The materials science procedural text corpus: Annotating materials synthesis procedures with shallow semantic structures

S Mysore, Z Jensen, E Kim, K Huang… - arxiv preprint arxiv …, 2019 - arxiv.org
Materials science literature contains millions of materials synthesis procedures described in
unstructured natural language text. Large-scale analysis of these synthesis procedures …

Semantic structural evaluation for text simplification

E Sulem, O Abend, A Rappoport - arxiv preprint arxiv:1810.05022, 2018 - arxiv.org
Current measures for evaluating text simplification systems focus on evaluating lexical text
aspects, neglecting its structural aspects. In this paper we propose the first measure to …

[PDF][PDF] Natural language processing

J Eisenstein - Jacob Eisenstein, 2018 - princeton-nlp.github.io
The goal of this text is focus on a core subset of the natural language processing, unified by
the concepts of learning and search. A remarkable number of problems in natural language …

A transition-based directed acyclic graph parser for UCCA

D Hershcovich, O Abend, A Rappoport - arxiv preprint arxiv:1704.00552, 2017 - arxiv.org
We present the first parser for UCCA, a cross-linguistically applicable framework for
semantic representation, which builds on extensive typological work and supports rapid …

A siamese neural network for learning semantically-informed sentence embeddings

N Bölücü, B Can, H Artuner - Expert Systems with Applications, 2023 - Elsevier
Semantic representation is a way of expressing the meaning of a text that can be processed
by a machine to serve a particular natural language processing (NLP) task that usually …

Sentiment analysis based on rhetorical structure theory: Learning deep neural networks from discourse trees

M Kraus, S Feuerriegel - Expert Systems with Applications, 2019 - Elsevier
Prominent applications of sentiment analysis are countless, covering areas such as
marketing, customer service and communication. The conventional bag-of-words approach …

Emotion classification in texts over graph neural networks: Semantic representation is better than syntactic

I Ameer, N Bölücü, G Sidorov, B Can - IEEE Access, 2023 - ieeexplore.ieee.org
Social media is a widely used platform that provides a huge amount of user-generated
content that can be processed to extract information about users' emotions. This has …

Multitask parsing across semantic representations

D Hershcovich, O Abend, A Rappoport - arxiv preprint arxiv:1805.00287, 2018 - arxiv.org
The ability to consolidate information of different types is at the core of intelligence, and has
tremendous practical value in allowing learning for one task to benefit from generalizations …

On the limitations of dataset balancing: The lost battle against spurious correlations

R Schwartz, G Stanovsky - arxiv preprint arxiv:2204.12708, 2022 - arxiv.org
Recent work has shown that deep learning models in NLP are highly sensitive to low-level
correlations between simple features and specific output labels, leading to overfitting and …

The Alexa meaning representation language

T Kollar, D Berry, L Stuart, K Owczarzak… - Proceedings of the …, 2018 - aclanthology.org
This paper introduces a meaning representation for spoken language understanding. The
Alexa meaning representation language (AMRL), unlike previous approaches, which factor …