Difference between revisions of "Paraphrase Identification (State of the art)"
Jump to navigation
Jump to search
| Line 1: | Line 1: | ||
| − | * [http://research.microsoft.com/en-us/downloads/607D14D9-20CD-47E3-85BC-A2F65CD28042/default.aspx Microsoft Research Paraphrase Corpus] (MSRP) | + | * '''source''': [http://research.microsoft.com/en-us/downloads/607D14D9-20CD-47E3-85BC-A2F65CD28042/default.aspx Microsoft Research Paraphrase Corpus] (MSRP) |
| − | * see Dolan | + | * '''task''': given a pair of sentences, classify them as paraphrases or not paraphrases |
| − | * train: 4,076 sentence pairs (2,753 positive: 67.5%) | + | * '''see''': Dolan et al. (2004) |
| − | * test: 1,725 sentence pairs (1,147 positive: 66.5%) | + | * '''train''': 4,076 sentence pairs (2,753 positive: 67.5%) |
| + | * '''test''': 1,725 sentence pairs (1,147 positive: 66.5%) | ||
== Sample data == | == Sample data == | ||
| − | * Sentence 1: Amrozi accused his brother, whom he called "the witness", of deliberately distorting his evidence. | + | * '''Sentence 1''': Amrozi accused his brother, whom he called "the witness", of deliberately distorting his evidence. |
| − | * Sentence 2: Referring to him as only "the witness", Amrozi accused his brother of deliberately distorting his evidence. | + | * '''Sentence 2''': Referring to him as only "the witness", Amrozi accused his brother of deliberately distorting his evidence. |
| − | * Class: 1 (true paraphrase) | + | * '''Class''': 1 (true paraphrase) |
Revision as of 14:08, 24 March 2009
- source: Microsoft Research Paraphrase Corpus (MSRP)
- task: given a pair of sentences, classify them as paraphrases or not paraphrases
- see: Dolan et al. (2004)
- train: 4,076 sentence pairs (2,753 positive: 67.5%)
- test: 1,725 sentence pairs (1,147 positive: 66.5%)
Sample data
- Sentence 1: Amrozi accused his brother, whom he called "the witness", of deliberately distorting his evidence.
- Sentence 2: Referring to him as only "the witness", Amrozi accused his brother of deliberately distorting his evidence.
- Class: 1 (true paraphrase)
Table of results
| Algorithm | Reference | Description | Accuracy | F |
|---|---|---|---|---|
| MCS | Mihalcea et al. (2006) | unsupervised combination of several word similarity measures | 70.3% | 81.3% |
| WDDP | Wan et al. (2006) | supervised dependency-based features | 75.0% | 73.0% |
References
Dolan, B., Quirk, C., and Brockett, C. (2004). Unsupervised construction of large paraphrase corpora: Exploiting massively parallel news sources, Proceedings of the 20th international conference on Computational Linguistics (COLING 2004), Geneva, Switzerland, pp. 350-356.
Mihalcea, R., Corley, C., and Strapparava, C. (2006). Corpus-based and knowledge-based measures of text semantic similarity, Proceedings of the National Conference on Artificial Intelligence (AAAI 2006), Boston, Massachusetts, pp. 775-780.
Wan, S., Dras, M., Dale, R., and Paris, C. (2006). Using dependency-based features to take the "para-farce" out of paraphrase, Proceedings of the Australasian Language Technology Workshop (ALTW 2006), pp. 131-138.