• Corpus ID: 13856836

Learning Biological Processes with Global Constraints

  title={Learning Biological Processes with Global Constraints},
  author={Aju Thalappillil Scaria and Jonathan Berant and Mengqiu Wang and Peter Clark and Justin Lewis and Brittany Harding and Christopher D. Manning},
Biological processes are complex phenomena involving a series of events that are related to one another through various relationships. [] Key Method We represent processes by graphs whose edges describe a set of temporal, causal and co-reference event-event relations, and characterize the structural properties of these graphs (e.g., the graphs are connected).

Figures and Tables from this paper

Learning Structures of Biological Processes with Joint Inference

This project aims to predict the events, entities associated with events, and event- event relations at the same time through joint inference in the hope of lowering cascading errors introduced from the pipeline framework, i.e. predict entities and inter-event relations based on the event prediction.

Knowledge-Enriched Event Causality Identification via Latent Structure Induction Networks

This work proposes a novel Latent Structure Induction Network (LSIN) to incorporate the external structural knowledge into this task and devise a Descriptive Graph Induction module to obtain and encode the graph-structured descriptive knowledge.

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.

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.

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.

Lexical Event Ordering with an Edge-Factored Model

This paper explores a lexical event ordering task, namely determining the likely temporal order of events based solely on the identity of their predicates and arguments, and proposes an “edgefactored” model for the task that decomposes over the edges of the event graph.

Causality Mining in Natural Languages Using Machine and Deep Learning Techniques: A Survey

A detailed taxonomy of causality mining from textual data is presented and popular ML and DL approaches with their comparative weaknesses and strengths, applications, popular datasets, and frameworks are discussed.

Improving Event Causality Recognition with Multiple Background Knowledge Sources Using Multi-Column Convolutional Neural Networks

It is empirically show that the combination of the neural network architecture and background knowledge significantly improves average precision, while the previous state-of-the-art method gains just a small benefit from such background knowledge.

Combining Formal and Distributional Models of Temporal and Intensional Semantics

It is shown how to closely integrate this information with theories of formal semantics, allowing complex compositional inferences such as is visiting! has arrived in but will leave, which will allow machine reading systems to understand not just what has happened, but when.

A study of the knowledge base requirements for passing an elementary science test

The analysis suggests that as well as fact extraction from text and statistically driven rule extraction, three other styles of automatic knowledge base construction (AKBC) would be useful: acquiring definitional knowledge, direct 'reading' of rules from texts that state them, and, given a particular representational framework, acquisition of specific instances of those models from text.




A system for extracting complex events among genes and proteins from biomedical literature, developed in context of the BioNLP’09 Shared Task on Event Extraction, and achieves the best performance on all three subtasks.

Event Extraction with Complex Event Classification Using Rich Features

An automatic event extraction system, which contains a model for complex events, by solving a classification problem with rich features, which outperforms the best system from the BioNLP'09 shared task challenge.

Joint Inference for Knowledge Extraction from Biomedical Literature

This paper presents the first joint approach for bio-event extraction that obtains state-of-the-art results and adopts a novel formulation by jointly predicting events and arguments, as well as individual dependency edges that compose the argument paths.

Event Extraction as Dependency Parsing

This work proposes a simple approach for the extraction of nested event structures by taking the tree of event-argument relations and using it directly as the representation in a reranking dependency parser, which provides a simple framework that captures global properties of both nested and flat event structures.

Predicting Globally-Coherent Temporal Structures from Texts via Endpoint Inference and Graph Decomposition

This paper proposes two innovations, inspired from work on temporal reasoning, that render an exact ILP inference viable in the general case, and shows that additional efficiency is gained by enforcing coherence on particular subsets of the entire temporal graphs.

Jointly Identifying Temporal Relations with Markov Logic

This work proposes a Markov Logic model that jointly identifies relations of all three relation types simultaneously and shows that this approach leads to about 2% higher accuracy for all three types of relations ---and to the best results for the task when compared to those of other machine learning based systems.

Probabilistic Frame Induction

This paper proposes the first probabilistic approach to frame induction, which incorporates frames, events, and participants as latent topics and learns those frame and event transitions that best explain the text.

Classifying Temporal Relations with Rich Linguistic Knowledge

This work aims to employ sophisticated linguistic knowledge derived from a variety of semantic and discourse relations, rather than focusing on morpho-syntactic knowledge, and leverage a novel combination of rule-based and learning-based approaches.

Joint Inference for Event Timeline Construction

An algorithmic approach is presented that jointly optimizes the temporal structure of a news article based on time intervals by coupling local classifiers that predict associations and temporal relations between pairs of temporal entities with global constraints.

Fast and Robust Joint Models for Biomedical Event Extraction

This work presents three joint models of increasing complexity designed to overcome cascading errors in pipelines of simple subtask-specific local classifiers extracting biomedical events from literature.