Procedural Reading Comprehension with Attribute-Aware Context Flow

  title={Procedural Reading Comprehension with Attribute-Aware Context Flow},
  author={Aida Amini and Antoine Bosselut and Bhavana Dalvi and Yejin Choi and Hannaneh Hajishirzi},
Procedural texts often describe processes (e.g., photosynthesis and cooking) that happen over entities (e.g., light, food). In this paper, we introduce an algorithm for procedural reading comprehension by translating the text into a general formalism that represents processes as a sequence of transitions over entity attributes (e.g., location, temperature). Leveraging pre-trained language models, our model obtains entity-aware and attribute-aware representations of the text by joint prediction… 

Figures and Tables from this paper

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.

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.

Coalescing Global and Local Information for Procedural Text Understanding

A new model that builds entity- and timestep-aware input representations (local input) considering the whole context (global input) and jointly model the entity states with a structured prediction objective (global output) is proposed, which optimizes for both precision and recall.

Modeling Temporal-Modal Entity Graph for Procedural Multimodal Machine Comprehension

A novel Temporal-Modal Entity Graph (TMEG) is proposed to capture textual and visual entities and trace their temporal-modal evolution and a graph aggregation module is introduced to conduct graph encoding and reasoning.

Time-Stamped Language Model: Teaching Language Models to Understand The Flow of Events

A Time-Stamped Language Model (TSLM) is proposed to encode event information in LMs architecture by introducing the timestamp encoding to enable pre-trained transformer-based language models to be used on other QA benchmarks by adapting those to the procedural text understanding.

LEMON: Language-Based Environment Manipulation via Execution-Guided Pre-training

A general approach for language-based environment manipulation tasks, which can deal with various environments using the same generative language model, and an execution-guided pre-training strategy to inject prior knowledge of environments to the language model with a pure synthetic pre- training corpus are proposed.

Tiered Reasoning for Intuitive Physics: Toward Verifiable Commonsense Language Understanding

The empirical results show that while large LMs can achieve high end performance, they struggle to support their predictions with valid supporting evidence, and this paper introduces Tiered Reasoning for Intuitive Physics ( TRIP), a novel commonsense reasoning dataset with dense annotations that enable multi-tiered evaluation of machines’ reasoning process.

50 Ways to Bake a Cookie: Mapping the Landscape of Procedural Texts

This work proposes an unsupervised learning approach for summarizing multiple procedural texts into an intuitive graph representation, allowing users to easily explore commonalities and differences, and demonstrates the approach on recipes, a prominent example of procedural texts.

Factoring Statutory Reasoning as Language Understanding Challenges

Models for statutory reasoning are shown to benefit from the additional structure found in Prolog programs, improving on prior baselines, and the decomposition into subtasks facilitates finer-grained model diagnostics and clearer incremental progress.

FaVIQ: FAct Verification from Information-seeking Questions

This paper constructs a large-scale challenging fact verification dataset called FAVIQ, consisting of 188k claims derived from an existing corpus of ambiguous information-seeking questions, verified to be natural, contain little lexical bias, and require a complete understanding of the evidence for verification.



Building Dynamic Knowledge Graphs from Text using Machine Reading Comprehension

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.

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.

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 about Actions and State Changes by Injecting Commonsense Knowledge

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.

Reasoning Over Paragraph Effects in Situations

This work presents ROPES, a challenging benchmark for reading comprehension targeting Reasoning Over Paragraph Effects in Situations, and targets expository language describing causes and effects, as they have clear implications for new situations.

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.

Effective Use of Transformer Networks for Entity Tracking

This paper tests standard lightweight approaches for prediction with pre-trained transformers, and finds that these approaches underperforms even simple baselines, and shows that much stronger results can be attained by restructuring the input to guide the model to focus on a particular entity.

The NarrativeQA Reading Comprehension Challenge

A new dataset and set of tasks in which the reader must answer questions about stories by reading entire books or movie scripts are presented, designed so that successfully answering their questions requires understanding the underlying narrative rather than relying on shallow pattern matching or salience.

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.

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.