The Power of the TSNLP: Lessons from a Diagnostic Evaluation of a Broad-Coverage Parser

Scarlett, Elizabeth; Śzpakowicz, Stan

doi:10.1007/3-540-45486-1_12

Cited by 4 publications

(3 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our proposed evaluation approach follows a similar rationale to that of the diagnostic test suite TSNLP (Balkan et al, 1994) designed for evaluating parsers on a per-phenomenon basis. As highlighted by Scarlett and Szpakowicz (2000) the systematic fine-grained evaluation of TSNLP enables precise pinpointing of parsers' limitations, while ensuring broad coverage and controlled evaluation of various linguistic phenomena and syntactic structures. Our proposal aims at initiating work on developing similar test suites for evaluating semantic composition models.…”

Section: Existing Approachesmentioning

confidence: 99%

Probing for semantic evidence of composition by means of simple classification tasks

Ettinger¹,

Elgohary²,

Resnik³

2016

Proceedings of the 1st Workshop on Evaluating Vector-Space Representations for NLP

122

View full text Add to dashboard Cite

show abstract

Section: Existing Approachesmentioning

confidence: 99%

Probing for semantic evidence of composition by means of simple classification tasks

Ettinger¹,

Elgohary²,

Resnik³

2016

Proceedings of the 1st Workshop on Evaluating Vector-Space Representations for NLP

122

View full text Add to dashboard Cite

show abstract

“…NLPWin is an NLP system from Microsoft that accepts sentences and delivers detailed syntactic analyses, together with a logical form representing an abstraction of the meaning (Elworthy, 2000). Scarlett and Szpakowicz (2000) report a diagnostic evaluation of DIPETT, a broad‐coverage parser of English sentences.…”

Section: Nlp Softwarementioning

confidence: 99%

Natural language processing

Chowdhury

2003

Annual Review Info Sci & Tec

685

242

View full text Add to dashboard Cite

Beginning with the basic issues of NLP, this chapter aims to chart the major research activities in this area since the last ARIST Chapter in 1996 (Haas, 1996), including: (i) natural language text processing systems - text summarization, information extraction, information retrieval, etc., including domain-specific applications; (ii) natural language interfaces; (iii) NLP in the context of www and digital libraries ; and (iv) evaluation of NLP systems

show abstract

“…NLPWin is an NLP system from Microsoft that accepts sentences and delivers detailed syntactic analysis, together with a logical form representing an abstraction of the meaning (Elworthy, 2000). Scarlett and Szpakowicz (2000) report a diagnostic evaluation of DIPETT, a broad-coverage parser of English sentences.…”

Section: Describes the Kana Customer Messagingmentioning

confidence: 99%

Natural Language Processing

View full text Add to dashboard Cite

The Power of the TSNLP: Lessons from a Diagnostic Evaluation of a Broad-Coverage Parser

Cited by 4 publications

References 3 publications

Probing for semantic evidence of composition by means of simple classification tasks

Probing for semantic evidence of composition by means of simple classification tasks

Natural language processing

Natural Language Processing

Contact Info

Product

Resources

About