Textual Analogy Parsing: What’s Shared and What’s Compared among Analogous Facts

To understand a sentence like “whereas only 10% of White Americans live at or below the poverty line, 28% of African Americans do” it is important not only to identify individual facts, e.g., poverty rates of distinct demographic groups, but also the higher-order relations between them, e.g., the disparity between them. In this paper, we propose the task of Textual Analogy Parsing (TAP) to model this higher-order meaning. Given a sentence such as the one above, TAP outputs a frame-style meaning representation which explicitly specifies what is shared (e.g., poverty rates) and what is compared (e.g., White Americans vs. African Americans, 10% vs. 28%) between its component facts. Such a meaning representation can enable new applications that rely on discourse understanding such as automated chart generation from quantitative text. We present a new dataset for TAP, baselines, and a model that successfully uses an ILP to enforce the structural constraints of the problem.

[1]  Amos Tversky,et al.  Studies of similarity , 1978 .

[2]  Herbert A. Simon,et al.  Why a Diagram is (Sometimes) Worth Ten Thousand Words , 1987, Cogn. Sci..

[3]  Brian Falkenhainer,et al.  The Structure-Mapping Engine: Algorithm and Examples , 1989, Artif. Intell..

[4]  K. Holyoak,et al.  Mental Leaps: Analogy in Creative Thought , 1994 .

[5]  D. Gentner,et al.  Structure mapping in analogy and similarity. , 1997 .

[6]  John B. Lowe,et al.  The Berkeley FrameNet Project , 1998, ACL.

[7]  Daniel Gildea,et al.  Automatic Labeling of Semantic Roles , 2000, ACL.

[8]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[9]  Maria T. Pazienza,et al.  Information Extraction , 2002, Lecture Notes in Computer Science.

[10]  Andrew Kehler,et al.  Coherence, reference, and the theory of grammar , 2002, CSLI lecture notes series.

[11]  Dan Roth,et al.  A Linear Programming Formulation for Global Inference in Natural Language Tasks , 2004, CoNLL.

[12]  Daniel Gildea,et al.  The Proposition Bank: An Annotated Corpus of Semantic Roles , 2005, CL.

[13]  Robert L. Goldstone,et al.  The Transfer of Scientific Principles Using Concrete and Idealized Simulations , 2005, Journal of the Learning Sciences.

[14]  W. Mann,et al.  Rhetorical Structure Theory: looking back and moving ahead , 2006 .

[15]  Livio Robaldo,et al.  The Penn Discourse Treebank 2.0 Annotation Manual , 2007 .

[16]  Derek C. Penn,et al.  Darwin's mistake: Explaining the discontinuity between human and nonhuman minds , 2008, Behavioral and Brain Sciences.

[17]  Ani Nenkova,et al.  Automatic sense prediction for implicit discourse relations in text , 2009, ACL.

[18]  Rashmi Prasad,et al.  Exploiting Scope for Shallow Discourse Parsing , 2010, LREC.

[19]  K. Holyoak,et al.  The Oxford handbook of thinking and reasoning , 2012 .

[20]  Dan Roth,et al.  Joint Inference for Event Timeline Construction , 2012, EMNLP.

[21]  Matthew D. Zeiler.  ADADELTA: An Adaptive Learning Rate Method , 2012, ArXiv.

[22]  K. Holyoak.  Analogy and Relational Reasoning , 2012 .

[23]  Peter D. Turney.  Distributional Semantics Beyond Words: Supervised Learning of Analogy and Paraphrase , 2013, TACL.

[24]  Geoffrey Zweig,et al.  Linguistic Regularities in Continuous Space Word Representations , 2013, NAACL.

[25]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[26]  Mihai Surdeanu,et al.  The Stanford CoreNLP Natural Language Processing Toolkit , 2014, ACL.

[27]  Luke S. Zettlemoyer,et al.  Learning to Automatically Solve Algebra Word Problems , 2014, ACL.

[28]  Peter Clark,et al.  Modeling Biological Processes for Reading Comprehension , 2014, EMNLP.

[29]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[30]  Dan Roth,et al.  Reasoning about Quantities in Natural Language , 2015, TACL.

[31]  Wei Xu,et al.  End-to-end learning of semantic role labeling using recurrent neural networks , 2015, ACL.

[32]  Mihai Surdeanu,et al.  Two Practical Rhetorical Structure Theory Parsers , 2015, NAACL.

[33]  Guillaume Lample,et al.  Neural Architectures for Named Entity Recognition , 2016, NAACL.

[34]  Ganesh Ramakrishnan,et al.  Numerical Relation Extraction with Minimal Supervision , 2016, AAAI.

[35]  Mirella Lapata,et al.  Neural Semantic Role Labeling with Dependency Path Embeddings , 2016, ACL.

[36]  Maneesh Agrawala,et al.  Generating Personalized Spatial Analogies for Distances and Areas , 2016, CHI.

[37]  Daniel G. Goldstein,et al.  Improving Comprehension of Numbers in the News , 2016, CHI.

[38]  Percy Liang,et al.  How Much is 131 Million Dollars? Putting Numbers in Perspective with Compositional Descriptions , 2016, ACL.

[39]  Luke S. Zettlemoyer,et al.  End-to-end Neural Coreference Resolution , 2017, EMNLP.

[40]  Luke S. Zettlemoyer,et al.  Deep Semantic Role Labeling: What Works and What’s Next , 2017, ACL.

[41]  Luca Antiga,et al.  Automatic differentiation in PyTorch , 2017 .

[42]  Christopher D. Manning,et al.  QSRL : A Semantic Role-Labeling Schema for Quantitative Facts , 2018 .