Mark Johnson

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)

Papers

1. A Language-agnostic Model of Child Language Acquisition (2024)
   The authors port Abend et al.'s semantic-bootstrapping learner from English to Hebrew. The learner sees one child-directed utterance at a time, paired with a logical form, and learns a CCG lexicon with EM over Dirichlet-process counts. The Hebrew data are from the CHILDES Hagar corpus (3,295 utterances), converted…
2. An Improved Non-monotonic Transition System for Dependency Parsing (2015)
   Greedy transition parsers usually commit to every attachment as soon as it is made, which traps them in garden paths.
3. A Non-Monotonic Arc-Eager Transition System for Dependency Parsing (2013)
   The paper relaxes the two deterministic constraints of the arc-eager transition system, which keep each step consistent with earlier head decisions.
4. 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…
5. 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.
6. 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…
7. Supersense Tagging of Unknown Nouns in WordNet (2003)
   The paper extends named-entity classification to common nouns. Each unknown noun is assigned one of 26 supersenses, the lexicographer classes that WordNet uses to organise its noun entries (person, location, event, quantity and so on). The classifier is an averaged multiclass perceptron over features from the context…

Co-authors (10)

• Eugene Charniak ×3
• David McClosky ×2
• Matthew Honnibal ×2
• Katherine Demuth
• Louis Mahon
• Mark Steedman
• Massimiliano Ciaramita
• Omri Abend
• Uri Berger
• Yoav Goldberg

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/authors/mark-johnson/