Jonathan K. Kummerfeld

Learn More
Coreference resolution metrics quantify errors but do not analyze them. Here, we consider an automated method of categorizing errors in the output of a coreference system into intuitive underlying error types. Using this tool, we first compare the error distributions across a large set of systems, then analyze common errors across the top ten systems,(More)
Constituency parser performance is primarily interpreted through a single metric, F-score on WSJ section 23, that conveys no linguistic information regarding the remaining errors. We classify errors within a set of linguistically meaningful types using tree transformations that repair groups of errors together. We use this analysis to answer a range of(More)
Aspects of Chinese syntax result in a distinctive mix of parsing challenges. However , the contribution of individual sources of error to overall difficulty is not well understood. We conduct a comprehensive automatic analysis of error types made by Chinese parsers, covering a broad range of error types for large sets of sentences, enabling the first(More)
Our submission was a reduced version of the system described in Haghighi and Klein (2010), with extensions to improve mention detection to suit the OntoNotes annotation scheme. Including exact matching mention detection in this shared task added a new and challenging dimension to the problem, particularly for our system, which previously used a very(More)
Despite the convexity of structured max-margin objectives (Taskar et al., 2004; Tsochantaridis et al., 2004), the many ways to optimize them are not equally effective in practice. We compare a range of online optimization methods over a variety of structured NLP tasks (coreference, summarization, parsing, etc) and find several broad trends. First, margin(More)
We identify the pattern of microscopic dynamical relaxation for a two-dimensional glass-forming liquid. On short time scales, bursts of irreversible particle motion, called cage jumps, aggregate into clusters. On larger time scales, clusters aggregate both spatially and temporally into avalanches. This propagation of mobility takes place along the soft(More)
Because English is a low morphology language , current statistical parsers tend to ignore morphology and accept some level of redundancy. This paper investigates how costly such redundancy is for a lex-icalised grammar such as CCG. We use morphological analysis to split verb inflectional suffixes into separate tokens , so that they can receive their own(More)
We propose an improved, bottom-up method for converting CCG derivations into PTB-style phrase structure trees. In contrast with past work (Clark and Curran, 2009), which used simple transductions on category pairs, our approach uses richer transductions attached to single categories. Our conversion preserves more sentences under round-trip conversion (51.1%(More)
  • 1