A Syntax Free Sequence-oriented Sentence Compression Method | As an alternative to syntactic parsing, we propose two novel features, intra-sentence positional term weighting (IPTW) and the patched language model (PLM) for our syntax-free sentence compressor . |
A Syntax Free Sequence-oriented Sentence Compression Method | 3.1 Sentence Compression as a Combinatorial Optimization Problem |
Abstract | Conventional sentence compression methods employ a syntactic parser to compress a sentence without changing its meaning. |
Abstract | Moreover, for the goal of on-demand sentence compression , the time spent in the parsing stage is not negligible. |
Analysis of reference compressions | This statistic supports the view that sentence compression that strongly depends on syntax is not useful in reproducing reference compressions. |
Analysis of reference compressions | We need a sentence compression method that can drop intermediate nodes in the syntactic tree aggressively beyond the tree-scoped boundary. |
Analysis of reference compressions | In addition, sentence compression methods that strongly depend on syntactic parsers have two problems: ‘parse error’ and ‘decoding speed.’ 44% of sentences output by a state-of-the-art Japanese dependency parser contain at least one error (Kudo and Matsumoto, 2005). |
Introduction | In accordance with this idea, conventional sentence compression methods employ syntactic parsers. |
Introduction | Moreover, on-demand sentence compression is made problematic by the time spent in the parsing stage. |
Introduction | This paper proposes a syntax-free sequence-oriented sentence compression method. |
Introduction | We consider three paraphrase applications in our experiments, including sentence compression , sentence simplification, and sentence similarity computation. |
Results and Analysis | Results show that the percentages of test sentences that can be paraphrased are 97.2%, 95.4%, and 56.8% for the applications of sentence compression , simplification, and similarity computation, respectively. |
Results and Analysis | Further results show that the average number of unit replacements in each sentence is 5.36, 4.47, and 1.87 for sentence compression , simplification, and similarity computation. |
Results and Analysis | A source sentence s is paraphrased in each application and we can see that: (l) for sentence compression , the paraphrase t is 8 bytes shorter than s; (2) for sentence simplification, the words wealth and part in t are easier than their sources asset and proportion, especially for the nonnative speakers; (3) for sentence similarity computation, the reference sentence s’ is listed below t, in which the words appearing in t but not in s are highlighted in blue. |
Statistical Paraphrase Generation | On the contrary, SPG has distinct purposes in different applications, such as sentence compression , sentence simplification, etc. |
Statistical Paraphrase Generation | The application in this example is sentence compression . |
Statistical Paraphrase Generation | Paraphrase application: sentence compression |