Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation

Hu, Zhiting; Shi, Haoran; Tan, Bowen; Wang, Wentao; Yang, Zichao; Zhao, Tiancheng; He, Junxian; Qin, Lianhui; Wang, Di; Ma, Xuezhe; Liu, Zhengzhong; Liang, Xiaodan; Zhu, Wangrong; Sachan, Devendra Singh; Xing, Eric P.

doi:10.18653/v1/p19-3027

Cited by 38 publications

(28 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We largely follow the same training and inference setups as in Radford et al (2018) for the GPT model and Radford et al (2019) for the GPT2 variants. Experiments are implemented with the text generation toolkit Texar (Hu et al, 2019). We provide more details in Appendix B.…”

Section: Hyperparametersmentioning

confidence: 99%

Counterfactual Story Reasoning and Generation

Qin¹,

Bosselut²,

Holtzman³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

Self Cite

View full text Add to dashboard Cite

Counterfactual reasoning requires predicting how alternative events, contrary to what actually happened, might have resulted in different outcomes. Despite being considered a necessary component of AI-complete systems, few resources have been developed for evaluating counterfactual reasoning in narratives.In this paper, we propose Counterfactual Story Rewriting: given an original story and an intervening counterfactual event, the task is to minimally revise the story to make it compatible with the given counterfactual event. Solving this task will require deep understanding of causal narrative chains and counterfactual invariance, and integration of such story reasoning capabilities into conditional language generation models.We present TIMETRAVEL, a new dataset of 29,849 counterfactual rewritings, each with the original story, a counterfactual event, and human-generated revision of the original story compatible with the counterfactual event.Additionally, we include 80,115 counterfactual "branches" without a rewritten storyline to support future work on semior un-supervised approaches to counterfactual story rewriting.Finally, we evaluate the counterfactual rewriting capacities of several competitive baselines based on pretrained language models, and assess whether common overlap and model-based automatic metrics for text generation correlate well with human scores for counterfactual rewriting.

show abstract

Section: Hyperparametersmentioning

confidence: 99%

Counterfactual Story Reasoning and Generation

Qin¹,

Bosselut²,

Holtzman³

et al. 2019

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conferen

Self Cite

View full text Add to dashboard Cite

show abstract

“…For fair comparison, we use Texar Hu et al (2018) as our codebase to implement all proposed methods and baselines, and to compared models for IWSLT 2014 and gigawords. The performance of our implementation is at least comparable with the reported results.…”

Section: Datasets and Setupmentioning

confidence: 99%

“…Table 4 shows performance comparisons of seven baselines and our model. We implement all baseline models on Texar Hu et al (2018) under the same setup as ours. Our model achieves the highest score on the test dataset on ROUGE-1, -2, -L metrics consistently.…”

Section: Abstractive Summarizationmentioning

confidence: 99%

Sequence Generation with Optimal-Transport-Enhanced Reinforcement Learning

Chen

Bai

Tao

et al. 2020

AAAI

View full text Add to dashboard Cite

Reinforcement learning (RL) has been widely used to aid training in language generation. This is achieved by enhancing standard maximum likelihood objectives with user-specified reward functions that encourage global semantic consistency. We propose a principled approach to address the difficulties associated with RL-based solutions, namely, high-variance gradients, uninformative rewards and brittle training. By leveraging the optimal transport distance, we introduce a regularizer that significantly alleviates the above issues. Our formulation emphasizes the preservation of semantic features, enabling end-to-end training instead of ad-hoc fine-tuning, and when combined with RL, it controls the exploration space for more efficient model updates. To validate the effectiveness of the proposed solution, we perform a comprehensive evaluation covering a wide variety of NLP tasks: machine translation, abstractive text summarization and image caption, with consistent improvements over competing solutions.

show abstract

“…It is built in C++ and designed for fast training in multi-GPU systems. Texar (Hu et al, 2018) is a text generation toolkit affiliated with Carnegie Mellon University, featuring a similar emphasis on modularity to ICE-CAPS. It includes reinforcement learning capabilities alongside its sequence modelling tools.…”

Section: Related Toolkitsmentioning

confidence: 99%

Microsoft Icecaps: An Open-Source Toolkit for Conversation Modeling

Shiv¹,

Quirk

Suri

et al. 2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: System Demonstrations

View full text Add to dashboard Cite

The Intelligent Conversation Engine: Code and Pre-trained Systems (Microsoft ICECAPS) is an upcoming open-source natural language processing repository. ICECAPS wraps Tensor-Flow functionality in a modular componentbased architecture, presenting an intuitive and flexible paradigm for constructing sophisticated learning setups. Capabilities include multitask learning between models with shared parameters, upgraded language model decoding features, a range of built-in architectures, and a user-friendly data processing pipeline. The system is targeted toward conversational tasks, exploring diverse response generation, coherence, and knowledge grounding. ICECAPS also provides pretrained conversational models that can be either used directly or loaded for fine-tuning or bootstrapping other models; these models power an online demo of our framework.

show abstract

Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generation

Cited by 38 publications

References 57 publications

Counterfactual Story Reasoning and Generation

Counterfactual Story Reasoning and Generation

Sequence Generation with Optimal-Transport-Enhanced Reinforcement Learning

Microsoft Icecaps: An Open-Source Toolkit for Conversation Modeling

Contact Info

Product

Resources

About