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

Lamm, Matthew; Chaganty, Arun Tejasvi; Manning, Christopher D.; Jurafsky, Dan; Liang, Percy

doi:10.18653/v1/d18-1008

Cited by 16 publications

(9 citation statements)

References 31 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For sequence tagging techniques, rule-based methods [52] are straightforward, but costly and limited. There are also many machine learning methods proposed which are more robust and easier to generalize, including Hidden Markov Models (HMM) [9], Support Vector Machines (SVM) [4] and Conditional Random Fields (CRF) [34].…”

Section: Natural Language Interactionsmentioning

confidence: 99%

Text-to-Viz: Automatic Generation of Infographics from Proportion-Related Natural Language Statements

Cui

Zhang

Wang

et al. 2020

IEEE Trans. Visual. Comput. Graphics

110

View full text Add to dashboard Cite

Figure 1. Examples created by Text-to-Viz. (a)-(d) are generated from the statement: "More than 20% of smartphone users are social network users." (e) and (f) are generated from the statement: "40 percent of USA freshwater is for agriculture." (g) and (h) are generated from the statement: "3 in 5 Chinese people live in rural areas." (i) and (j) are generated from the statement: "65% of coffee is consumed at breakfast." (k)-(m) are generated from the statement: "Among all students, 49% like football, 32% like basketball, and 21% like baseball." (n) and (o) are generated from the statement: "Humans made 51.5% of online traffic, while good bots made 19.5% and bad bots made 29%."Abstract-Combining data content with visual embellishments, infographics can effectively deliver messages in an engaging and memorable manner. Various authoring tools have been proposed to facilitate the creation of infographics. However, creating a professional infographic with these authoring tools is still not an easy task, requiring much time and design expertise. Therefore, these tools are generally not attractive to casual users, who are either unwilling to take time to learn the tools or lacking in proper design expertise to create a professional infographic. In this paper, we explore an alternative approach: to automatically generate infographics from natural language statements. We first conducted a preliminary study to explore the design space of infographics. Based on the preliminary study, we built a proof-of-concept system that automatically converts statements about simple proportionrelated statistics to a set of infographics with pre-designed styles. Finally, we demonstrated the usability and usefulness of the system through sample results, exhibits, and expert reviews.

show abstract

Section: Natural Language Interactionsmentioning

confidence: 99%

Text-to-Viz: Automatic Generation of Infographics from Proportion-Related Natural Language Statements

Cui

Zhang

Wang

et al. 2020

IEEE Trans. Visual. Comput. Graphics

110

View full text Add to dashboard Cite

show abstract

“…The instantiation of QED presented in the current work is limited to extractive wh-questions whose answers are entailed by single sentences. We feel this scoping is well justified, because (1) a significant portion of NQ falls under QED's current purview; (2) previous work and data analysis suggests QED can be readily extended to accommodate these other types (Hearst, 1992;Miltsakaki et al, 2004;Lamm et al, 2018;Tandon et al, 2019); and (3) close study of the single sentence case is a necessary condition for these other question types.…”

Section: Scoping and Extension To Other Question Typesmentioning

confidence: 96%

“…(2) previous work and data analysis suggests QED can be readily extended to accommodate these other types (Hearst, 1992;Miltsakaki et al, 2004;Lamm et al, 2018;Tandon et al, 2019); and (3) close study of the single sentence case is a necessary condition for these other question types. In Figure 7, we present several representative NQ instances that require more machinery than QED provides at present.…”

Section: Scoping and Extension To Other Question Typesmentioning

confidence: 99%

QED: A Framework and Dataset for Explanations in Question Answering

Lamm

Palomaki

Alberti

et al. 2021

Transactions of the Association for Computational Linguistics

Self Cite

View full text Add to dashboard Cite

A question answering system that in addition to providing an answer provides an explanation of the reasoning that leads to that answer has potential advantages in terms of debuggability, extensibility, and trust. To this end, we propose QED, a linguistically informed, extensible framework for explanations in question answering. A QED explanation specifies the relationship between a question and answer according to formal semantic notions such as referential equality, sentencehood, and entailment. We describe and publicly release an expert-annotated dataset of QED explanations built upon a subset of the Google Natural Questions dataset, and report baseline models on two tasks—post- hoc explanation generation given an answer, and joint question answering and explanation generation. In the joint setting, a promising result suggests that training on a relatively small amount of QED data can improve question answering. In addition to describing the formal, language-theoretic motivations for the QED approach, we describe a large user study showing that the presence of QED explanations significantly improves the ability of untrained raters to spot errors made by a strong neural QA baseline.

show abstract

“…Tables are common in financial documents, especially formal documents. Lamm et al [3] propose a dataset and method for parsing numeral information in Penn Treebank Wall Street Journal articles [4]. Data mining methods can be used on such data after it has been translated into structured form.…”

Section: Future Directionsmentioning

confidence: 99%

Perspectives and Conclusion

Chen

Huang

Chen

2021

From Opinion Mining to Financial Argument Mining

View full text Add to dashboard Cite

In this book, we started by describing the components of financial opinions as well as opinion sources in the financial domain. Then, we surveyed options for modeling financial opinions, and discussed in detail one fundamental characteristic of financial narratives: numerals. We also listed numerous applications and research directions. We have thus described financial opinion mining and have provided essential examples to illustrate various concepts. In this final chapter, we organize future directions and summarize the ideas in the book.

show abstract

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

Cited by 16 publications

References 31 publications

Text-to-Viz: Automatic Generation of Infographics from Proportion-Related Natural Language Statements

Text-to-Viz: Automatic Generation of Infographics from Proportion-Related Natural Language Statements

QED: A Framework and Dataset for Explanations in Question Answering

Perspectives and Conclusion

Contact Info

Product

Resources

About