Improving Human Text Comprehension through Semi-Markov CRF-based Neural Section Title Generation Sebastian Gehrmann, Steven Layne, Franck Dernoncourt @SebGehr gehrmann@seas.harvard.edu
Long texts are hard to comprehend When another old cave is discovered in the south of France, it is not usually news. Rather, it is an ordinary event. Such discoveries are so frequent these days that hardly anybody pays heed to them. However, when the Lascaux cave complex was discovered in 1940, the world was amazed. Painted directly on its walls were hundreds of scenes showing how people lived thousands of years ago. The scenes show people hunting animals, such as bison or wild cats. Other images depict birds and, most noticeably, horses, which appear in more than 300 wall images, by far outnumbering all other animals. Early artists drawing these animals accomplished a monumental and difficult task. They did not limit themselves to the easily accessible walls but carried their painting materials to spaces that required climbing steep walls or crawling into narrow passages in the Lascaux complex. Unfortunately, the paintings have been exposed to the destructive action of water and temperature changes, which easily wear the images away. Because the Lascaux caves have many entrances, air movement has also damaged the images inside. Although they are not out in the open air, where natural light would have destroyed them long ago, many of the images have deteriorated and are barely recognizable. To prevent further damage, the site was closed to tourists in 1963, 23 years after it was discovered.
Can Summaries Help? Lascaux cave complex When another old cave is discovered in the south of France, it is not usually news. Rather, it is an ordinary event. Such discoveries are so frequent these days that hardly anybody pays heed discovered to them. However, when the Lascaux cave complex was discovered in 1940, the world was amazed. Painted directly on its walls were hundreds of scenes showing how people lived thousands of years ago. The scenes show people hunting animals, such as bison or wild cats. Other images depict birds and, most noticeably, horses, which appear in more than 300 wall images, by far outnumbering all other animals. Paintings exposed Early artists drawing these animals accomplished a monumental and difficult task. They did not to destructive action limit themselves to the easily accessible walls but carried their painting materials to spaces that required climbing steep walls or crawling into narrow passages in the Lascaux complex. Unfortunately, the paintings have been exposed to the destructive action of water and temperature changes, which easily wear the images away. Because the Lascaux caves have many entrances, air movement has also damaged the images inside. Although they are not out in the open air, where natural light would have destroyed them long ago, many of the images have deteriorated and are barely recognizable. Site closed to tourists To prevent further damage, the site was closed to tourists in 1963, 23 years after it was discovered.
We hypothesize that summaries, presented as section titles, can improve the fact retention , fact retrieval and text comprehension . Goals (1) A low-resource approach to generating section titles (2) An evaluation framework for comprehension tasks Dooling et al. (1971), Kintsch et al. (1978), Smith et al. (1992)
<latexit sha1_base64="XsZmpryMYguDk2Fkozp56rQsf78=">ACJHicbVDLSsNAFJ3UV62vqks3g0VQKCWpgoIohuXFawVmhIm0k7dDIJMzfSEOq/uPFX3LjwgQs3fovTmoVaDwczrmHuf4seAabPvDKszMzs0vFBdLS8srq2vl9Y1rHSWKsiaNRKRufKZ4JI1gYNgN7FiJPQFa/mD87HfumVK80heQRqzTkh6kgecEjCSVz4ehy7QaSIEHh36DnV1HP2qtgV3Qh0dSxJI8m9OxfYEDIeBKO71GROsOVK3bNngBPEycnFZSj4ZVf3W5Ek5BJoIJo3XbsGDoZUcCpYKOSm2gWEzogPdY2VJKQ6U42OXKEd4zSxWZT8yTgifozkZFQ6zT0zWRIoK/emPxP6+dQHDUybiME2CSfn8UJAJDhMeN4S5XjIJIDSFUcbMrpn2iCAXTa8mU4Pw9eZpc12vOfq1+eVA5PcvrKItI12kYMO0Sm6QA3URBTdo0f0jF6sB+vJerPev0cLVp7ZRL9gfX4BF0SjQg=</latexit> <latexit sha1_base64="4BueSHlBjyT+AG9b7qJ7aMVRUNA=">ACN3icbVBNSwMxEM36bf2qevQSLIJeyq4KehS9eBIF2wrdUrLptAaT7JLMSsuy/iov/g1vevGgiFf/gWm7B78GAm/em8dkXpRIYdH3n7yJyanpmdm5+dLC4tLySnl1rW7j1HCo8VjG5ipiFqTQUEOBEq4SA0xFEhrRzclQb9yCsSLWlzhIoKVYT4u4Awd1S6fhanuOB0wCxH6mFnQmN+FQt+N+4QZlueFyExPsX6eh3TUG5VZJgVoPsi3h8adrniV/1R0b8gKECFHXeLj+GnZinypm5ZNY2Az/BluEgkvIS2FqIWH8hvWg6aBmCmwrG92d0y3HdGg3Nu5pCP2uyNjytqBitykYnhtf2tD8j+tmWL3sJUJnaTojhsv6qaSYkyHIdKOMBRDhxg3Aj3V8qvXVAcXZQlF0Lw+S/oL5bDfaquxf7laPjIo45skE2yTYJyAE5IqfknNQIJ/fkmbySN+/Be/HevY/x6IRXeNbJj/I+vwDIx7Cg</latexit> Section Titles in Two Steps When another old cave is discovered in the south of France, it is not usually news. Rather, it is an ordinary event. Such discoveries are so frequent these days that hardly anybody pays heed to them. However, when the Lascaux cave complex was (1) Select the most important Sentence discovered in 1940, the world was amazed . Painted directly on its walls were hundreds of scenes showing how people lived thousands of years ago. The scenes show people hunting animals, such as bison or wild cats. Other images depict birds and, most noticeably, horses, which appear in more than 300 wall images, by far outnumbering all other animals. sent ∈ para saliency( sent ) argmax However, when the Lascaux cave complex was discovered in 1940, the world was amazed. (2) Compress the sentence x i ∀ ( x 1 , y 1 ) , . . . , ( x n , y n ) i ff y i = 1 Lascaux cave complex discovered
<latexit sha1_base64="XsZmpryMYguDk2Fkozp56rQsf78=">ACJHicbVDLSsNAFJ3UV62vqks3g0VQKCWpgoIohuXFawVmhIm0k7dDIJMzfSEOq/uPFX3LjwgQs3fovTmoVaDwczrmHuf4seAabPvDKszMzs0vFBdLS8srq2vl9Y1rHSWKsiaNRKRufKZ4JI1gYNgN7FiJPQFa/mD87HfumVK80heQRqzTkh6kgecEjCSVz4ehy7QaSIEHh36DnV1HP2qtgV3Qh0dSxJI8m9OxfYEDIeBKO71GROsOVK3bNngBPEycnFZSj4ZVf3W5Ek5BJoIJo3XbsGDoZUcCpYKOSm2gWEzogPdY2VJKQ6U42OXKEd4zSxWZT8yTgifozkZFQ6zT0zWRIoK/emPxP6+dQHDUybiME2CSfn8UJAJDhMeN4S5XjIJIDSFUcbMrpn2iCAXTa8mU4Pw9eZpc12vOfq1+eVA5PcvrKItI12kYMO0Sm6QA3URBTdo0f0jF6sB+vJerPev0cLVp7ZRL9gfX4BF0SjQg=</latexit> <latexit sha1_base64="4BueSHlBjyT+AG9b7qJ7aMVRUNA=">ACN3icbVBNSwMxEM36bf2qevQSLIJeyq4KehS9eBIF2wrdUrLptAaT7JLMSsuy/iov/g1vevGgiFf/gWm7B78GAm/em8dkXpRIYdH3n7yJyanpmdm5+dLC4tLySnl1rW7j1HCo8VjG5ipiFqTQUEOBEq4SA0xFEhrRzclQb9yCsSLWlzhIoKVYT4u4Awd1S6fhanuOB0wCxH6mFnQmN+FQt+N+4QZlueFyExPsX6eh3TUG5VZJgVoPsi3h8adrniV/1R0b8gKECFHXeLj+GnZinypm5ZNY2Az/BluEgkvIS2FqIWH8hvWg6aBmCmwrG92d0y3HdGg3Nu5pCP2uyNjytqBitykYnhtf2tD8j+tmWL3sJUJnaTojhsv6qaSYkyHIdKOMBRDhxg3Aj3V8qvXVAcXZQlF0Lw+S/oL5bDfaquxf7laPjIo45skE2yTYJyAE5IqfknNQIJ/fkmbySN+/Be/HevY/x6IRXeNbJj/I+vwDIx7Cg</latexit> Section Titles in Two Steps When another old cave is discovered in the south of France, it is not usually news. Rather, it is an ordinary event. Such discoveries are so frequent these days that hardly anybody pays heed to them. However, when the Lascaux cave complex was (1) Select the most important Sentence discovered in 1940, the world was amazed . Painted directly on its walls were hundreds of scenes showing how people lived thousands of years ago. The scenes show people hunting animals, such as bison or wild cats. Other images depict birds and, most noticeably, horses, which appear in more than 300 wall images, by far outnumbering all other animals. sent ∈ para saliency( sent ) argmax However, when the Lascaux cave complex was discovered in 1940, the world was amazed. (2) Compress the sentence x i ∀ ( x 1 , y 1 ) , . . . , ( x n , y n ) i ff y i = 1 Lascaux cave complex discovered
<latexit sha1_base64="XsZmpryMYguDk2Fkozp56rQsf78=">ACJHicbVDLSsNAFJ3UV62vqks3g0VQKCWpgoIohuXFawVmhIm0k7dDIJMzfSEOq/uPFX3LjwgQs3fovTmoVaDwczrmHuf4seAabPvDKszMzs0vFBdLS8srq2vl9Y1rHSWKsiaNRKRufKZ4JI1gYNgN7FiJPQFa/mD87HfumVK80heQRqzTkh6kgecEjCSVz4ehy7QaSIEHh36DnV1HP2qtgV3Qh0dSxJI8m9OxfYEDIeBKO71GROsOVK3bNngBPEycnFZSj4ZVf3W5Ek5BJoIJo3XbsGDoZUcCpYKOSm2gWEzogPdY2VJKQ6U42OXKEd4zSxWZT8yTgifozkZFQ6zT0zWRIoK/emPxP6+dQHDUybiME2CSfn8UJAJDhMeN4S5XjIJIDSFUcbMrpn2iCAXTa8mU4Pw9eZpc12vOfq1+eVA5PcvrKItI12kYMO0Sm6QA3URBTdo0f0jF6sB+vJerPev0cLVp7ZRL9gfX4BF0SjQg=</latexit> <latexit sha1_base64="4BueSHlBjyT+AG9b7qJ7aMVRUNA=">ACN3icbVBNSwMxEM36bf2qevQSLIJeyq4KehS9eBIF2wrdUrLptAaT7JLMSsuy/iov/g1vevGgiFf/gWm7B78GAm/em8dkXpRIYdH3n7yJyanpmdm5+dLC4tLySnl1rW7j1HCo8VjG5ipiFqTQUEOBEq4SA0xFEhrRzclQb9yCsSLWlzhIoKVYT4u4Awd1S6fhanuOB0wCxH6mFnQmN+FQt+N+4QZlueFyExPsX6eh3TUG5VZJgVoPsi3h8adrniV/1R0b8gKECFHXeLj+GnZinypm5ZNY2Az/BluEgkvIS2FqIWH8hvWg6aBmCmwrG92d0y3HdGg3Nu5pCP2uyNjytqBitykYnhtf2tD8j+tmWL3sJUJnaTojhsv6qaSYkyHIdKOMBRDhxg3Aj3V8qvXVAcXZQlF0Lw+S/oL5bDfaquxf7laPjIo45skE2yTYJyAE5IqfknNQIJ/fkmbySN+/Be/HevY/x6IRXeNbJj/I+vwDIx7Cg</latexit> Section Titles in Two Steps When another old cave is discovered in the south of France, it is not usually news. Rather, it is an ordinary event. Such discoveries are so frequent these days that hardly anybody pays heed to them. However, when the Lascaux cave complex was (1) Select the most important Sentence discovered in 1940, the world was amazed . Painted directly on its walls were hundreds of scenes showing how people lived thousands of years ago. The scenes show people hunting animals, such as bison or wild cats. Other images depict birds and, most noticeably, horses, which appear in more than 300 wall images, by far outnumbering all other animals. sent ∈ para saliency( sent ) argmax However, when the Lascaux cave complex was discovered in 1940, the world was amazed. (2) Compress the sentence x i ∀ ( x 1 , y 1 ) , . . . , ( x n , y n ) i ff y i = 1 Lascaux cave complex discovered
Recommend
More recommend
