1 / 7

Robust Semantic Role Labeling for Nominals

Robust Semantic Role Labeling for Nominals. Robert Munro Aman Naimat. In brief. Created a system for Nominal Semantic Role Labeling Useful for Information Extraction and Q&A: An Example. The police investigated the crime. Agent PRED Patient. Architecture.

trammell
Télécharger la présentation

Robust Semantic Role Labeling for Nominals

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Robust Semantic Role Labeling for Nominals Robert Munro Aman Naimat

  2. In brief • Created a system for Nominal Semantic Role Labeling • Useful for Information Extraction and Q&A: • An Example The police investigated the crime Agent PRED Patient

  3. Architecture • Tested on the NomBank corpus (250,000 size) • [the crime’s ARG1] [investigation PRED] … • [the police’s ARG0] [investigation PRED] … • [The investigation PRED] of [thepoliceARG0?/ARG1?] … • Based on the current SOTA (Liu & Ng 2007) • Developed 12 new features: 1) Syntactic Context: Agents are more likely to be in the sentence’s subject position: 2) Animacy features: The most animate argument is more likely to be the Agent • Stanford Classifier (MaxEnt)

  4. Our contribution • We improved the current State of the Art results: Us! Liu & Ng, 2007 (Baseline)

  5. Our contribution • Especially over unseen predicate/constituents: Us! Liu & Ng, 2007 (Baseline)

  6. Data analysis Syntactic position Animacy

  7. Conclusions • Features modeling syntactic context and animacy improve nominal-Semantic Role Labeling • Consistently outperforms the current state of the art results: +.012 FB1 over all NomBank +.033 FB1 over unseen predicate/constituents • Greater improvements are possible

More Related