Papers by Aaron Steven White

12 papers
Natural Language Inference with Mixed Effects (2020.starsem-1)

Copied to clipboard

Challenge: aggregating raw annotations to a single label is problematic due to disagreement among annotators.
Approach: They propose a generic method that allows one to skip the aggregation step and train on the raw annotations directly without subjecting the model to unwanted noise.
Outcome: The proposed method improves performance over models that do not incorporate such effects.
Collecting Diverse Natural Language Inference Problems for Sentence Representation Evaluation (D18-1)

Copied to clipboard

Challenge: a plethora of new natural language inference datasets has been created in recent years . however, these datasets do not provide clear insight into what type of reasoning or inference a model may be performing.
Approach: They propose to recast 13 existing natural language inference datasets into a common structure.
Outcome: The proposed datasets provide insight into how well a sentence representation captures distinct types of reasoning.
Lexicosyntactic Inference in Neural Models (D18-1)

Copied to clipboard

Challenge: lexicosyntactic inferences are triggered by surprising aspects of the syntactical context that a word occurs in.
Approach: They build a factuality judgment dataset for English clause-embedding verbs in various syntactic contexts and use it to probe the behavior of current state-of-the-art neural systems.
Outcome: The proposed model makes systematic errors that are visible through the lens of factuality prediction.
Fine-Grained Temporal Relation Extraction (P19-1)

Copied to clipboard

Challenge: Existing methods for temporal relations and event durations are insufficient for determining the fine-grained temporal structure of complex events.
Approach: They propose a semantic framework for temporal relations and event durations that maps pairs of events to real-valued scales.
Outcome: The proposed framework can predict fine-grained temporal relations and event durations . it can be applied to the entire English Web Treebank dataset .
Joint Universal Syntactic and Semantic Parsing (2021.tacl-1)

Copied to clipboard

Challenge: Several attempts have been made to jointly parse syntax and semantics, but this trade-off is not well understood.
Approach: They propose multiple model architectures that exploit the rich syntactic and semantic annotations contained in the Universal Decompositional Semantics dataset to obtain state-of-the-art results.
Outcome: The proposed model outperforms existing models in 8 languages and their results are consistent across languages.
Neural Models of Factuality (N18-1)

Copied to clipboard

Challenge: A central function of natural language is to convey information about the properties of events.
Approach: They propose to use a FactBank, UW, and MEANTIME event factuality dataset to build two neural models that outperform previous models.
Outcome: The proposed models outperform previous models on FactBank, UW, and MEANTIME datasets.
LOME: Large Ontology Multilingual Extraction (2021.eacl-demos)

Copied to clipboard

Challenge: LOME is a system for performing multilingual information extraction with large ontologies.
Approach: They propose a system for multilingual information extraction with a framenet parser . LOME is available as a Docker container on Docker Hub and a lightweight version is available on the web .
Outcome: The proposed system outperforms or is competitive with the (monolingual) state-of-the-art . it can be used to build knowledge graphs with large ontologies and across multiple languages .
Decomposing and Recomposing Event Structure (2022.tacl-1)

Copied to clipboard

Challenge: Using annotated sentences and document-level UDS graphs, we induce an event structure classification with semantic role, entity, and event-event relation classifications.
Approach: They propose to use Universal Decompositional Semantics (UDS) graphs to induce event structure classification . they augment existing annotations with inferential properties capturing fine-grained aspects of temporal and aspectual structure of events.
Outcome: The proposed model is the largest annotation of event structure and (partial) event coreference to date.
Universal Decompositional Semantic Parsing (2020.acl-main)

Copied to clipboard

Challenge: Decompositional Semantics is a formalism that encodes semantic information in a feature-based scheme using continuous scales rather than categorical labels.
Approach: They propose a transductive model for parsing into Universal Decompositional Semantics representations and a pipeline model for annotating the graph with decompositionally semantic attribute scores.
Outcome: The proposed model performs well while performing attribute prediction.
Temporal Reasoning in Natural Language Inference (2020.findings-emnlp)

Copied to clipboard

Challenge: We use five new natural language inference (NLI) datasets focused on temporal reasoning.
Approach: They introduce five new natural language inference datasets focused on temporal reasoning.
Outcome: The proposed models capture the temporal reasoning of four existing datasets.
Everything Is All It Takes: A Multipronged Strategy for Zero-Shot Cross-Lingual Information Extraction (2021.emnlp-main)

Copied to clipboard

Challenge: Zero-shot cross-lingual information extraction (IE) is a technique for training data in a source language but not in .
Approach: They explore techniques including data projection and self-training to improve zero-shot cross-lingual information extraction (IE) IE is a construction of an IE model for some target language given existing annotations exclusively in English.
Outcome: The proposed techniques show that they perform better than any single strategy.
The Universal Decompositional Semantics Dataset and Decomp Toolkit (2020.lrec-1)

Copied to clipboard

Challenge: Decompositional semantics is a method of crowd-sourcing semantic annotations while retaining high interannotator agreement.
Approach: They present the Universal Decompositional Semantics dataset (v1.0) they propose a decomposition-aligned approach to semantic annotation that uses simple questions to answer .
Outcome: The dataset is bundled with the Decomp toolkit (v0.1) both datasets are publicly available at http://decomp.io.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations