Gus Hahn-Powell

Also published as: Gustave Hahn-Powell


pdf bib
Exploring Interpretability in Event Extraction: Multitask Learning of a Neural Event Classifier and an Explanation Decoder
Zheng Tang | Gus Hahn-Powell | Mihai Surdeanu
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop

We propose an interpretable approach for event extraction that mitigates the tension between generalization and interpretability by jointly training for the two goals. Our approach uses an encoder-decoder architecture, which jointly trains a classifier for event extraction, and a rule decoder that generates syntactico-semantic rules that explain the decisions of the event classifier. We evaluate the proposed approach on three biomedical events and show that the decoder generates interpretable rules that serve as accurate explanations for the event classifier’s decisions, and, importantly, that the joint training generally improves the performance of the event classifier. Lastly, we show that our approach can be used for semi-supervised learning, and that its performance improves when trained on automatically-labeled data generated by a rule-based system.

pdf bib
Odinson: A Fast Rule-based Information Extraction Framework
Marco A. Valenzuela-Escárcega | Gus Hahn-Powell | Dane Bell
Proceedings of the 12th Language Resources and Evaluation Conference

We present Odinson, a rule-based information extraction framework, which couples a simple yet powerful pattern language that can operate over multiple representations of text, with a runtime system that operates in near real time. In the Odinson query language, a single pattern may combine regular expressions over surface tokens with regular expressions over graphs such as syntactic dependencies. To guarantee the rapid matching of these patterns, our framework indexes most of the necessary information for matching patterns, including directed graphs such as syntactic dependencies, into a custom Lucene index. Indexing minimizes the amount of expensive pattern matching that must take place at runtime. As a result, the runtime system matches a syntax-based graph traversal in 2.8 seconds in a corpus of over 134 million sentences, nearly 150,000 times faster than its predecessor.


pdf bib
Enabling Search and Collaborative Assembly of Causal Interactions Extracted from Multilingual and Multi-domain Free Text
George C. G. Barbosa | Zechy Wong | Gus Hahn-Powell | Dane Bell | Rebecca Sharp | Marco A. Valenzuela-Escárcega | Mihai Surdeanu
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations)

Many of the most pressing current research problems (e.g., public health, food security, or climate change) require multi-disciplinary collaborations. In order to facilitate this process, we propose a system that incorporates multi-domain extractions of causal interactions into a single searchable knowledge graph. Our system enables users to search iteratively over direct and indirect connections in this knowledge graph, and collaboratively build causal models in real time. To enable the aggregation of causal information from multiple languages, we extend an open-domain machine reader to Portuguese. The new Portuguese reader extracts over 600 thousand causal statements from 120 thousand Portuguese publications with a precision of 62%, which demonstrates the value of mining multilingual scientific information.


pdf bib
Text Annotation Graphs: Annotating Complex Natural Language Phenomena
Angus Forbes | Kristine Lee | Gus Hahn-Powell | Marco A. Valenzuela-Escárcega | Mihai Surdeanu
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf bib
Scientific Discovery as Link Prediction in Influence and Citation Graphs
Fan Luo | Marco A. Valenzuela-Escárcega | Gus Hahn-Powell | Mihai Surdeanu
Proceedings of the Twelfth Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-12)

We introduce a machine learning approach for the identification of “white spaces” in scientific knowledge. Our approach addresses this task as link prediction over a graph that contains over 2M influence statements such as “CTCF activates FOXA1”, which were automatically extracted using open-domain machine reading. We model this prediction task using graph-based features extracted from the above influence graph, as well as from a citation graph that captures scientific communities. We evaluated the proposed approach through backtesting. Although the data is heavily unbalanced (50 times more negative examples than positives), our approach predicts which influence links will be discovered in the “near future” with a F1 score of 27 points, and a mean average precision of 68%.


pdf bib
Swanson linking revisited: Accelerating literature-based discovery across domains using a conceptual influence graph
Gus Hahn-Powell | Marco A. Valenzuela-Escárcega | Mihai Surdeanu
Proceedings of ACL 2017, System Demonstrations


pdf bib
Sieve-based Coreference Resolution in the Biomedical Domain
Dane Bell | Gus Hahn-Powell | Marco A. Valenzuela-Escárcega | Mihai Surdeanu
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)

We describe challenges and advantages unique to coreference resolution in the biomedical domain, and a sieve-based architecture that leverages domain knowledge for both entity and event coreference resolution. Domain-general coreference resolution algorithms perform poorly on biomedical documents, because the cues they rely on such as gender are largely absent in this domain, and because they do not encode domain-specific knowledge such as the number and type of participants required in chemical reactions. Moreover, it is difficult to directly encode this knowledge into most coreference resolution algorithms because they are not rule-based. Our rule-based architecture uses sequentially applied hand-designed “sieves”, with the output of each sieve informing and constraining subsequent sieves. This architecture provides a 3.2% increase in throughput to our Reach event extraction system with precision parallel to that of the stricter system that relies solely on syntactic patterns for extraction.

pdf bib
Odin’s Runes: A Rule Language for Information Extraction
Marco A. Valenzuela-Escárcega | Gus Hahn-Powell | Mihai Surdeanu
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)

Odin is an information extraction framework that applies cascades of finite state automata over both surface text and syntactic dependency graphs. Support for syntactic patterns allow us to concisely define relations that are otherwise difficult to express in languages such as Common Pattern Specification Language (CPSL), which are currently limited to shallow linguistic features. The interaction of lexical and syntactic automata provides robustness and flexibility when writing extraction rules. This paper describes Odin’s declarative language for writing these cascaded automata.

pdf bib
SnapToGrid: From Statistical to Interpretable Models for Biomedical Information Extraction
Marco A. Valenzuela-Escárcega | Gus Hahn-Powell | Dane Bell | Mihai Surdeanu
Proceedings of the 15th Workshop on Biomedical Natural Language Processing

pdf bib
This before That: Causal Precedence in the Biomedical Domain
Gus Hahn-Powell | Dane Bell | Marco A. Valenzuela-Escárcega | Mihai Surdeanu
Proceedings of the 15th Workshop on Biomedical Natural Language Processing


pdf bib
A Domain-independent Rule-based Framework for Event Extraction
Marco A. Valenzuela-Escárcega | Gus Hahn-Powell | Mihai Surdeanu | Thomas Hicks
Proceedings of ACL-IJCNLP 2015 System Demonstrations

pdf bib
Higher-order Lexical Semantic Models for Non-factoid Answer Reranking
Daniel Fried | Peter Jansen | Gustave Hahn-Powell | Mihai Surdeanu | Peter Clark
Transactions of the Association for Computational Linguistics, Volume 3

Lexical semantic models provide robust performance for question answering, but, in general, can only capitalize on direct evidence seen during training. For example, monolingual alignment models acquire term alignment probabilities from semi-structured data such as question-answer pairs; neural network language models learn term embeddings from unstructured text. All this knowledge is then used to estimate the semantic similarity between question and answer candidates. We introduce a higher-order formalism that allows all these lexical semantic models to chain direct evidence to construct indirect associations between question and answer texts, by casting the task as the traversal of graphs that encode direct term associations. Using a corpus of 10,000 questions from Yahoo! Answers, we experimentally demonstrate that higher-order methods are broadly applicable to alignment and language models, across both word and syntactic representations. We show that an important criterion for success is controlling for the semantic drift that accumulates during graph traversal. All in all, the proposed higher-order approach improves five out of the six lexical semantic models investigated, with relative gains of up to +13% over their first-order variants.