Mova0.5 pre-release⌕
☰
home / docs / papers / authors / Daniel Gildea

Daniel Gildea

6 paper cards in Mova's library · 2001–2019

Daniel Gildea wrote 6 of the papers Mova reads, in 2001–2019, most of them on Machine translation, Semantic role labeling, Treebanks; often with Linfeng Song, Yue Zhang, Zhiguo Wang.

OpenAlex · ORCID · h-index 37 · 9308 citations · 190 works — openalex, 2026-10-18

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 · ORCID

Topics: Machine translation 3 · Semantic role labeling 2 · Treebanks 1

Papers

  1. Semantic Neural Machine Translation Using AMR (2019)
    The paper asks whether an AMR graph of the source sentence helps neural machine translation. The model keeps a BiLSTM encoder over the words and adds a graph recurrent network that encodes the AMR graph without linearising it. A doubly attentive LSTM decoder reads both encodings. On WMT16 English-German (4.17M…
  2. AMR-to-text Generation with Synchronous Node Replacement Grammar (2017)
    The paper generates sentences directly from the AMR graph, without first making a spanning tree, so that no information is lost in the graph-to-tree step.
  3. The Proposition Bank: An Annotated Corpus of Semantic Roles (2005)
    PropBank adds predicate-argument labels to the Penn Treebank (Wall Street Journal part): numbered roles Arg0 to Arg5 that are defined per verb sense, plus adjunct tags (ArgM with function types such as temporal, locative, manner).
  4. Syntactic Features for Evaluation of Machine Translation (2005)
    The paper adds syntax to n-gram evaluation. The headword-chain metric (HWCM) matches the head-modifier paths of the reference against the hypothesis. The subtree metric (STM) matches constituent subtrees, and a dependency subtree variant (DSTM) matches head subtrees. All of them need a parser on the hypothesis. At…
  5. Automatic Labeling of Semantic Roles (2002)
    The first statistical system for labeling semantic roles with FrameNet frame elements (Agent, Patient, Speaker, Topic and others).
  6. Corpus Variation and Parser Performance (2001)
    The paper asks how much a statistical parser depends on the corpus it is trained on. It uses Collins' Model 1, a lexicalized generative parser, trained and tested on the Wall Street Journal (39,832 training sentences) and on the Brown corpus (about 21,800 training sentences, with every tenth sentence held out). A…

Co-authors (9)

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/authors/daniel-gildea/