Papers by Rebecca Sharp

9 papers
Grounding Gradable Adjectives through Crowdsourcing (L18-1)

Copied to clipboard

Challenge: Often, texts describe interactions using vague, high-level language . crowdsourcing is expensive and requires extensive literature review and time .
Approach: They propose a method for estimating concrete groundings for a set of gradable adjectives by crowdsourcing human intuitions and fitting a mixed effects model to the text.
Outcome: The proposed model can generalize to unseen data and has a predictive R 2 of 0.632 in general and 0.677 on a subset of high-frequency adjectives.
MathAlign: Linking Formula Identifiers to their Contextual Natural Language Descriptions (2020.lrec-1)

Copied to clipboard

Challenge: Existing approaches to extract mathematical concepts and their descriptions are useful for a variety of tasks, including math information retrieval and accessibility efforts to make scientific documents available to the visually impaired.
Approach: They propose a rule-based approach which extracts LaTeX representations of formula identifiers and links them to their in-text descriptions, given only the original PDF and the location of the formula of interest.
Outcome: The proposed approach extracts LaTeX representations of formula identifiers and links them to their in-text descriptions, given only the original PDF and the location of the formula of interest.
Enabling Search and Collaborative Assembly of Causal Interactions Extracted from Multilingual and Multi-domain Free Text (N19-4)

Copied to clipboard

Challenge: a new searchable knowledge graph allows users to search for causal interactions in multiple languages . a recent study shows that search tools are shallow and do not support multilingual research .
Approach: They propose a system that integrates causal interactions into a single searchable knowledge graph.
Outcome: The proposed system extracts over 600 thousand causal statements from 120 thousand Portuguese publications with a precision of 62%.
From Examples to Rules: Neural Guided Rule Synthesis for Information Extraction (2022.lrec-1)

Copied to clipboard

Challenge: a "deep learning tsunami" has brought tremendous improvements in performance to most NLP applications.
Approach: They propose a method for rule synthesis from examples that combines the advantages of deep learning and rule-based methods.
Outcome: The proposed method achieves state-of-the-art on 1-shot task and competitive performance in 5-shot scenario.
Eidos, INDRA, & Delphi: From Free Text to Executable Causal Models (N19-4)

Copied to clipboard

Challenge: a paper proposes a method for building probabilistic models of complex phenomena such as food insecurity . currently, these models are hand-built for each new situation and require months to construct .
Approach: They propose an approach that builds executable probabilistic models from raw, free text.
Outcome: The proposed approach builds executable probabilistic models from raw, free text.
A Human-machine Interface for Few-shot Rule Synthesis for Information Extraction (2022.naacl-demo)

Copied to clipboard

Challenge: Vacareanu et al., 2021) proposes a system that helps users build transparent information extraction models . rule-based methods address the opacity of neural architectures by producing models that are transparent .
Approach: They propose a system that assists a user in constructing transparent information extraction models . the system generates high-precision rules even in a 1-shot setting, they show .
Outcome: The proposed system generates high-precision rules even in a 1-shot setting . it outperforms manually written patterns on a widely-used relation extraction dataset .
Towards the Necessity for Debiasing Natural Language Inference Datasets (2020.lrec-1)

Copied to clipboard

Challenge: Delexicalization of datasets can improve natural language inference performance . a dataset with a delexicalized version of the FEVER dataset is used for natural language learning .
Approach: They propose two techniques for delexicalization that modify annotated datasets to control the importance of lexical entities.
Outcome: The proposed methods maintain performance in-domain and improve performance in some out-of-domain settings.
On the Importance of Delexicalization for Fact Verification (D19-1)

Copied to clipboard

Challenge: Neural networks (NNs) perform state-of-the-art (SOA) performance in many complex tasks.
Approach: They investigate the importance that a model assigns to various aspects of data . they experiment with two strategies of masking to mitigate this dependence on lexicalized information .
Outcome: The proposed model improves on the in-domain dataset by 10% compared to the fully lexicalized model.
An Unsupervised Method for Learning Representations of Multi-word Expressions for Semantic Classification (2020.coling-main)

Copied to clipboard

Challenge: Existing methods for learning multi-word expressions have language sparsity and are not supervised.
Approach: They propose an unsupervised approach to learning a compositional representation function for multi-word expressions . they use a Tratz dataset to train the composition function on the word-semantic relation .
Outcome: The proposed method outperforms the previous state-of-the-art method on the Tratz dataset with an F1 score of 50.4%.

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