material ID: evaluations

Related Papers

Toward Communicating Simple Sentences Using Pictorial Representations

Authors: nan

Publication: TIPSTER (2006)

DOI: nan

AbstractThis paper evaluates the hypothesis that pictorial representations can be used to effectively convey simple sentences across language barriers. Comparative evaluations show that a considerable amount of understanding can be …...

29107

Can You Summarize This? Identifying Correlates of Input Difficulty for Multi-Document Summarization

Authors: nan

Publication: TIPSTER (2008)

DOI: nan

Different summarization requirements could make the writing of a good summary more dif- ficult, or easier. Summary length and the char- acteristics of the input are such constraints in- fluencing …...

36680

Keyphrase Extraction for N-best Reranking in Multi-Sentence Compression

Authors: nan

Publication: TIPSTER (2013)

DOI: nan

Multi-Sentence Compression (MSC) is the task of generating a short single sentence sum- mary from a cluster of related sentences. This paper presents an N-best reranking method based on keyphrase …...

23714

A Comparative Evaluation Methodology for NLG in Interactive Systems

Authors: nan

Publication: TIPSTER (2014)

DOI: nan

AbstractInteractive systems have become an increasingly important type of application for deployment of NLG technology over recent years. At present, we do not yet have commonly agreed terminology or methodology …...

17019

Learning Zero-Shot Multifaceted Visually Grounded Word Embeddings via Multi-Task Training

Authors: nan

Publication: TIPSTER (2021)

DOI: nan

AbstractLanguage grounding aims at linking the symbolic representation of language (e.g., words) into the rich perceptual knowledge of the outside world. The general approach is to embed both textual and …...

41788

Constructing Distributions of Variation in Referring Expression Type from Corpora for Model Evaluation

Authors: nan

Publication: TIPSTER (2022)

DOI: nan

AbstractThe generation of referring expressions (REs) is a non-deterministic task. However, the algorithms for the generation of REs are standardly evaluated against corpora of written texts which include only one …...

15455