Eugene Charniak

4 paper cards in Mova's library · 2004–2006

Eugene Charniak wrote 4 of the papers Mova reads, in 2004–2006, most of them on Dependency parsing, Treebanks; often with Mark Johnson, David McClosky, Eric K. Ringger.

The profile is the library's match of the name; two people with one name are not always told apart.

Ideas Mova took (1)

From the ideas ledger: an idea tried, kept or queued, or measured with no gain, and what it gave.

kept — Oracle gap from en beam-curve: report the oracle LAS of the beam against the 1-best LAS at beam sizes 1, 2, 4, 8 and 16 on EWT dev; a large gap, as the paper shows for 50-best, says a reranker has room to help. (Coarse-to-Fine n-Best Parsing and MaxEnt Discriminative… · beam oracle EWT dev our tags: width 1/2/4/8/16 1-best 75.27/78.12/78.83/79.39/79.24, oracle 75.27/79.67/82.20/84.14/85.52 (gap 4.74 at 8); commit 3ba5388e8)

Effective Self-Training for Parsing (2006)
Self-training of parsers was thought to fail because the parser's own errors are amplified. This paper shows that it works when the self-labelled trees come from a two-stage parser and reranker: the 50-best parses of 24 million unlabelled News sentences are reranked, and the reranker's best tree is added to the Wall…
Reranking and Self-Training for Parser Adaptation (2006)
Parsers trained on the Wall Street Journal lose much accuracy on other genres: the standard parser scores 89.7% on WSJ but only 82.9% on the Brown corpus.
Coarse-to-Fine n-Best Parsing and MaxEnt Discriminative Reranking (2005) 1 idea kept
A discriminative reranker needs a good list of candidate parses for each sentence. The authors produce 50-best lists with a coarse-to-fine generative parser: a coarse pass prunes the chart, and a finer pass scores the surviving parses, which gives lists of much higher quality than the usual n-best output. A MaxEnt…
Using the Penn Treebank to Evaluate Non-Treebank Parsers (2004)
The question is how to compare a parser that was never trained on the Penn Treebank (NLPWin, built at Microsoft Research) with Treebank-trained parsers such as Charniak's, when the two attach modifiers in a different order and use different brackets.