Nicolas Nicolov

Natural Language Assistant: A Dialog System for Online Product Recommendation

With the emergence of electronic-commerce systems, successful information access on electroniccommerce web sites becomes essential. Menu-driven navigation and keyword search currently provided by most commercial sites have considerable limitations because they tend to overwhelm and frustrate users with lengthy, rigid, and ineffective interactions. To provide an efficient solution for information access, we have built the NATURAL language ASSISTANT (NLA), a web-based natural language dialog system to help users find relevant products on electronic-commerce sites. The system brings together technologies in natural language processing and human-computer interaction to create a faster and more intuitive way of interacting with web sites. By combining statistical parsing techniques with traditional AI rule-based technology, we have created a dialog system that accommodates both customer needs and business requirements. The system is currently embedded in an application for recommending laptops and was deployed as a pilot on IBMs web site.

Natural language dialogue for personalized interaction

T he pragmatic goal of natural language (NL) and multimodal interfaces (speech recognition, keyboard entry, pointing, among others) is to enable ease-of-use for users/customers in performing more sophisticated human-computer interactions (HCI). NL research attempts to define extensive discourse models that in turn provide improved models of context-enabling HCI and personalization. Customers have the initiative to Technologies that successfully recognize and react to spoken or typed words are key to true personalization. Front-and back-end systems must respond in accord, and one solution may be found somewhere in the middle(ware).

Weblog Classification for Fast Splog Filtering: A URL Language Model Segmentation Approach

This paper shows that in the context of statistical weblog classification for splog filtering based on n-grams of tokens in the URL, further segmenting the URLs beyond the standard punctuation is helpful. Many splog URLs contain phrases in which the words are glued together in order to avoid splog filtering techniques based on punctuation segmentation and unigrams. A technique which segments long tokens into the words forming the phrase is proposed and evaluated. The resulting tokens are used as features for a weblog classifier whose accuracy is similar to that of humans (78% vs. 76%) and reaches 93.3% of precision in identifying splogs with recall of 50.9%.

Identifying and tracking entity mentions in a maximum entropy framework

We present a system for identifying and tracking named, nominal, and pronominal mentions of entities within a text document. Our maximum entropy model for mention detection combines two pre-existing named entity taggers (built to extract different entity categories) and other syntactic and morphological feature streams to achieve competitive performance. We developed a novel maximum entropy model for tracking all mentions of an entity within a document. We participated in the Automatic Content Extraction (ACE) evaluation and performed well. We describe our system and present results of the ACE evaluation.

Generating full paraphrases of fragments in a dialogue interpretation system

Using SHARDS -- a semantically-based HPSG approach to the resolution of dialogue fragments -- we will show how to generate full para-phrases for fragments in dialogue. We adopt a template-filler approach that does not require deep generation from an underlying semantic representation. Instead it reuses the results of the parse and interpretation process to dynamically compute templates and to update fillers as the dialogue proceeds. This recycling of already available syntactic and phonological information makes generation efficient, as it reduces the operations of the generator to mere string manipulations.

A conversational interface for online shopping

We present a deployed, conversational dialog system that assists users in finding computers based on their usage patterns and constraints on specifications. We discuss findings from a market survey and two user studies. We compared our system to a directed dialog system and a menu driven navigation system. We found that the conversational interface reduced the average number of clicks by 63% and the average interaction time by 33% over a menu driven search system. The focus of our continuing work includes developing a dynamic, adaptive dialog management strategy, robustly handling user input and improving the user interface.

Conversational sales assistant for online shopping

Websites of businesses should accommodate both customer needs and business requirements. Traditional menu-driven navigation and key word search do not allow users to describe their intentions precisely. We have developed a conversational interface to online shopping that provides convenient, personalized access to information using natural language dialog. User studies show significantly reduced length of interactions in terms of time and number of clicks in finding products. The core dialog engine is easily adaptable to other domains.

Full Paraphrase Generation for Fragments in Dialogue

Much previous work on generation has focused on the general problem of producing lexical strings from abstract semantic representations. We consider generation in the context of a particular task, creating full sentential paraphrases of fragments in dialogue. When the syntactic, semantic and phonological information provided by a dialogue fragment resolution system is made accessible to a generation component, much of the indeterminacy of lexical selection is eliminated.

AAAI 2006 Spring Symposium Reports

The Association for the Advancement of Artificial Intelligence, in cooperation with Stanford Universitys Computer Science Department, was pleased to present its 2006 Spring Symposium Series held March 27-29, 2006, at Stanford University, California. The titles of the eight symposia were (1) Argumentation for Consumers of Health Care (chaired by Nancy Green); (2) Between a Rock and a Hard Place: Cognitive Science Principles Meet AI Hard Problems (chaired by Christian Lebiere); (3) Computational Approaches to Analyzing Weblogs (chaired by Nicolas Nicolov); (4) Distributed Plan and Schedule Management (chaired by Ed Durfee); (5) Formalizing and Compiling Background Knowledge and Its Applications to Knowledge Representation and Question Answering (chaired by Chitta Baral); (6) Semantic Web Meets e-Government (chaired by Ljiljana Stojanovic); (7) To Boldly Go Where No Human-Robot Team Has Gone Before (chaired by Terry Fong); and (8) What Went Wrong and Why: Lessons from AI Research and Applications (chaired by Dan Shapiro).