Elamur Research⌕
☰
home / authors / Jenny Rose Finkel

Jenny Rose Finkel

Jenny Rose Finkel works on statistical methods for extracting structure from text: named entities, coreference chains and syntactic trees. A recurring thread in the papers here is how to move beyond strictly local models, letting a system use evidence from elsewhere in the document or impose global consistency on its predictions. The work belongs to named entity recognition, information extraction and coreference resolution.

The most cited paper here describes the Stanford CoreNLP toolkit (2014), which joins tokenisers, taggers, parsers and other analysers into one pipeline that is easy to call from Java. An earlier paper, Incorporating Non-local Information into Information Extraction Systems by Gibbs Sampling (2005), replaced exact Viterbi decoding with sampling and annealing so that a tagger could enforce long-distance regularities, such as giving a repeated name the same label throughout a document.

Work from 2008 and 2009 brought parsing ideas into extraction. Nested Named Entity Recognition (2009) treated entities inside other entities as phrases in a shallow tree and recovered them with a parser. Efficient, Feature-based, Conditional Random Field Parsing (2008) scored each grammar rule with rich overlapping features in a discriminative model, and Enforcing Transitivity in Coreference Resolution (2008) used integer linear programming to keep pairwise coreference decisions consistent.

The papers here come from Stanford University. The main collaborator is Christopher D. Manning, and co-authors also include Mihai Surdeanu, Steven Bethard and John Bauer.

Jenny Rose Finkel has 5 papers in our library, in 2005–2014, most of them on Named entity recognition, Coreference resolution, Information extraction; often with Christopher D. Manning, David McClosky, John Bauer.

5 papers in our library · 2005–2014

current affiliationProteogenomics Research Institute for Systems Medicine, San Diego, United States; Prism Clinical Research, Saint Paul, United States; Stanford University, Stanford, United States

OpenAlex · h-index 14 · 33 works · 11 537 citations OpenAlex, 2026-10-14

5 works in our library · 2 491 citations in our library · 1 more work in our library · ⭐ Paper Star rank #131

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

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

Affiliations

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

Topics

Named entity recognition1Coreference resolution1Information extraction1

Works by year

2010s

20141 paper

2000s

20091 paper20082 papers20051 paper

Papers

The most cited first (OpenAlex and our library).

  1. The Stanford CoreNLP Natural Language Processing Toolkit (2014 · 8 620 citations)
    Combining NLP components that each expose their own API usually requires fragile custom glue code. Large frameworks such as UIMA or GATE avoid that, but users have to learn the framework before they can analyse any text. This system-demonstration paper presents Stanford CoreNLP, a JVM-based toolkit that chains…
  2. Incorporating Non-local Information into Information Extraction Systems by Gibbs Sampling (2005 · 3 618 citations)
    HMMs, CMMs and CRFs, among other sequence models, depend on the Markov property to keep Viterbi decoding exact and inexpensive.
  3. Nested Named Entity Recognition (2009 · 403 citations)
    Standard NER systems assume entities never overlap, so they miss entities embedded inside others, such as a location within an organization name or a protein inside a DNA mention.
  4. Efficient, Feature-based, Conditional Random Field Parsing (2008 · 261 citations)
    Constituency parsing in 2008 was still dominated by generative PCFG-style models. Earlier discriminative parsers that used dynamic programming either trained only on very short sentences or used no features at all. This paper presents a CRF-based parser (CRF-CFG) that scores each rule application with arbitrary…
  5. Enforcing Transitivity in Coreference Resolution (2008 · 128 citations)
    Pairwise coreference classifiers judge each pair of mentions separately. They then merge links after the fact, which can yield implausible chains. For example, "John Smith" and "Jane Smith" may end up in one entity only because each is linked to "Smith". Finkel and Manning argue that earlier ILP-based coreference…

Also in our library

1 more work of theirs is in our library without a page here yet; it will appear as we publish them.

Co-authors here

5 co-authors with a page, the most papers together first.

Cited by

Papers of our library cite their works 2 491 times (of the 140 884 papers whose bibliographies we read); 243 citing papers with a page here →.

This page in Markdown → https://md.research.elamur.ai/free/en/authors/jenny-rose-finkel/