Travis Wolfe’s research while affiliated with Johns Hopkins University and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (8)


Feature Generation for Robust Semantic Role Labeling
  • Article

February 2017

·

11 Reads

Travis Wolfe

·

Mark Dredze

·

Benjamin Van Durme

Hand-engineered feature sets are a well understood method for creating robust NLP models, but they require a lot of expertise and effort to create. In this work we describe how to automatically generate rich feature sets from simple units called featlets, requiring less engineering. Using information gain to guide the generation process, we train models which rival the state of the art on two standard Semantic Role Labeling datasets with almost no task or linguistic insight.




Interactive Knowledge Base Population
  • Article
  • Full-text available

May 2015

·

128 Reads

·

2 Citations

Travis Wolfe

·

Mark Dredze

·

James Mayfield

·

[...]

·

Benjamin Van Durme

Most work on building knowledge bases has focused on collecting entities and facts from as large a collection of documents as possible. We argue for and describe a new paradigm where the focus is on a high-recall extraction over a small collection of documents under the supervision of a human expert, that we call Interactive Knowledge Base Population (IKBP).

Download


Figure 3: Overall coverage and average number of LUs per frame for varying values of t.  
Table 3 ).
FrameNet+: Fast Paraphrastic Tripling of FrameNet

January 2015

·

90 Reads

·

24 Citations

We increase the lexical coverage of FrameNet through automatic paraphras-ing. We use crowdsourcing to manually filter out bad paraphrases in order to en-sure a high-precision resource. Our ex-panded FrameNet contains an additional 22K lexical units, a 3-fold increase over the current FrameNet, and achieves 40% better coverage when evaluated in a prac-tical setting on New York Times data.



PARMA: A predicate argument aligner

July 2013

·

44 Reads

·

12 Citations

We introduce PARMA, a system for cross-document, semantic predicate and argument alignment. Our system combines a number of linguistic resources familiar to researchers in areas such as recognizing textual entailment and question answering, integrating them into a simple discriminative model. PARMA achieves state of the art results on an existing and a new dataset. We suggest that previous efforts have focussed on data that is biased and too easy, and we provide a more difficult dataset based on translation data with a low baseline which we beat by 17% F1.

Citations (7)


... Therefore, in addition to the list of documents , the initial search query effectively retrieves a query-specific knowledge graph = ( , ), where = =1 and = =1 . We assume that concepts and relations in have been pre-extracted by NLP algorithms in the search engine backend [9,35,54]. As described in Section 3.1, often contains a large number (hundreds or even thousands) of concepts and relations. ...

Reference:

GRAFS: Graphical Faceted Search System to Support Conceptual Understanding in Exploratory Search
Pocket Knowledge Base Population
  • Citing Conference Paper
  • January 2017

... We utilize majority portions of the Concretely Annotated New York Times and Wikipedia corpora from Ferraro et al. (2014). These have been annotated with three frame semantic parses: FrameNet from Das et al. (2010), and both FrameNet and PropBank from Wolfe et al. (2016). In total, we use nearly five million frame-annotated documents. ...

A Study of Imitation Learning Methods for Semantic Role Labeling
  • Citing Conference Paper
  • January 2016

... While many coreferring mention pairs in event coreference datasets such as ECB+ (Cybulska and Vossen, 2014) are lexically and contextually similar, or even share the same lemma (Wolfe et al., 2015), the difficulty arises for dissimilar coreferring mentions. For example, in Figure 1, spent and hospitalized are coreferring. ...

Predicate Argument Alignment using a Global Coherence Model
  • Citing Conference Paper
  • January 2015

... In an effort to improve FrameNet's LU coverage, Pavlick et al. (2015) proposes increasing the LU vocabulary via automatic paraphrasing and crowdworker verification, without expanding the lexicographic annotations. Others address this limitation by generating annotations through lexical substitution (Anwar et al., 2023) and predicate replacement (Pancholy et al., 2021); neither leverages the generative capabilities of LLMs, however. ...

FrameNet+: Fast Paraphrastic Tripling of FrameNet

... KELVIN () and BBN system (Min et al., 2015) both use hand-crafted rules to limit the number of fillers, e.g., remove less precise relations if a person has more than 8 (current and ex-) spouses. (Wolfe et al., 2015) and (He and Grishman, 2015) proposed interactive tools for KB construction with human guidance. Knowledge Base Completion With the recent popularity of structured KBs such as Freebase (Bollacker et al., 2008), YAGO (Suchanek et al., 2007) and above-mentioned KBP techniques, there is a growing interest in completing a partially-complete KB with tensor decomposition (Chang et al., 2014), matrix factorization (Riedel et al., 2013), graph random walk (Lao et al., 2011;Lao et al., 2012;Gardner et al., 2014), neural networks (Socher et al., 2013;Neelakantan et al., 2015;Dong et al., 2014) and others (Guu et al., 2015;Gardner et al., 2013;Das et al., 2016). ...

Interactive Knowledge Base Population

... Roth and Frank (2012b), for instance, annotate gold predicate alignments in 70 pairs of topically related documents from GigaPairs (Roth and Frank, 2012a) and introduce a graph-based clustering model for the task. Wolfe et al. (2013) present PARMA, a feature-rich, regularized logistic regression model for the same task that makes independent alignment decisions for each predicate and argument. While CDAE demands neither identification of a predicate in the source document nor an explicit argument-to-argument alignment, it is similar to this work in identifying aligned sets of arguments of the same event across documents. ...

PARMA: A predicate argument aligner
  • Citing Conference Paper
  • July 2013