Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13)

Dmitry Ustalov, Swapna Somasundaran, Peter Jansen, Goran Glavaš, Martin Riedl, Mihai Surdeanu, Michalis Vazirgiannis (Editors)


Anthology ID:
D19-53
Month:
November
Year:
2019
Address:
Hong Kong
Venues:
EMNLP | TextGraphs | WS
SIG:
Publisher:
Association for Computational Linguistics
URL:
https://aclanthology.org/D19-53
DOI:
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
https://aclanthology.org/D19-53.pdf

pdf bib
Proceedings of the Thirteenth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-13)
Dmitry Ustalov | Swapna Somasundaran | Peter Jansen | Goran Glavaš | Martin Riedl | Mihai Surdeanu | Michalis Vazirgiannis

pdf bib
Relation Prediction for Unseen-Entities Using Entity-Word Graphs
Yuki Tagawa | Motoki Taniguchi | Yasuhide Miura | Tomoki Taniguchi | Tomoko Ohkuma | Takayuki Yamamoto | Keiichi Nemoto

Knowledge graphs (KGs) are generally used for various NLP tasks. However, as KGs still miss some information, it is necessary to develop Knowledge Graph Completion (KGC) methods. Most KGC researches do not focus on the Out-of-KGs entities (Unseen-entities), we need a method that can predict the relation for the entity pairs containing Unseen-entities to automatically add new entities to the KGs. In this study, we focus on relation prediction and propose a method 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. In the experiments, our method shows a significant improvement in the relation prediction for the entity pairs containing Unseen-entities.

pdf bib
Neural Speech Translation using Lattice Transformations and Graph Networks
Daniel Beck | Trevor Cohn | Gholamreza Haffari

Speech translation systems usually follow a pipeline approach, using word lattices as an intermediate representation. However, previous work assume access to the original transcriptions used to train the ASR system, which can limit applicability in real scenarios. In this work we propose an approach for speech translation through lattice transformations and neural models based on graph networks. Experimental results show that our approach reaches competitive performance without relying on transcriptions, while also being orders of magnitude faster than previous work.

pdf bib
Using Graphs for Word Embedding with Enhanced Semantic Relations
Matan Zuckerman | Mark Last

Word embedding algorithms have become a common tool in the field of natural language processing. While some, like Word2Vec, are based on sequential text input, others are utilizing a graph representation of text. In this paper, we introduce a new algorithm, named WordGraph2Vec, or in short WG2V, which combines the two approaches to gain the benefits of both. The algorithm uses a directed word graph to provide additional information for sequential text input algorithms. Our experiments on benchmark datasets show that text classification algorithms are nearly as accurate with WG2V as with other word embedding models while preserving more stable accuracy rankings.

pdf bib
Identifying Supporting Facts for Multi-hop Question Answering with Document Graph Networks
Mokanarangan Thayaparan | Marco Valentino | Viktor Schlegel | André Freitas

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. However, complex Question Answering (QA) typically requires multi-hop reasoning-i.e. the integration of supporting facts from different sources, to infer the correct answer. This paper proposes Document Graph Network (DGN), a message passing architecture for the identification of supporting facts over a graph-structured representation of text. The evaluation on HotpotQA shows that DGN obtains competitive results when compared to a reading comprehension baseline operating on raw text, confirming the relevance of structured representations for supporting multi-hop reasoning.

pdf bib
Essentia : Mining Domain-specific Paraphrases with Word-Alignment GraphsEssentia: Mining Domain-specific Paraphrases with Word-Alignment Graphs
Danni Ma | Chen Chen | Behzad Golshan | Wang-Chiew Tan

Paraphrases are important linguistic resources for a wide variety of NLP applications. Many techniques for automatic paraphrase mining from general corpora have been proposed. While these techniques are successful at discovering generic paraphrases, they often fail to identify domain-specific paraphrases (e.g., staff, concierge in the hospitality domain). This is because current techniques are often based on statistical methods, while domain-specific corpora are too small to fit statistical methods. In this paper, we present an unsupervised graph-based technique to mine paraphrases from a small set of sentences that roughly share the same topic or intent. Our system, Essentia, relies on word-alignment techniques to create a word-alignment graph that merges and organizes tokens from input sentences. The resulting graph is then used to generate candidate paraphrases. We demonstrate that our system obtains high quality paraphrases, as evaluated by crowd workers. We further show that the majority of the identified paraphrases are domain-specific and thus complement existing paraphrase databases.staff, concierge in the hospitality domain). This is because current techniques are often based on statistical methods, while domain-specific corpora are too small to fit statistical methods. In this paper, we present an unsupervised graph-based technique to mine paraphrases from a small set of sentences that roughly share the same topic or intent. Our system, Essentia, relies on word-alignment techniques to create a word-alignment graph that merges and organizes tokens from input sentences. The resulting graph is then used to generate candidate paraphrases. We demonstrate that our system obtains high quality paraphrases, as evaluated by crowd workers. We further show that the majority of the identified paraphrases are domain-specific and thus complement existing paraphrase databases.

pdf bib
Layerwise Relevance Visualization in Convolutional Text Graph Classifiers
Robert Schwarzenberg | Marc Hübner | David Harbecke | Christoph Alt | Leonhard Hennig

Representations in the hidden layers of Deep Neural Networks (DNN) are often hard to interpret since it is difficult to project them into an interpretable domain. Graph Convolutional Networks (GCN) allow this projection, but existing explainability methods do not exploit this fact, i.e. do not focus their explanations on intermediate states. In this work, we present a novel method that traces and visualizes features that contribute to a classification decision in the visible and hidden layers of a GCN. Our method exposes hidden cross-layer dynamics in the input graph structure. We experimentally demonstrate that it yields meaningful layerwise explanations for a GCN sentence classifier.

pdf bib
ASU at TextGraphs 2019 Shared Task : Explanation ReGeneration using Language Models and Iterative Re-RankingASU at TextGraphs 2019 Shared Task: Explanation ReGeneration using Language Models and Iterative Re-Ranking
Pratyay Banerjee

In this work we describe the system from Natural Language Processing group at Arizona State University for the TextGraphs 2019 Shared Task. The task focuses on Explanation Regeneration, an intermediate step towards general multi-hop inference on large graphs. Our approach consists of modeling the explanation regeneration task as a learning to rank problem, for which we use state-of-the-art language models and explore dataset preparation techniques. We utilize an iterative reranking based approach to further improve the rankings. Our system secured 2nd rank in the task with a mean average precision (MAP) of 41.3 % on the test set.

pdf bib
Chains-of-Reasoning at TextGraphs 2019 Shared Task : Reasoning over Chains of Facts for Explainable Multi-hop InferenceTextGraphs 2019 Shared Task: Reasoning over Chains of Facts for Explainable Multi-hop Inference
Rajarshi Das | Ameya Godbole | Manzil Zaheer | Shehzaad Dhuliawala | Andrew McCallum

This paper describes our submission to the shared task on Multi-hop Inference Explanation Regeneration in TextGraphs workshop at EMNLP 2019 (Jansen and Ustalov, 2019). Our system identifies chains of facts relevant to explain an answer to an elementary science examination question. To counter the problem of ‘spurious chains’ leading to ‘semantic drifts’, we train a ranker that uses contextualized representation of facts to score its relevance for explaining an answer to a question. Our system was ranked first w.r.t the mean average precision (MAP) metric outperforming the second best system by 14.95 points.

pdf bib
Graph-Based Semi-Supervised Learning for Natural Language Understanding
Zimeng Qiu | Eunah Cho | Xiaochun Ma | William Campbell

Semi-supervised learning is an efficient method to augment training data automatically from unlabeled data. Development of many natural language understanding (NLU) applications has a challenge where unlabeled data is relatively abundant while labeled data is rather limited. In this work, we propose transductive graph-based semi-supervised learning models as well as their inductive variants for NLU. We evaluate the approach’s applicability using publicly available NLU data and models. In order to find similar utterances and construct a graph, we use a paraphrase detection model. Results show that applying the inductive graph-based semi-supervised learning can improve the error rate of the NLU model by 5 %.

pdf bib
Graph Enhanced Cross-Domain Text-to-SQL GenerationSQL Generation
Siyu Huo | Tengfei Ma | Jie Chen | Maria Chang | Lingfei Wu | Michael Witbrock

Semantic parsing is a fundamental problem in natural language understanding, as it involves the mapping of natural language to structured forms such as executable queries or logic-like knowledge representations. Existing deep learning approaches for semantic parsing have shown promise on a variety of benchmark data sets, particularly on text-to-SQL parsing. However, most text-to-SQL parsers do not generalize to unseen data sets in different domains. In this paper, we propose a new cross-domain learning scheme to perform text-to-SQL translation and demonstrate its use on Spider, a large-scale cross-domain text-to-SQL data set. We improve upon a state-of-the-art Spider model, SyntaxSQLNet, by constructing a graph of column names for all databases and using graph neural networks to compute their embeddings. The resulting embeddings offer better cross-domain representations and SQL queries, as evidenced by substantial improvement on the Spider data set compared to SyntaxSQLNet.

pdf bib
Reasoning Over Paths via Knowledge Base Completion
Saatviga Sudhahar | Andrea Pierleoni | Ian Roberts

Reasoning over paths in large scale knowledge graphs is an important problem for many applications. In this paper we discuss a simple approach to automatically build and rank paths between a source and target entity pair with learned embeddings using a knowledge base completion model (KBC). We assembled a knowledge graph by mining the available biomedical scientific literature and extracted a set of high frequency paths to use for validation. We demonstrate that our method is able to effectively rank a list of known paths between a pair of entities and also come up with plausible paths that are not present in the knowledge graph. For a given entity pair we are able to reconstruct the highest ranking path 60 % of the time within the top 10 ranked paths and achieve 49 % mean average precision. Our approach is compositional since any KBC model that can produce vector representations of entities can be used.

pdf bib
Node Embeddings for Graph Merging : Case of Knowledge Graph Construction
Ida Szubert | Mark Steedman

Combining two graphs requires merging the nodes which are counterparts of each other. In this process errors occur, resulting in incorrect merging or incorrect failure to merge. We find a high prevalence of such errors when using AskNET, an algorithm for building Knowledge Graphs from text corpora. AskNET node matching method uses string similarity, which we propose to replace with vector embedding similarity. We explore graph-based and word-based embedding models and show an overall error reduction of from 56 % to 23.6 %, with a reduction of over a half in both types of incorrect node matching.

pdf bib
DBee : A Database for Creating and Managing Knowledge Graphs and EmbeddingsDBee: A Database for Creating and Managing Knowledge Graphs and Embeddings
Viktor Schlegel | André Freitas

This paper describes DBee, a database to support the construction of data-intensive AI applications. DBee provides a unique data model which operates jointly over large-scale knowledge graphs (KGs) and embedding vector spaces (VSs). This model supports queries which exploit the semantic properties of both types of representations (KGs and VSs). Additionally, DBee aims to facilitate the construction of KGs and VSs, by providing a library of generators, which can be used to create, integrate and transform data into KGs and VSs.