Ralph Weischedel
Biographic Data
| ID | 6536337 |
|---|---|
| NAME | Ralph Weischedel |
| GIVEN NAMES | Ralph |
| FAMILY NAME | Weischedel |
| SIGNATURE | WEISCHEDEL R |
| AFFILIATIONS | University of Pennsylvania |
| VERIFIED | No |
| TOTAL WORKS | 3 |
| TOTAL CITATIONS | 5 |
| AUTHOR COUNT | 3 |
| EDITOR COUNT | 0 |
| FIRST PUBLICATION YEAR | 1973 |
| LATEST PUBLICATION YEAR | 2018 |
| H-INDEX | 1 |
What Can Be Accomplished with the State of the Art in Information Extraction? A Personal View
Though information extraction (IE) research has more than a 25-year history, F 1 scores remain low. Thus, one could question continued investment in IE research. In this article, we present three applications where information extraction of entities, relations, and/or events has been used, and note the common features that seem to have led to success. We also identify key research challenges whose solution seems essential for broader successes. B…
String-to-Dependency Statistical Machine Translation
We propose a novel string-to-dependency algorithm for statistical machine translation. This algorithm employs a target dependency language model during decoding to exploit long distance word relations, which cannot be modeled with a traditional n-gram language model. Experiments show that the algorithm achieves significant improvement in MT performance over a state-of-the-art hierarchical string-to-string system on NIST MT06 and MT08 newswire eva…
Optimal Network Problem: A Branch-and-Bound Algorithm
The problem of selecting a subset of links so as to minimize the sum of shortest path distances between all pairs of nodes, subject to a budget constraint on total length of links, may be solved by a modification of a branch-and-bound algorithm developed for optimal variable selection problems in statistics. The modified algorithm is described in detail, and encouraging computational experience on 10 node networks is reported. The use of the algo…
Optimal Network Problem: A Branch-and-Bound Algorithm
The problem of selecting a subset of links so as to minimize the sum of shortest path distances between all pairs of nodes, subject to a budget constraint on total length of links, may be solved by a modification of a branch-and-bound algorithm developed for optimal variable selection problems in statistics. The modified algorithm is described in detail, and encouraging computational experience on 10 node networks is reported. The use of the algo…
String-to-Dependency Statistical Machine Translation
We propose a novel string-to-dependency algorithm for statistical machine translation. This algorithm employs a target dependency language model during decoding to exploit long distance word relations, which cannot be modeled with a traditional n-gram language model. Experiments show that the algorithm achieves significant improvement in MT performance over a state-of-the-art hierarchical string-to-string system on NIST MT06 and MT08 newswire eva…
Optimal Network Problem: A Branch-and-Bound Algorithm
The problem of selecting a subset of links so as to minimize the sum of shortest path distances between all pairs of nodes, subject to a budget constraint on total length of links, may be solved by a modification of a branch-and-bound algorithm developed for optimal variable selection problems in statistics. The modified algorithm is described in detail, and encouraging computational experience on 10 node networks is reported. The use of the algo…
String-to-Dependency Statistical Machine Translation
We propose a novel string-to-dependency algorithm for statistical machine translation. This algorithm employs a target dependency language model during decoding to exploit long distance word relations, which cannot be modeled with a traditional n-gram language model. Experiments show that the algorithm achieves significant improvement in MT performance over a state-of-the-art hierarchical string-to-string system on NIST MT06 and MT08 newswire eva…
What Can Be Accomplished with the State of the Art in Information Extraction? A Personal View
Though information extraction (IE) research has more than a 25-year history, F 1 scores remain low. Thus, one could question continued investment in IE research. In this article, we present three applications where information extraction of entities, relations, and/or events has been used, and note the common features that seem to have led to success. We also identify key research challenges whose solution seems essential for broader successes. B…
Computer Science (3 works) · Algorithm (2 works) · Artificial Intelligence (2 works) · Mathematics (2 works) · Theoretical Computer Science (2 works) · Advanced Database Systems and Queries (1 works) · Algorithms and Data Compression (1 works) · Branch and bound (1 works) · Branch and cut (1 works) · Budget constraint (1 works)