LEATHER: A Framework for Learning to Generate Human-like Text in Dialogue

• URL: http://arxiv.org/abs/2210.07777v1
• Date: Fri, 14 Oct 2022 13:05:11 GMT
• Title: LEATHER: A Framework for Learning to Generate Human-like Text in Dialogue
• Authors: Anthony Sicilia and Malihe Alikhani
• Abstract summary: We propose a new theoretical framework for learning to generate text in dialogue. Compared to existing theories of learning, our framework allows for analysis of the multi-faceted goals inherent to text-generation.
• Score: 15.102346715690755
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Algorithms for text-generation in dialogue can be misguided. For example, in task-oriented settings, reinforcement learning that optimizes only task-success can lead to abysmal lexical diversity. We hypothesize this is due to poor theoretical understanding of the objectives in text-generation and their relation to the learning process (i.e., model training). To this end, we propose a new theoretical framework for learning to generate text in dialogue. Compared to existing theories of learning, our framework allows for analysis of the multi-faceted goals inherent to text-generation. We use our framework to develop theoretical guarantees for learners that adapt to unseen data. As an example, we apply our theory to study data-shift within a cooperative learning algorithm proposed for the GuessWhat?! visual dialogue game. From this insight, we propose a new algorithm, and empirically, we demonstrate our proposal improves both task-success and human-likeness of the generated text. Finally, we show statistics from our theory are empirically predictive of multiple qualities of the generated dialogue, suggesting our theory is useful for model-selection when human evaluations are not available.

Related papers

• Learning to Generate Equitable Text in Dialogue from Biased Training Data [15.102346715690755]
  A dialogue system's decision-making process and generated responses are crucial for user engagement, satisfaction, and task achievement. We use theories of computational learning to study this problem.
  arXiv  Detail & Related papers  (2023-07-10T01:44:13Z)
• Opportunities and Challenges in Neural Dialog Tutoring [54.07241332881601]
  We rigorously analyze various generative language models on two dialog tutoring datasets for language learning. We find that although current approaches can model tutoring in constrained learning scenarios, they perform poorly in less constrained scenarios. Our human quality evaluation shows that both models and ground-truth annotations exhibit low performance in terms of equitable tutoring.
  arXiv  Detail & Related papers  (2023-01-24T11:00:17Z)
• An Inclusive Notion of Text [69.36678873492373]
  We argue that clarity on the notion of text is crucial for reproducible and generalizable NLP. We introduce a two-tier taxonomy of linguistic and non-linguistic elements that are available in textual sources and can be used in NLP modeling.
  arXiv  Detail & Related papers  (2022-11-10T14:26:43Z)
• MOCHA: A Multi-Task Training Approach for Coherent Text Generation from Cognitive Perspective [22.69509556890676]
  We propose a novel multi-task training strategy for coherent text generation grounded on the cognitive theory of writing. We extensively evaluate our model on three open-ended generation tasks including story generation, news article writing and argument generation.
  arXiv  Detail & Related papers  (2022-10-26T11:55:41Z)
• Modeling Non-Cooperative Dialogue: Theoretical and Empirical Insights [11.462075538526703]
  We investigate the ability of agents to identify non-cooperative interlocutors while completing a concurrent visual-dialogue task. We use the tools of learning theory to develop a theoretical model for identifying non-cooperative interlocutors and apply this theory to analyze different communication strategies.
  arXiv  Detail & Related papers  (2022-07-15T02:08:41Z)
• Revise and Resubmit: An Intertextual Model of Text-based Collaboration in Peer Review [52.359007622096684]
  Peer review is a key component of the publishing process in most fields of science. Existing NLP studies focus on the analysis of individual texts. editorial assistance often requires modeling interactions between pairs of texts.
  arXiv  Detail & Related papers  (2022-04-22T16:39:38Z)
• An Attention-Based Model for Predicting Contextual Informativeness and Curriculum Learning Applications [11.775048147405725]
  We develop models for estimating contextual informativeness, focusing on the instructional aspect of sentences. We show how our model identifies key contextual elements in a sentence that are likely to contribute most to a reader's understanding of the target word. We believe our results open new possibilities for applications that support language learning for both human and machine learners.
  arXiv  Detail & Related papers  (2022-04-21T05:17:49Z)
• Deep Reinforcement Learning with Stacked Hierarchical Attention for Text-based Games [64.11746320061965]
  We study reinforcement learning for text-based games, which are interactive simulations in the context of natural language. We aim to conduct explicit reasoning with knowledge graphs for decision making, so that the actions of an agent are generated and supported by an interpretable inference procedure. We extensively evaluate our method on a number of man-made benchmark games, and the experimental results demonstrate that our method performs better than existing text-based agents.
  arXiv  Detail & Related papers  (2020-10-22T12:40:22Z)
• Concept Learners for Few-Shot Learning [76.08585517480807]
  We propose COMET, a meta-learning method that improves generalization ability by learning to learn along human-interpretable concept dimensions. We evaluate our model on few-shot tasks from diverse domains, including fine-grained image classification, document categorization and cell type annotation.
  arXiv  Detail & Related papers  (2020-07-14T22:04:17Z)
• Emergence of Pragmatics from Referential Game between Theory of Mind Agents [64.25696237463397]
  We propose an algorithm, using which agents can spontaneously learn the ability to "read between lines" without any explicit hand-designed rules. We integrate the theory of mind (ToM) in a cooperative multi-agent pedagogical situation and propose an adaptive reinforcement learning (RL) algorithm to develop a communication protocol.
  arXiv  Detail & Related papers  (2020-01-21T19:37:33Z)

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.