Reasoning about Actions and State Changes by Injecting Commonsense Knowledge

  title={Reasoning about Actions and State Changes by Injecting Commonsense Knowledge},
  author={Niket Tandon and Bhavana Dalvi and Joel Grus and Wen-tau Yih and Antoine Bosselut and Peter Clark},
  booktitle={Conference on Empirical Methods in Natural Language Processing},
Comprehending procedural text, e.g., a paragraph describing photosynthesis, requires modeling actions and the state changes they produce, so that questions about entities at different timepoints can be answered. [] Key Method Unlike earlier methods, we treat the problem as a neural structured prediction task, allowing hard and soft constraints to steer the model away from unlikely predictions. We show that the new model significantly outperforms earlier systems on a benchmark dataset for procedural text…

Figures and Tables from this paper

Predicting State Changes in Procedural Text using Analogical Question Answering

A novel approach that uses analogical question answering to predict what state changes affect entities in a paragraph describing a process, starting from the hypothesis that human level QA requires multiple layers of rich, relational representations.

Everything Happens for a Reason: Discovering the Purpose of Actions in Procedural Text

This work presents a new model (XPAD) that biases effect predictions towards those that explain more of the actions in the paragraph and are more plausible with respect to background knowledge, and extends an existing benchmark dataset for procedural text comprehension, ProPara, by adding the new task of explaining actions by predicting their dependencies.

Reasoning over Entity-Action-Location Graph for Procedural Text Understanding

This paper proposes a novel approach (REAL) to procedural text understanding, where a general framework is built to systematically model the entity-entity, entity-action, and entity-location relations using a graph neural network and develops algorithms for graph construction, representation learning, and state and location tracking.

Procedural Reasoning Networks for Understanding Multimodal Procedures

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.

Temporal Reasoning on Implicit Events from Distant Supervision

A neuro-symbolic temporal reasoning model, SymTime, is proposed, which exploits distant supervision signals from large-scale text and uses temporal rules to combine start times and durations to infer end times and generalizes to other temporal reasoning tasks.

Knowledge-Aware Procedural Text Understanding with Multi-Stage Training

A novel KnOwledge-Aware proceduraL text understAnding (KoaLa) model is proposed, which effectively leverages multiple forms of external knowledge in this task of procedural text understanding and achieves state-of-the-art performance in comparison to various baselines.

Social Commonsense Reasoning with Multi-Head Knowledge Attention

This work proposes a novel multi-head knowledge attention model that encodes semi-structured commonsense inference rules and learns to incorporate them in a transformer-based reasoning cell, and is the first to demonstrate that a model that learns to perform counterfactual reasoning helps predicting the best explanation in an abductive reasoning task.

Be Consistent! Improving Procedural Text Comprehension using Label Consistency

This work presents a new learning framework that leverages label consistency during training, allowing consistency bias to be built into the model and significantly improves prediction performance over prior state-of-the-art systems.

Procedural Reading Comprehension with Attribute-Aware Context Flow

An algorithm for procedural reading comprehension is introduced by translating the text into a general formalism that represents processes as a sequence of transitions over entity attributes (e.g., location, temperature).

Life is a Circus and We are the Clowns: Automatically Finding Analogies between Situations and Processes

An interpretable, scalable algorithm is developed that can extract analogies from a large dataset of procedural texts, achieving 79% precision, and it is demonstrated that the algorithm is robust to paraphrasing the input texts.



What Happened? Leveraging VerbNet to Predict the Effects of Actions in Procedural Text

This work leverages VerbNet to build a rulebase of the preconditions and effects of actions, and uses it along with commonsense knowledge of persistence to answer questions about change in paragraphs describing processes.

Tracking State Changes in Procedural Text: a Challenge Dataset and Models for Process Paragraph Comprehension

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.

Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks

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.

Mise en Place: Unsupervised Interpretation of Instructional Recipes

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.

Simulating Action Dynamics with Neural Process Networks

This work introduces Neural Process Networks to understand procedural text through (neural) simulation of action dynamics, and complements existing memory architectures with dynamic entity tracking by explicitly modeling actions as state transformers.

Tracking the World State with Recurrent Entity Networks

The EntNet sets a new state-of-the-art on the bAbI tasks, and is the first method to solve all the tasks in the 10k training examples setting, and can generalize past its training horizon.

Bidirectional Attention Flow for Machine Comprehension

The BIDAF network is introduced, a multi-stage hierarchical process that represents the context at different levels of granularity and uses bi-directional attention flow mechanism to obtain a query-aware context representation without early summarization.

Query-Reduction Networks for Question Answering

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.

Neural Semantic Parsing with Type Constraints for Semi-Structured Tables

A new semantic parsing model for answering compositional questions on semi-structured Wikipedia tables with a state-of-the-art accuracy and type constraints and entity linking are valuable components to incorporate in neural semantic parsers.

Modeling Biological Processes for Reading Comprehension

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.