A Natural Language Generation System for Constituent Correspondence

Will Kolkey, Jian Dong, Greg Bybee

July 12, 2019

WORKING DRAFT
Selected for the Proceedings of the INLG2019 Conference

ABSTRACT

Roughly 30% of congressional staffers in the United States report spending a “great deal” of time writing responses to constituent letters (Furnas, 2018). Letters often solicit an update on the status of legislation and a description of a congressman’s vote record or vote intention — structurable data that can be leveraged by a natural language generation system to create a coherent letter response.

This paper describes how PoliScribe, a pipeline-architectured NLG platform, constructs personalized responses to constituents inquiring about legislation. Emphasis will be placed on adapting NLG methodologies to the political domain, which entails special attention to affect, discursive variety, and rhetorical strategies that align a speaker with their interlocutor, even in cases of policy disagreement.

I. INTRODUCTION

Recent work in the field of NLG has shifted from emphasizing the provision of information to aspects of tone and style. The shift follows from the increasing complexity of NLG systems themselves, which have evolved from vehicles of information delivery to sophisticated platforms aiming to persuade, engage, and even entertain. (Gatt and Krahmer, 2018). The trend holds particular relevance to the domain of political epistolography, in which qualities such as affect and personality are important for meeting the conventions of the genre.

This paper discusses these themes in the context of PoliScribe, an NLG system that is currently utilized by several dozen legislative offices across the United States, including federal and state representatives from California, Texas, and New York. To our knowledge, this is the first instance of an NLG platform that has been applied to constituent communications.

II. LETTER GENERATION

PoliScribe is designed to respond to constituents who are advocating for or against legislation. At its core, the platform follows a Leveltian model of text generation, whereby letters are constructed according to a rules-based schema consisting of content and document planning, sentence planning, and surface realization (Levelt, 1989; Reiter and Dale, 1999).

PoliScribe works by inputting a bill number into the user interface (e.g., H.R. 5) and selecting the member’s disposition toward the bill (e.g., strongly support, undecided, etc.). The system connects to public databases to identify the bill’s title, description, vote history, committee assignments, and sponsorship information. These and other informational elements are expressed within PoliScribe as independent sentences, noun phrases, adjectives, or subordinate clauses, and are realized through a process of aggregation with a bias for sentence variation.

The output of this operation is a letter that explains where a bill is in the legislative process and how the elected official feels about the legislation. The system is versatile, supporting more than a billion letter variations, depending on factors that include the stylistic preferences of the user, the legislative stage of the bill, and the relationship of the constituent’s policy views to that of their Representative’s.

III. NAVIGATING AFFECT AND STYLE

Since the objective of PoliScribe is to imitate the letter-writing style of a political officeholder, discursive features such as tone, personality, and affect are essential to engendering authenticity.

The system operates to imitate the stylistic tone of legislative offices by requiring users to fill out a language questionnaire prior to onboarding. Answers to questions such as — How do you express agreement with a constituent who supports a bill? — influence both the system’s lexicon and rules for aggregation.

In addition, PoliScribe maintains a cognitive model for how the constituent might feel about a legislative development, termed constituent satisfaction, which influences the emotive content of the letter response. If a bill supported both by the constituent and their Representative is defeated on the House floor, for example, the system might use language expressing disappointment: e.g., Despite my best efforts, the bill failed on the House floor. If that same bill was instead approved by the House, the system might say: I am pleased to confirm the bill has passed the House of Representatives.

IV. ALIGNMENT STRATEGIES

Just as important, PoliScribe takes into account the policy perspective of the constituent, so that letter-responses are framed around a shared vocabulary and political outlook. Such alignment strategies are common in dialogue and likewise pertain to epistolary correspondence, which are just another form of conversational act (Altman, 1982).

Alignment is achieved by tagging bills with one of 220 topics appropriated from the Comparative Agendas Project (CAP), an organization that classifies legislation across democracies. Though CAP maintains a directory of coded bills, legislation can also be tagged independently through classification algorithms (Purpura and Hillard, 2006). PoliScribe next determines whether the bill is conservative, liberal, or bipartisan — primarily by considering the party affiliations of the bill’s authors and cosponsors.

These efforts allow PoliScribe to employ issue-specific language that aligns with the policy perspective of the constituent. For example, a letter to a supporter of a conservative bill tagged National Budget might employ language emphasizing fiscal prudence. By contrast, a letter to a constituent supporting a liberal bill tagged Labor Union might employ language emphasizing fair labor practices. Issue-specific language can be edited and approved by user offices, ensuring that the system’s rhetoric is consistent with their own policy outlook.

Tagging also enables PoliScribe to identify legislation that is related to bills that constituents write about. This allows the system to educate the constituent about the Representative’s vote record or emphasize areas of past agreement. This is particularly useful for engendering a sense of alignment when the Representative disagrees with the constituent or has not yet taken a public position on a piece of pending legislation, but has voted for thematically similar legislation in the past: e.g., I am still considering the merits of this legislation, but you will be happy to know that I voted for a similar bill last year that would…

V. CONCLUSIONS

PoliScribe has been in use by legislative offices since the beginning of 2019, with users reporting that the system has improved response times and has enabled more detailed responses to constituent letters. Essential has been the ability to accommodate the various stylistic preferences and affectations of individual elected officials, a level of customizability no doubt fundamental for any NLG system operating on behalf of distinct and forceful personalities.

REFERENCES

Janet Gurkin Altman. 1982. Epistolarity: Approaches to a Form. Ohio State University Press, Columbus.

Alexander Furnas. 2018. Legislative staff are spending an increasing amount of time on constituent services. LegBranch.org. Accessed: 2 July 2019.

Albert Gatt and Emiel Krahmer. 2018. Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation. In Journal of AI Research, 6l: 65-170.

Willem J.M. Levelt. 1989. Speaking: From Intention to Articulation. MIT Press, Cambridge.

Stephen Purpura and Dustin Hillard. 2006. Automated Classification of Congressional Legislation. In Proceedings of the 2006 International Conference on Digital Government Research: 219-225.

Ehud Reiter and Robert Dale. 1999. Building natural language generation systems. Cambridge University Press, New York.