Sequential Decision-Making for Inline Text Autocomplete

• URL: http://arxiv.org/abs/2403.15502v2
• Date: Sat, 15 Jun 2024 18:02:51 GMT
• Title: Sequential Decision-Making for Inline Text Autocomplete
• Authors: Rohan Chitnis, Shentao Yang, Alborz Geramifard,
• Abstract summary: We study the problem of improving inline autocomplete suggestions in text entry systems. We use reinforcement learning to learn suggestion policies through repeated interactions with a target user.
• Score: 14.83046358936405
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autocomplete suggestions are fundamental to modern text entry systems, with applications in domains such as messaging and email composition. Typically, autocomplete suggestions are generated from a language model with a confidence threshold. However, this threshold does not directly take into account the cognitive load imposed on the user by surfacing suggestions, such as the effort to switch contexts from typing to reading the suggestion, and the time to decide whether to accept the suggestion. In this paper, we study the problem of improving inline autocomplete suggestions in text entry systems via a sequential decision-making formulation, and use reinforcement learning to learn suggestion policies through repeated interactions with a target user over time. This formulation allows us to factor cognitive load into the objective of training an autocomplete model, through a reward function based on text entry speed. We acquired theoretical and experimental evidence that, under certain objectives, the sequential decision-making formulation of the autocomplete problem provides a better suggestion policy than myopic single-step reasoning. However, aligning these objectives with real users requires further exploration. In particular, we hypothesize that the objectives under which sequential decision-making can improve autocomplete systems are not tailored solely to text entry speed, but more broadly to metrics such as user satisfaction and convenience.

Related papers

• Examining Racial Stereotypes in YouTube Autocomplete Suggestions [1.297210402524609]
  We examine how YouTube autocompletes serve as an information source for users exploring information about race. Using critical discourse analysis, we identify five major sociocultural contexts in which racial biases manifest.
  arXiv  Detail & Related papers  (2024-10-04T02:53:25Z)
• AutoSurvey: Large Language Models Can Automatically Write Surveys [77.0458309675818]
  This paper introduces AutoSurvey, a speedy and well-organized methodology for automating the creation of comprehensive literature surveys. Traditional survey paper creation faces challenges due to the vast volume and complexity of information. Our contributions include a comprehensive solution to the survey problem, a reliable evaluation method, and experimental validation demonstrating AutoSurvey's effectiveness.
  arXiv  Detail & Related papers  (2024-06-10T12:56:06Z)
• Long-Span Question-Answering: Automatic Question Generation and QA-System Ranking via Side-by-Side Evaluation [65.16137964758612]
  We explore the use of long-context capabilities in large language models to create synthetic reading comprehension data from entire books. Our objective is to test the capabilities of LLMs to analyze, understand, and reason over problems that require a detailed comprehension of long spans of text.
  arXiv  Detail & Related papers  (2024-05-31T20:15:10Z)
• Seasonality Based Reranking of E-commerce Autocomplete Using Natural Language Queries [15.37457156804212]
  Query autocomplete (QAC) also known as typeahead, suggests list of complete queries as user types prefix in the search box. One of the goals of typeahead is to suggest relevant queries to users which are seasonally important. We propose a neural network based natural language processing (NLP) algorithm to incorporate seasonality as a signal.
  arXiv  Detail & Related papers  (2023-08-03T21:14:25Z)
• TEMPERA: Test-Time Prompting via Reinforcement Learning [57.48657629588436]
  We propose Test-time Prompt Editing using Reinforcement learning (TEMPERA) In contrast to prior prompt generation methods, TEMPERA can efficiently leverage prior knowledge. Our method achieves 5.33x on average improvement in sample efficiency when compared to the traditional fine-tuning methods.
  arXiv  Detail & Related papers  (2022-11-21T22:38:20Z)
• The Effectiveness of Bidirectional Generative Patent Language Models [1.8275108630751844]
  A simplified design of the autocomplete function is proposed to increase effectiveness by more than 10%. With the new design, the effectiveness of autocomplete can reach more than 60%, which means that more than 60% of keystrokes can be saved by autocomplete. A key finding is that the autocomplete effectiveness of a model for the same text remains similar no matter where the calculation starts.
  arXiv  Detail & Related papers  (2022-09-04T03:12:27Z)
• What is wrong with you?: Leveraging User Sentiment for Automatic Dialog Evaluation [73.03318027164605]
  We propose to use information that can be automatically extracted from the next user utterance as a proxy to measure the quality of the previous system response. Our model generalizes across both spoken and written open-domain dialog corpora collected from real and paid users.
  arXiv  Detail & Related papers  (2022-03-25T22:09:52Z)
• POSSCORE: A Simple Yet Effective Evaluation of Conversational Search with Part of Speech Labelling [25.477834359694473]
  Conversational search systems, such as Google Assistant and Microsoft Cortana, provide a new search paradigm where users are allowed, via natural language dialogues, to communicate with search systems. We propose POSSCORE, a simple yet effective automatic evaluation method for conversational search. We show that our metrics can correlate with human preference, achieving significant improvements over state-of-the-art baseline metrics.
  arXiv  Detail & Related papers  (2021-09-07T12:31:29Z)
• Session-Aware Query Auto-completion using Extreme Multi-label Ranking [61.753713147852125]
  We take the novel approach of modeling session-aware query auto-completion as an e Multi-Xtreme Ranking (XMR) problem. We adapt a popular XMR algorithm for this purpose by proposing several modifications to the key steps in the algorithm. Our approach meets the stringent latency requirements for auto-complete systems while leveraging session information in making suggestions.
  arXiv  Detail & Related papers  (2020-12-09T17:56:22Z)
• Saying No is An Art: Contextualized Fallback Responses for Unanswerable Dialogue Queries [3.593955557310285]
  Most dialogue systems rely on hybrid approaches for generating a set of ranked responses. We design a neural approach which generates responses which are contextually aware with the user query. Our simple approach makes use of rules over dependency parses and a text-to-text transformer fine-tuned on synthetic data of question-response pairs.
  arXiv  Detail & Related papers  (2020-12-03T12:34:22Z)
• Automated Concatenation of Embeddings for Structured Prediction [75.44925576268052]
  We propose Automated Concatenation of Embeddings (ACE) to automate the process of finding better concatenations of embeddings for structured prediction tasks. We follow strategies in reinforcement learning to optimize the parameters of the controller and compute the reward based on the accuracy of a task model.
  arXiv  Detail & Related papers  (2020-10-10T14:03:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.