Filter Results:
- Full text PDF available (22)
Publication Year
2008
2018
- This year (7)
- Last 5 years (14)
- Last 10 years (24)
Publication Type
Co-author
Journals and Conferences
Data Set Used
Learn More
- Jonathan K. Kummerfeld, David Leo Wright Hall, James R. Curran, Dan Klein
- EMNLP-CoNLL
- 2012
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… (More)
- Jonathan K. Kummerfeld, Dan Klein
- EMNLP
- 2013
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… (More)
- Rebecca S. Portnoff, Sadia Afroz, +5 authors Vern Paxson
- WWW
- 2017
Underground forums are widely used by criminals to buy and sell a host of stolen items, datasets, resources, and criminal services. These forums contain important resources for understanding… (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… (More)
We propose a novel self-training method for a parser which uses a lexicalised grammar and supertagger, focusing on increasing the speed of the parser rather than its accuracy. The idea is to train… (More)
- Stephen Clark, Ann Copestake, +8 authors Tim Dawborn
- 2009
Scalable syntactic processing will underpin the sophisticated language technology needed for next generation information access. Companies are already using nlp tools to create web-scale question… (More)
- Jonathan K. Kummerfeld, James R. Curran
- ALTA
- 2008
Manually maintaining comprehensive databases of multi-word expressions, for example Verb-Particle Constructions (VPCs), is infeasible. We describe a new type level classifier for potential VPCs,… (More)
Linguistically diverse datasets are critical for training and evaluating robust machine learning systems, but data collection is a costly process that often requires experts. Crowdsourcing the… (More)
- Laura Wendlandt, Jonathan K. Kummerfeld, Rada Mihalcea
- NAACL-HLT
- 2018
Despite the recent popularity of word embedding methods, there is only a small body of work exploring the limitations of these representations. In this paper, we consider one aspect of embedding… (More)
- Catherine Finegan-Dollak, Jonathan K. Kummerfeld, +4 authors Dragomir R. Radev
- ACL
- 2018
New resources to make these evaluations easier • New Advising dataset, plus 7 existing-text-to-SQL datasets cleaned, variablized, and put into a single, standard format, with tools for easy use. •… (More)