Jimmy J. Lin. 2001. Indexing and retrieving natural language using ternary expressions. Master's thesis, MIT. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Anaphora Resolution for Question Answering - Castagnola (Correct)
....language systems like START at the other. They are linguistically informed search engines, which attempt to use natural language tools to aid the retrieval of information in order to return a smaller amount of irrelevant information than traditional search engines. One of these systems, Sapere [22], indexes relations between words to allow it http: www.ai.mit.edu projects infolab http: www.altavista.com, http: www.google.com 9 to search for information in a smart way. By storing relations like Subject VerbObject, it can distinguish between cases that the simple bag of words ....
Jimmy J. Lin. Indexing and Retrieving Natural Language Using Ternary Expressions. Master of Engineering, Massachusetts Institute of Technology, 2001.
Extracting Paraphrases from Aligned Corpora - Ibrahim (2002) (Correct)
....time correctly parsing sentence fragments, quotes, and long sentences from general domain corpora. Finally, it is not currently computationally feasible to parse large corpora. Naturally there are many systems that try to fall between word based approaches and full syntactic parsing. Sapere [13] developed by Jimmy Lin at MIT uses Minipar[10] to produce dependency trees for sentences and then uses rules to extract simple semantic relationships such as possessive relations, subject verb relations, verb object relations, adjectivenoun relations, and adverb verb relations. Relations are ....
....at possible applications of paraphrases in natural language systems. Barzilay [3] uses paraphrases in multiple document summarization. Since the paraphrases are based on link relations, it is natural to examine the application of synonym phrases in an information retrieval system such as Sapere [13]. Sapere is an ideal information retrieval tool to test this system s paraphrases on because the paraphrases are based on link relations and thus can be indexed within 43 Sapere s relational framework. A simple experiment would be to expand a query with all the matching paraphrases and measure ....
Jimmy J. Lin. Indexing and retrieving natural language using ternanry expressions. Master's thesis, Massachussetts Institute of Technology, 2001.
Start and Beyond - Katz, Lin (2002) Self-citation (Lin) (Correct)
....relations and retrieving responses based on them can dramatically increase the performance of a question answering system. To this end, we have developed Sapere, a prototype question answering system based on matching syntactic relations derived from the question with those derived from the corpus [10, 17]. These relations are simplified versions of Start s ternary expressions, but can be generated automatically and indexed on a large scale. To e#ectively use relations for question answering, we still need to address a critical question: exactly what types of relations are beneficial to question ....
Jimmy J. Lin. Indexing and retrieving natural language using ternary expressions. Master's thesis, Massachusetts Institute of Technology, 2001.
Towards Semantic-Based Overlap Measures for Question Answering - Molla (2003) (Correct)
No context found.
Jimmy J. Lin. 2001. Indexing and retrieving natural language using ternary expressions. Master's thesis, MIT.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC