Výsledky vyhledávání

Report

Looking Under the Hood : Tools for Diagnosing your Question Answering Engine

Autor: Breck, Eric, Light, Marc, Mann, Gideon S., Riloff, Ellen, Anand, Brianne Brown Pranav, Rooth, Mats, Thelen, Michael

In this paper we analyze two question answering tasks : the TREC-8 question answering task and a set of reading comprehension exams. First, we show that Q/A systems perform better when there are multiple answer opportunities per question. Next, we an

Externí odkaz: http://arxiv.org/abs/cs/0107006

Zobrazit plný text záznamu

Report

How to Evaluate your Question Answering System Every Day and Still Get Real Work Done

Autor: Breck, Eric, Burger, John D., Ferro, Lisa, Hirschman, Lynette, House, David, Light, Marc, Mani, Inderjeet

In this paper, we report on Qaviar, an experimental automated evaluation system for question answering applications. The goal of our research was to find an automatically calculated measure that correlates well with human judges' assessment of answer

Externí odkaz: http://arxiv.org/abs/cs/0004008

Zobrazit plný text záznamu

Report

Morphological Cues for Lexical Semantics

Autor: Light, Marc

Publikováno v: Proceedings of the 34th Meeting of the Association for Computational Linguistics (ACL'96)

Most natural language processing tasks require lexical semantic information. Automated acquisition of this information would thus increase the robustness and portability of NLP systems. This paper describes an acquisition method which makes use of fi

Externí odkaz: http://arxiv.org/abs/cmp-lg/9606003

Zobrazit plný text záznamu

Report

Classification in Feature-based Default Inheritance Hierarchies

Autor: Light, Marc

Publikováno v: Proceedings of KONVENS-94

Increasingly, inheritance hierarchies are being used to reduce redundancy in natural language processing lexicons. Systems that utilize inheritance hierarchies need to be able to insert words under the optimal set of classes in these hierarchies. In

Externí odkaz: http://arxiv.org/abs/cmp-lg/9606004

Zobrazit plný text záznamu

Report

Knowledge Representation for Lexical Semantics: Is Standard First Order Logic Enough?

Autor: Light, Marc, Schubert, Lenhart

Natural language understanding applications such as interactive planning and face-to-face translation require extensive inferencing. Many of these inferences are based on the meaning of particular open class words. Providing a representation that can

Externí odkaz: http://arxiv.org/abs/cmp-lg/9412004

Zobrazit plný text záznamu