Mark Riedl


2020

pdf bib
Reducing Non-Normative Text Generation from Language Models
Xiangyu Peng | Siyan Li | Spencer Frazier | Mark Riedl
Proceedings of the 13th International Conference on Natural Language Generation

Large-scale, transformer-based language models such as GPT-2 are pretrained on diverse corpora scraped from the internet. Consequently, they are prone to generating non-normative text (i.e. in violation of social norms). We introduce a technique for fine-tuning GPT-2, using a policy gradient reinforcement learning technique and a normative text classifier to produce reward and punishment values. We evaluate our technique on five data sets using automated and human participant experiments. The normative text classifier is 81-90% accurate when compared to gold-standard human judgements of normative and non-normative generated text. Our normative fine-tuning technique is able to reduce non-normative text by 27-61%, depending on the data set.

2019

pdf bib
Toward Automated Quest Generation in Text-Adventure Games
Prithviraj Ammanabrolu | William Broniec | Alex Mueller | Jeremy Paul | Mark Riedl
Proceedings of the 4th Workshop on Computational Creativity in Language Generation

pdf bib
Transfer in Deep Reinforcement Learning Using Knowledge Graphs
Prithviraj Ammanabrolu | Mark Riedl
Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13)

Text adventure games, in which players must make sense of the world through text descriptions and declare actions through text descriptions, provide a stepping stone toward grounding action in language. Prior work has demonstrated that using a knowledge graph as a state representation and question-answering to pre-train a deep Q-network facilitates faster control policy learning. In this paper, we explore the use of knowledge graphs as a representation for domain knowledge transfer for training text-adventure playing reinforcement learning agents. Our methods are tested across multiple computer generated and human authored games, varying in domain and complexity, and demonstrate that our transfer learning methods let us learn a higher-quality control policy faster.

pdf bib
Guided Neural Language Generation for Automated Storytelling
Prithviraj Ammanabrolu | Ethan Tien | Wesley Cheung | Zhaochen Luo | William Ma | Lara Martin | Mark Riedl
Proceedings of the Second Workshop on Storytelling

Neural network based approaches to automated story plot generation attempt to learn how to generate novel plots from a corpus of natural language plot summaries. Prior work has shown that a semantic abstraction of sentences called events improves neural plot generation and and allows one to decompose the problem into: (1) the generation of a sequence of events (event-to-event) and (2) the transformation of these events into natural language sentences (event-to-sentence). However, typical neural language generation approaches to event-to-sentence can ignore the event details and produce grammatically-correct but semantically-unrelated sentences. We present an ensemble-based model that generates natural language guided by events. Our method outperforms the baseline sequence-to-sequence model. Additionally, we provide results for a full end-to-end automated story generation system, demonstrating how our model works with existing systems designed for the event-to-event problem.

pdf bib
Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning
Prithviraj Ammanabrolu | Mark Riedl
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

Text-based adventure games provide a platform on which to explore reinforcement learning in the context of a combinatorial action space, such as natural language. We present a deep reinforcement learning architecture that represents the game state as a knowledge graph which is learned during exploration. This graph is used to prune the action space, enabling more efficient exploration. The question of which action to take can be reduced to a question-answering task, a form of transfer learning that pre-trains certain parts of our architecture. In experiments using the TextWorld framework, we show that our proposed technique can learn a control policy faster than baseline alternatives. We have also open-sourced our code at https://github.com/rajammanabrolu/KG-DQN.

2018

pdf bib
A Simple and Effective Approach to the Story Cloze Test
Siddarth Srinivasan | Richa Arora | Mark Riedl
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)

In the Story Cloze Test, a system is presented with a 4-sentence prompt to a story, and must determine which one of two potential endings is the ‘right’ ending to the story. Previous work has shown that ignoring the training set and training a model on the validation set can achieve high accuracy on this task due to stylistic differences between the story endings in the training set and validation and test sets. Following this approach, we present a simpler fully-neural approach to the Story Cloze Test using skip-thought embeddings of the stories in a feed-forward network that achieves close to state-of-the-art performance on this task without any feature engineering. We also find that considering just the last sentence of the prompt instead of the whole prompt yields higher accuracy with our approach.