--- title: "Wayne Ward — author profile and papers" description: "Wayne Ward: 2 papers on Elamur Research (2004–2008), h-index 34 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/wayne-ward/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/wayne-ward/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Wayne Ward # Wayne Ward Wayne Ward works on semantic role labeling, also called shallow semantic parsing. The task is to find, for each verb in a sentence, the phrases that act as its arguments and to tag them with PropBank roles. In the papers here, Ward treats this as classification over the constituents of a syntactic parse. The method uses support vector machines with structural and lexical features, trained on PropBank annotations of Wall Street Journal text. Two questions recur: which features help the labeler, and how well such systems hold up on text unlike their training material. The most cited of these papers is [Shallow Semantic Parsing using Support Vector Machines](https://md.research.elamur.ai/free/en/papers/pradhan-2004-shallow-semantic-parsing-support-vector/) (2004). It builds on the Gildea and Jurafsky framework, swapping in SVMs for the earlier classifier. It then adds features such as verb clusters, partial paths, verb senses and the head words of prepositional phrases. The system is evaluated on both hand-corrected and automatically produced parses. A first stage screens out parse nodes that are not arguments. The SVM outputs are also calibrated as probabilities, so that clashes between overlapping argument guesses can be settled by keeping the strongest. The later paper, [Towards Robust Semantic Role Labeling](https://md.research.elamur.ai/free/en/papers/pradhan-2008-robust-semantic-role-labeling/) (2008), turns to generalization across genres. It presents ASSERT, an SVM-based labeler whose candidate labels are rescored by a trigram model over argument sequences inside a Viterbi search. The paper then tests this labeler, trained on Wall Street Journal material, on PropBanked Brown Corpus text, where accuracy drops markedly. It examines how separating the identification of argument nodes from the assignment of their roles bears on that loss. Both papers sit within [Semantic role labeling](https://md.research.elamur.ai/free/en/topics/semantic-role-labeling/) and [Semantic parsing & meaning representation](https://md.research.elamur.ai/free/en/topics/semantic-parsing/). Ward's papers are associated with the [University of Colorado Boulder](https://md.research.elamur.ai/free/en/universities/university-of-colorado-boulder/), [Carnegie Mellon University](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) and [Boulder Language Technologies](https://md.research.elamur.ai/free/en/companies/boulder-language-technologies/). The work here was written with [Sameer Pradhan](https://md.research.elamur.ai/free/en/authors/sameer-pradhan/), [James H. Martin](https://md.research.elamur.ai/free/en/authors/james-h-martin/) and [Dan Jurafsky](https://md.research.elamur.ai/free/en/authors/dan-jurafsky/). Wayne Ward has 2 papers in our library, in 2004–2008, most of them on [Semantic role labeling](https://md.research.elamur.ai/free/en/topics/semantic-role-labeling/), [Semantic parsing & meaning representation](https://md.research.elamur.ai/free/en/topics/semantic-parsing/); often with [James H. Martin](https://md.research.elamur.ai/free/en/authors/james-h-martin/), [Sameer Pradhan](https://md.research.elamur.ai/free/en/authors/sameer-pradhan/), [Dan Jurafsky](https://md.research.elamur.ai/free/en/authors/dan-jurafsky/). 2 papers in our library · 2004–2008 [OpenAlex](https://openalex.org/A5082719298) · [**h-index 34**](https://openalex.org/authors/A5082719298) · [124 works](https://openalex.org/works?filter=author.id:A5082719298) · [4 225 citations](https://openalex.org/works?filter=author.id:A5082719298&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [2 works in our library](https://md.research.elamur.ai/free/en/authors/wayne-ward/#papers) · [173 citations in our library](https://md.research.elamur.ai/free/en/authors/wayne-ward/cited-by/) · [⭐ Paper Star rank #2580](https://md.research.elamur.ai/free/en/paper-stars/page/26/#star-2580) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Wayne+Ward) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Wayne+Ward) · [dblp](https://dblp.org/search?q=Wayne+Ward) · [ACL Anthology](https://aclanthology.org/search/?q=Wayne+Ward) ## Affiliations - [University of Colorado Boulder](https://md.research.elamur.ai/free/en/universities/university-of-colorado-boulder/) · Boulder, United States —1979–2021 on 49 papers - [Boulder Language Technologies (United States)](https://md.research.elamur.ai/free/en/companies/boulder-language-technologies/) · Boulder, United States —2008–2020 on 15 papers - [Carnegie Mellon University](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) · Pittsburgh, United States —1988–2018 on 21 papers - [University of Colorado System](https://md.research.elamur.ai/free/en/universities/university-of-colorado-system/) · Boulder, United States —2000–2008 on 5 papers From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 more institutions on single bylines are not listed. ## Topics [Semantic role labeling 1](https://md.research.elamur.ai/free/en/topics/semantic-role-labeling/) · [Semantic parsing & meaning representation 1](https://md.research.elamur.ai/free/en/topics/semantic-parsing/) ## Works by year ### 2000s [**2008** 1 paper](https://md.research.elamur.ai/free/en/papers/pradhan-2008-robust-semantic-role-labeling/) · [**2004** 1 paper](https://md.research.elamur.ai/free/en/papers/pradhan-2004-shallow-semantic-parsing-support-vector/) ## Papers The most cited first (OpenAlex and our library). 1. **[Shallow Semantic Parsing using Support Vector Machines](https://md.research.elamur.ai/free/en/papers/pradhan-2004-shallow-semantic-parsing-support-vector/)** *(2004 · 497 citations)* The paper addresses shallow semantic parsing, also called semantic role labeling: for each verb in a sentence, find the constituents that act as its arguments and assign them PropBank labels such as ARG0–ARG5 and ARGM adjuncts. 2. **[Towards Robust Semantic Role Labeling](https://md.research.elamur.ai/free/en/papers/pradhan-2008-robust-semantic-role-labeling/)** *(2008 · 160 citations)* Semantic role labeling (SRL) systems are usually trained and tested on the same corpus, which can hide how poorly they generalize. ## Co-authors here 3 co-authors with a page, the most papers together first. - [James H. Martin](https://md.research.elamur.ai/free/en/authors/james-h-martin/) ×2 - [Sameer Pradhan](https://md.research.elamur.ai/free/en/authors/sameer-pradhan/) ×2 - [Dan Jurafsky](https://md.research.elamur.ai/free/en/authors/dan-jurafsky/) ## Cited by Papers of our library cite their works 173 times (of the 140 884 papers whose bibliographies we read); [20 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/wayne-ward/cited-by/).