relied on ad-hoc approach and hand-crafted domain knowledge. Such approaches make it difficult for a fully integrated system to be developed and modified for other domain applications and tasks. The proposed framework in this thesis addresses such limitations. Overcoming the weaknesses of previous systems have been the key challenges in this study. The research in this study has provided a better understanding of the system requirements and the development of a systematic approach for the construction of intelligent CAs based on agent architecture using a modular N-tiered approach. This study demonstrates an effective implementation and exploration of the new paradigm of Computer Mediated Conversation (CMC) through CAs. The most significant aspect of the proposed framework is its ability to re-use and encapsulate expertise such as domain knowledge, natural language query and human-computer interface through plug-in components. As a result, the developer does not need to change the framework implementation for different applications. This proposed system provides interoperability among heterogeneous systems and it has the flexibility to be adapted for other languages, interface designs and domain applications. A modular design of knowledge representation facilitates the creation of the CA knowledge bases. This enables easier integration of open-domain and domain-specific knowledge with the ability to provide answers for broader queries. In order to build the knowledge base for the CAs, this study has also proposed a mechanism to gather information from commonsense collaborative knowledge and online web documents. The proposed Automated Knowledge Extraction Agent (AKEA) has been used for the extraction of unstructured knowledge from the Web. On the other hand, it is also realised that it is important to establish the trustworthiness of the sources of information. This thesis introduces a Web Knowledge Trust Model (WKTM) to establish the trustworthiness of the sources. In order to assess the proposed framework, relevant tools and application modules have been developed and an evaluation of their effectiveness has been carried out to validate the performance and accuracy of the system. Both laboratory and public experiments with online users in real-time have been carried out. The results have shown that the proposed system is effective. In addition, it has been demonstrated that the CA could be implemented on the Web, mobile services and Instant Messaging (IM). In the real-time human-machine conversation experiment, it was shown that AINI is able to carry out conversations with human users by providing spontaneous interaction in an unconstrained setting. The study observed that AINI and humans share common properties in linguistic features and paralinguistic cues. These human-computer interactions have been analysed and contributed to the understanding of how the users interact with CAs. Such knowledge is also useful for the development of conversation systems utilising the commonalities found in these interactions. While AINI is found having difficulties in responding to some forms of paralinguistic cues, this could lead to research directions for further work to improve the CA performance in the future.

Thesis (B.A.)--Haverford College, Dept. of Computer Science, Swarthmore College. Dept. of Linguistics, 2007. / Includes bibliographical references.

<p>Information retrieval has been a prevasive part of human society since its existence.With the advent of internet and World wide Web it became an extensive area of researchand major foucs, which lead to development of various search engines to locate the de-sired information, mostly for globally connected computer networks viz. internet.Butthere is another major part of computer network viz. intranet, which has not seen muchof advancement in information retrieval approaches, in spite of being a major source ofinformation within a large number of organizations.Most common technique for intranet based search engines is still mere database-centric. Thus practically intranets are unable to avail the benefits of sophisticated tech-niques that have been developed for internet based search engines without exposing thedata to commercial search engines.In this Master level thesis we propose a ”state of the art architecture” for an advancedsearch engine for intranet which is capable of dealing with continuously growing sizeof intranets knowledge base. This search engine employs lexical processing of doc-umetns,where documents are indexed and searched based on standalone terms or key-words, along with the semantic processing of the documents where the context of thewords and the relationship among them is given more importance.Combining lexical and semantic processing of the documents give an effective ap-proach to handle navigational queries along with research queries, opposite to the modernsearch engines which either uses lexical processing or semantic processing (or one as themajor) of the documents. We give equal importance to both the approaches in our design,considering best of the both world.This work also takes into account various widely acclaimed concepts like inferencerules, ontologies and active feedback from the user community to continuously enhanceand improve the quality of search results along with the possibility to infer and deducenew knowledge from the existing one, while preparing for the advent of semantic web.</p>

This article summarizes and extends recent results linking deterministic parsing to observed "locality principles" in syntax. It also argues that grammatical theories based on explicit phrase structure rules are unlikely to provide comparable explanations of why natural languages are built the way they are.

Thesis (Ph.D.)--University of Delaware, 2006. / Principal faculty advisors: Kathleen F. McCoy and Vijay K. Shanker, Computer & Information Sciences. Includes bibliographical references.

In this thesis we use a knowledge-based approach to disambiguating prepositional phrase attachments in English sentences. This method was first introduced by S. M. Harabagiu. The Penn Treebank corpus is used as the training text. We extract 4-tuples of the form <em>VP</em>, <em>NP</em>₁, Prep, <em>NP</em>₂ and sort them into classes according to the semantic relationships between parts of each tuple. These relationships are extracted from WordNet. Classes are sorted into different tiers based on the strictness of their semantic relationship. Disambiguation of prepositional phrase attachments can be cast as a constraint satisfaction problem, where the tiers of extracted classes act as the constraints. Satisfaction is achieved when the strictest possible tier unanimously indicates one kind of attachment. The most challenging kind of problems for disambiguation of prepositional phrases are ones where the prepositional phrase may attach to either the closest verb or noun. <br /><br /> We first demonstrate that the best approach to extracting tuples from parsed texts is a top-down postorder traversal algorithm. Following that, the various challenges in forming the prepositional classes utilizing WordNet semantic relations are described. We then discuss the actions that need to be taken towards applying the prepositional classes to the disambiguation task. A novel application of this method is also discussed, by which the tuples to be disambiguated are also expanded via WordNet, thus introducing a client-side application of the algorithms utilized to build prepositional classes. Finally, we present results of different variants of our disambiguating algorithm, contrasting the precision and recall of various combinations of constraints, and comparing our algorithm to a baseline method that falls back to attaching a prepositional phrase to the closest left phrase. Our conclusion is that our algorithm provides improved performance compared to the baseline and is therefore a useful new method of performing knowledge-based disambiguation of prepositional phrase attachments.

Information retrieval has been a prevasive part of human society since its existence.With the advent of internet and World wide Web it became an extensive area of researchand major foucs, which lead to development of various search engines to locate the de-sired information, mostly for globally connected computer networks viz. internet.Butthere is another major part of computer network viz. intranet, which has not seen muchof advancement in information retrieval approaches, in spite of being a major source ofinformation within a large number of organizations.Most common technique for intranet based search engines is still mere database-centric. Thus practically intranets are unable to avail the benefits of sophisticated tech-niques that have been developed for internet based search engines without exposing thedata to commercial search engines.In this Master level thesis we propose a ”state of the art architecture” for an advancedsearch engine for intranet which is capable of dealing with continuously growing sizeof intranets knowledge base. This search engine employs lexical processing of doc-umetns,where documents are indexed and searched based on standalone terms or key-words, along with the semantic processing of the documents where the context of thewords and the relationship among them is given more importance.Combining lexical and semantic processing of the documents give an effective ap-proach to handle navigational queries along with research queries, opposite to the modernsearch engines which either uses lexical processing or semantic processing (or one as themajor) of the documents. We give equal importance to both the approaches in our design,considering best of the both world.This work also takes into account various widely acclaimed concepts like inferencerules, ontologies and active feedback from the user community to continuously enhanceand improve the quality of search results along with the possibility to infer and deducenew knowledge from the existing one, while preparing for the advent of semantic web.

In this thesis we use a knowledge-based approach to disambiguating prepositional phrase attachments in English sentences. This method was first introduced by S. M. Harabagiu. The Penn Treebank corpus is used as the training text. We extract 4-tuples of the form <em>VP</em>, <em>NP</em>₁, Prep, <em>NP</em>₂ and sort them into classes according to the semantic relationships between parts of each tuple. These relationships are extracted from WordNet. Classes are sorted into different tiers based on the strictness of their semantic relationship. Disambiguation of prepositional phrase attachments can be cast as a constraint satisfaction problem, where the tiers of extracted classes act as the constraints. Satisfaction is achieved when the strictest possible tier unanimously indicates one kind of attachment. The most challenging kind of problems for disambiguation of prepositional phrases are ones where the prepositional phrase may attach to either the closest verb or noun. <br /><br /> We first demonstrate that the best approach to extracting tuples from parsed texts is a top-down postorder traversal algorithm. Following that, the various challenges in forming the prepositional classes utilizing WordNet semantic relations are described. We then discuss the actions that need to be taken towards applying the prepositional classes to the disambiguation task. A novel application of this method is also discussed, by which the tuples to be disambiguated are also expanded via WordNet, thus introducing a client-side application of the algorithms utilized to build prepositional classes. Finally, we present results of different variants of our disambiguating algorithm, contrasting the precision and recall of various combinations of constraints, and comparing our algorithm to a baseline method that falls back to attaching a prepositional phrase to the closest left phrase. Our conclusion is that our algorithm provides improved performance compared to the baseline and is therefore a useful new method of performing knowledge-based disambiguation of prepositional phrase attachments.