Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13)
Transfer in Deep Reinforcement Learning Using Knowledge Graphs (D19-53)
Copied to clipboard
| Challenge: | Text adventure games provide a stepping stone toward grounding action in language . prior work demonstrated that using a knowledge graph as a state representation facilitates faster control policy learning. |
| Approach: | They propose to use knowledge graphs as a representation for domain knowledge transfer for training text-adventure playing reinforcement learning agents. |
| Outcome: | The proposed methods let us learn a higher-quality control policy faster in text adventure games. |
Relation Prediction for Unseen-Entities Using Entity-Word Graphs (D19-53)
Copied to clipboard
Yuki Tagawa, Motoki Taniguchi, Yasuhide Miura, Tomoki Taniguchi, Tomoko Ohkuma, Takayuki Yamamoto, Keiichi Nemoto
| Challenge: | Knowledge graphs (KGs) are incomplete and miss some information. |
| Approach: | They propose to learn entity representations via a graph structure that uses Seen-entities, Unseen-Entities and words as nodes created from the descriptions of all entities. |
| Outcome: | The proposed method improves relation prediction for the entity pairs containing Unseen-entities. |
Scalable graph-based method for individual named entity identification (D19-53)
Copied to clipboard
| Challenge: | Named entity recognition (NED) is a method for identifying named entities within a knowledge base. |
| Approach: | They propose a method for individual identification requiring few annotated data samples. |
| Outcome: | The proposed method is well-motivated for integration in real systems. |
Neural Speech Translation using Lattice Transformations and Graph Networks (D19-53)
Copied to clipboard
| Challenge: | Existing work on end-to-end systems bypass the need for intermediate representations, but this approach is limited in practical applications. |
| Approach: | They propose a lattice-tosequence model which uses lattics as encoders and graph networks to address two problems by applying latticae transformations and a neural model. |
| Outcome: | The proposed model beats pipeline approaches while being orders of magnitude faster than previous work. |
Using Graphs for Word Embedding with Enhanced Semantic Relations (D19-53)
Copied to clipboard
| Challenge: | Word embedding algorithms are based on sequential text input, while others are utilizing a graph representation of text. |
| Approach: | They propose a word embedding algorithm based on a directed word graph to provide additional information for sequential text input algorithms. |
| Outcome: | The proposed algorithm is based on a directed word graph to provide additional information for sequential text input algorithms. |
Identifying Supporting Facts for Multi-hop Question Answering with Document Graph Networks (D19-53)
Copied to clipboard
| Challenge: | Recent advances in reading comprehension have resulted in models that surpass human performance when the answer is contained in a single, continuous passage of text. |
| Approach: | They propose a document-structured message passing architecture for the identification of supporting facts over a graph-structure based representation of text. |
| Outcome: | The proposed model outperforms a baseline reading comprehension test on raw text and shows that it is relevant for multi-hop reasoning. |
Essentia: Mining Domain-specific Paraphrases with Word-Alignment Graphs (D19-53)
Copied to clipboard
| Challenge: | Existing methods for mining general-purpose paraphrases are often based on statistical methods, but domain-specific corpora are too small to fit statistical methods. |
| Approach: | They propose a method to mine paraphrases from a small set of sentences that roughly share the same topic or intent. |
| Outcome: | The proposed method obtains high quality paraphrases as evaluated by crowd workers. |
Layerwise Relevance Visualization in Convolutional Text Graph Classifiers (D19-53)
Copied to clipboard
| Challenge: | Existing explainability methods do not focus on intermediate states in hidden layers of Deep Neural Networks (DNNs). |
| Approach: | They propose a method that visits visible and hidden layers of a deep neural network and projects them onto the interpretable domain. |
| Outcome: | The proposed method yields meaningful layerwise explanations for a GCN sentence classifier. |
TextGraphs 2019 Shared Task on Multi-Hop Inference for Explanation Regeneration (D19-53)
Copied to clipboard
| Challenge: | Detailed extended analyses of all submitted systems showed large relative improvements in accessing the most challenging multi-hop inference problems, while absolute performance remains low. |
| Approach: | The Shared Task on Multi-Hop Inference for Explanation Regeneration asks participants to regenerate detailed gold explanations for elementary science questions by selecting facts from a knowledge base of semi-structured tables. |
| Outcome: | The top-performing system achieved a mean average precision of 0.56 . the task combines facts from a knowledge base and supervised training data . |
ASU at TextGraphs 2019 Shared Task: Explanation ReGeneration using Language Models and Iterative Re-Ranking (D19-53)
Copied to clipboard
| Challenge: | Explanation Regeneration task is an intermediate step towards general multi-hop inference on large graphs. |
| Approach: | They propose a system that performs multi-hop inference and ranks a set of explanatory facts for a given elementary science question and correct answer pair. |
| Outcome: | The proposed system secured 2nd rank in the text graphs 2019 shared task with a mean average precision (MAP) of 41.3% on the test set. |
Red Dragon AI at TextGraphs 2019 Shared Task: Language Model Assisted Explanation Generation (D19-53)
Copied to clipboard
| Challenge: | The TextGraphs-13 Shared Task on Explanation Regeneration asked participants to develop methods to reconstruct gold explanations for elementary science questions. |
| Approach: | The TextGraphs-13 Shared Task on Explanation Regeneration asked participants to develop methods to reconstruct gold explanations for elementary science questions. |
| Outcome: | The Explanation Regeneration shared task asked participants to develop methods to reconstruct gold explanations for elementary science questions. |
Team SVMrank: Leveraging Feature-rich Support Vector Machines for Ranking Explanations to Elementary Science Questions (D19-53)
Copied to clipboard
| Challenge: | TextGraphs 2019 Shared Task on Multi-Hop Inference for Explanation Regeneration tackles explanation generation for elementary science questions. |
| Approach: | They propose a hybrid pipelined machine learning model and rule-based system to address MIER-19 . they use a featurerich learning-to-rank machine learning and a rule-driven system to rerank the LTR model predictions. |
| Outcome: | The proposed model was ranked fourth in the evaluation, close to the second and third ranked teams, achieving 39.4% MAP. |
Chains-of-Reasoning at TextGraphs 2019 Shared Task: Reasoning over Chains of Facts for Explainable Multi-hop Inference (D19-53)
Copied to clipboard
| Challenge: | EMNLP 2019 shared task on 'Multi-hop Inference Explanation Regeneration' identifies chains of facts relevant to explain an answer to an elementary science examination question. |
| Approach: | They propose a system that identifies chains of facts relevant to explain an answer to an elementary science examination question. |
| Outcome: | The proposed system outperforms the second best system by 14.95 points on the mean average precision (MAP) metric. |
Joint Semantic and Distributional Word Representations with Multi-Graph Embeddings (D19-53)
Copied to clipboard
| Challenge: | Prior work has shown that word embeddings can be improved by using semantic knowledge-bases. |
| Approach: | They propose a way to combine distributional and semantic information while preserving lexical information of co-occurrences of words. |
| Outcome: | The proposed method improves word embeddings on a variety of word similarities. |
Evaluating Research Novelty Detection: Counterfactual Approaches (D19-53)
Copied to clipboard
| Challenge: | Despite its importance, this direction of research has not been explored as much. |
| Approach: | They propose to use counterfactual simulations to evaluate paper novelty detection models . they ask models to differentiate papers at time t and counterf actual paper from future time . |
| Outcome: | The proposed models can be compared against a set of papers with a given date and with different annotations. |
Do Sentence Interactions Matter? Leveraging Sentence Level Representations for Fake News Classification (D19-53)
Copied to clipboard
| Challenge: | Existing methods to distinguish between trusted and fake news articles lack feature engineering . et al. (2009) define fake news as the one which deliberately exposes real-world individuals, organisations and events to ridicule. |
| Approach: | They propose a graph neural network-based model which captures sentence interactions within a document. |
| Outcome: | The proposed model beats baselines and achieves state-of-the-art accuracy on existing datasets. |
Faceted Hierarchy: A New Graph Type to Organize Scientific Concepts and a Construction Method (D19-53)
Copied to clipboard
| Challenge: | faceted concept hierarchy is a structure of parent-child relationships . concepts are expected to be organized in a hierarchical structure for student learning . |
| Approach: | They propose a faceted concept hierarchy that aims to build facets from scientific literature. |
| Outcome: | The proposed hierarchy is more complete than "type-of" relations, and resolves conflicts by maintaining the acyclic structure of a hierarchy. |
Graph-Based Semi-Supervised Learning for Natural Language Understanding (D19-53)
Copied to clipboard
| Challenge: | Semi-supervised learning is an efficient method to augment training data from unlabeled data. |
| Approach: | They propose semi-supervised learning models and their inductive variants for NLU and use them to find similar utterances and construct a graph. |
| Outcome: | The proposed model improves the error rate of the model by 5% using publicly available NLU data and models. |
Graph Enhanced Cross-Domain Text-to-SQL Generation (D19-53)
Copied to clipboard
| Challenge: | Existing deep learning approaches for semantic parsing do not generalize to unseen data sets . existing benchmarks have shown text-to-SQL parsers do not generally perform well to unsen SQL queries. |
| Approach: | They propose a new cross-domain learning scheme to perform text-to-SQL translation . they demonstrate its use on a large-scale cross- domain text- to-Sql data set Spider . |
| Outcome: | The proposed learning scheme improves on a large-scale text-to-SQL data set. |
Reasoning Over Paths via Knowledge Base Completion (D19-53)
Copied to clipboard
| Challenge: | Existing methods to predict missing links in knowledge graphs are lacking. |
| Approach: | They propose a method to automatically rank paths between a source and target entity pair using a knowledge base completion model. |
| Outcome: | The proposed method can rank and rank paths in biomedical knowledge graphs with a KBC model. |
Node Embeddings for Graph Merging: Case of Knowledge Graph Construction (D19-53)
Copied to clipboard
| Challenge: | Combining two graphs requires merging the nodes which are counterparts of each other. In this process errors occur, resulting in incorrect merging or failure to merge. |
| Approach: | They propose to replace string similarity with vector embedding similarity to reduce errors when merging two graphs . they propose to use graph-based and word-based embeddable graph embeddances to obtain graph node embeddations. |
| Outcome: | The proposed algorithm reduces errors in merging two graphs with a corpus level one graph using string similarity and vector embedding similarity. |
DBee: A Database for Creating and Managing Knowledge Graphs and Embeddings (D19-53)
Copied to clipboard
| Challenge: | DBee provides a data model which operates over knowledge graphs and embedding vector spaces . |
| Approach: | They describe a database which provides a data model which exploits the semantic properties of large-scale knowledge graphs and embedding vector spaces. |
| Outcome: | The proposed model exploits the semantic properties of both types of representations. |
A Constituency Parsing Tree based Method for Relation Extraction from Abstracts of Scholarly Publications (D19-53)
Copied to clipboard
| Challenge: | Existing methods for relation extraction rely on lexical patterns and dependency templates. |
| Approach: | They propose a rule-based method for extracting entity networks from scientific literature . they use syntactic features of constituent parsing trees to extract and construct graphs . |
| Outcome: | The proposed method outperforms state-of-the-art methods in several cases. |