Aligning Semantic Graphs for Textual Inference and Machine Reading

نویسندگان

  • Marie-Catherine de Marneffe
  • Trond Grenager
  • Bill MacCartney
  • Daniel Cer
  • Daniel Ramage
  • Chloé Kiddon
  • Christopher D. Manning
چکیده

This paper presents our work on textual inference and situates it within the context of the larger goals of machine reading. The textual inference task is to determine if the meaning of one text can be inferred from the meaning of another and from background knowledge. Our system generates semantic graphs as a representation of the meaning of a text. This paper presents new results for aligning pairs of semantic graphs, and proposes the application of natural logic to derive inference decisions from those aligned pairs. We consider this work as first steps toward a system able to demonstrate broad-coverage text understanding and learning

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Robust Graph Alignment Methods for Textual Inference and Machine Reading

This paper presents our work on textual inference and situates it within the context of the larger goals of machine reading. The textual inference task is to determine if the meaning of one text can be inferred from the meaning of another combined with background knowledge. Most existing work either provides only very limited text understanding by using bag-of-words lexical similarity models or...

متن کامل

Evaluation of “Mosaic 1 Reading”: A Microstructural Approach to Textual Analysis of Pedagogical Materials

To analyze and evaluate textbooks, researchers have either proposed scales and checklists to be filled by teachers and learners or conducted qualitative investigations of the match between SLA theories and textbook activities. This study, however, employs the microstructural approach of schema theory to scrutinize the reading passages of “Mosaic 1 Reading”. To this end, 17 passages of the textb...

متن کامل

Recognizing Textual Entailment Using Description Logic and Semantic Relatedness

Recognizing Textual Entailment using Description Logic and Semantic Relatedness Reda Siblini, Ph.D. Concordia University, 2014 Textual entailment (TE) is a relation that holds between two pieces of text where one reading the first piece can conclude that the second is most likely true. Accurate approaches for textual entailment can be beneficial to various natural language processing (NLP) appl...

متن کامل

TheDoxa of Reading andrew goldstone

Reading Graphs, Maps, Trees as a late-stage graduate student in 2008 was invigorating.1 Here was an approach to literary history free from the pieties of “close reading,” committed to empiricism, seeking to fulfill the promise of the sociology of literature with its “materialist conception of form” (92). And, at the time, it seemed entirely natural that the way to follow the path laid out by Fr...

متن کامل

Learning Alignments and Leveraging Natural Logic

We describe an approach to textual inference that improves alignments at both the typed dependency level and at a deeper semantic level. We present a machine learning approach to alignment scoring, a stochastic search procedure, and a new tool that finds deeper semantic alignments, allowing rapid development of semantic features over the aligned graphs. Further, we describe a complementary sema...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2007