Be Consistent! Improving Procedural Text Comprehension using Label Consistency

@inproceedings{Du2019BeCI,
  title={Be Consistent! Improving Procedural Text Comprehension using Label Consistency},
  author={X. Du and Bhavana Dalvi Mishra and Niket Tandon and Antoine Bosselut and Wen-tau Yih and P. Clark and Claire Cardie},
  booktitle={NAACL},
  year={2019}
}
  • X. Du, Bhavana Dalvi Mishra, +4 authors Claire Cardie
  • Published in NAACL 2019
  • Computer Science
Our goal is procedural text comprehension, namely tracking how the properties of entities (e.g., their location) change with time given a procedural text (e.g., a paragraph about photosynthesis, a recipe. [...] Key Method We present a new learning framework that leverages label consistency during training, allowing consistency bias to be built into the model. Evaluation on a standard benchmark dataset for procedural text, ProPara (Dalvi et al., 2018), shows that our approach significantly improves prediction…Expand
Procedural Reasoning Networks for Understanding Multimodal Procedures
TLDR
This paper introduces a new entity-aware neural comprehension model augmented with external relational memory units and finds that this model learns effective dynamic representations of entities even though it does not use any supervision at the level of entity states. Expand
Understanding Procedural Text Using Interactive Entity Networks
TLDR
This paper proposes a novel Interactive Entity Network (IEN), which is a recurrent network with memory equipped cells for state tracking that outperforms state-of-the-art models by precisely capturing the interactions of multiple entities and explicitly leverage the relationship between entity interactions and subsequent state changes. Expand
Structured Tuning for Semantic Role Labeling
TLDR
This paper presents a structured tuning framework to improve models using softened constraints only at training time, which leverages the expressiveness of neural networks and provides supervision with structured loss components. Expand
Predicting State Changes in Procedural Text using Analogical Question Answering
Many of the changes in the world that happen over time are characterized by processes. Creating programs that comprehend procedural text (e.g. the stages of photosynthesis) is a crucial task inExpand
Joint Semantic Analysis with Document-Level Cross-Task Coherence Rewards
TLDR
A neural network architecture is presented for joint coreference resolution and semantic role labeling for English, and graph neural networks are trained to model the 'coherence' of the combined shallow semantic graph to encourage global coherence over the document and between semantic annotations. Expand
Measuring and Improving Consistency in Pretrained Language Models
TLDR
The creation of PARAREL, a high-quality resource of cloze-style query English paraphrases, and analysis of the representational spaces of PLMs suggest that they have a poor structure and are currently not suitable for representing knowledge in a robust way. Expand
Enabling Interactive Answering of Procedural Questions
TLDR
A mechanism to enable task oriented procedural question answering system for user assistance in English is presented and an answering “corpus” in a tree-form from unstructured document passages is created. Expand
Augmenting Neural Networks with First-order Logic
TLDR
This paper presents a novel framework for introducing declarative knowledge to neural network architectures in order to guide training and prediction, and shows that knowledge-augmented networks can strongly improve over baselines, especially in low-data regimes. Expand
Enriching a Model's Notion of Belief using a Persistent Memory
TLDR
This work adds a memory component a BeliefBank that records a model’s answers, and two mechanisms that use it to improve consistency among beliefs, and shows that, in a controlled experimental setting, these two mechanisms improve both accuracy and consistency. Expand
Learning To Segment Actions From Visual and Language Instructions via Differentiable Weak Sequence Alignment
We address the problem of unsupervised localization of task-relevant actions (key-steps) and feature learning in instructional videos using both visual and language instructions. Our key observationExpand
...
1
2
...

References

SHOWING 1-10 OF 27 REFERENCES
Tracking State Changes in Procedural Text: a Challenge Dataset and Models for Process Paragraph Comprehension
TLDR
A new dataset and models for comprehending paragraphs about processes, an important genre of text describing a dynamic world, are presented and two new neural models that exploit alternative mechanisms for state prediction are introduced, in particular using LSTM input encoding and span prediction. Expand
Reasoning about Actions and State Changes by Injecting Commonsense Knowledge
TLDR
This paper shows how the predicted effects of actions in the context of a paragraph can be improved in two ways: by incorporating global, commonsense constraints (e.g., a non-existent entity cannot be destroyed), and by biasing reading with preferences from large-scale corpora. Expand
Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension
TLDR
A neural machine-reading model that constructs dynamic knowledge graphs recurrently for each step of the described procedure, and uses them to track the evolving states of participant entities to present some evidence that the model’s knowledge graphs help it to impose commonsense constraints on its predictions. Expand
A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task
TLDR
A thorough examination of this new reading comprehension task by creating over a million training examples by pairing CNN and Daily Mail news articles with their summarized bullet points, and showing that a neural network can be trained to give good performance on this task. Expand
Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks
TLDR
This work argues for the usefulness of a set of proxy tasks that evaluate reading comprehension via question answering, and classify these tasks into skill sets so that researchers can identify (and then rectify) the failings of their systems. Expand
Mise en Place: Unsupervised Interpretation of Instructional Recipes
TLDR
An unsupervised hard EM approach to automatically mapping instructional recipes to action graphs, which define what actions should be performed on which objects and in what order, which incorporates aspects of procedural semantics and world knowledge. Expand
Modeling Biological Processes for Reading Comprehension
TLDR
This paper focuses on a new reading comprehension task that requires complex reasoning over a single document, and demonstrates that answering questions via predicted structures substantially improves accuracy over baselines that use shallower representations. Expand
Query-Reduction Networks for Question Answering
TLDR
Query-Reduction Network (QRN), a variant of Recurrent Neural Network (RNN) that effectively handles both short-term and long-term sequential dependencies to reason over multiple facts, is proposed. Expand
Globally Coherent Text Generation with Neural Checklist Models
TLDR
The neural checklist model is presented, a recurrent neural network that models global coherence by storing and updating an agenda of text strings which should be mentioned somewhere in the output, and demonstrates high coherence with greatly improved semantic coverage of the agenda. Expand
AllenNLP: A Deep Semantic Natural Language Processing Platform
TLDR
AllenNLP is designed to support researchers who want to build novel language understanding models quickly and easily and provides a flexible data API that handles intelligent batching and padding, and a modular and extensible experiment framework that makes doing good science easy. Expand
...
1
2
3
...