Resolving event coreference with supervised representation learning and clustering-oriented regularization

K Kenyon-Dean, JCK Cheung, D Precup - arXiv preprint arXiv:1805.10985, 2018 - arxiv.org
We present an approach to event coreference resolution by developing a general framework
for clustering that uses supervised representation learning. We propose a neural network …

Semantic overlap summarization among multiple alternative narratives: An exploratory study

N Bansal, M Akter, SKK Santu - Proceedings of the 29th …, 2022 - aclanthology.org
In this paper, we introduce an important yet relatively unexplored NLP task called Semantic
Overlap Summarization (SOS), which entails generating a single summary from multiple …

QA-align: Representing cross-text content overlap by aligning question-answer propositions

DB Weiss, P Roit, A Klein, O Ernst, I Dagan - arXiv preprint arXiv …, 2021 - arxiv.org
Multi-text applications, such as multi-document summarization, are typically required to
model redundancies across related texts. Current methods confronting consolidation …

Factoring statutory reasoning as language understanding challenges

N Holzenberger, B Van Durme - arXiv preprint arXiv:2105.07903, 2021 - arxiv.org
Statutory reasoning is the task of determining whether a legal statute, stated in natural
language, applies to the text description of a case. Prior work introduced a resource that …

Famus: Frames across multiple sources

S Vashishtha, A Martin, W Gantt, B Van Durme… - arXiv preprint arXiv …, 2023 - arxiv.org
Understanding event descriptions is a central aspect of language processing, but current
approaches focus overwhelmingly on single sentences or documents. Aggregating …

SEM-f1: an automatic way for semantic evaluation of multi-narrative overlap summaries at scale

N Bansal, M Akter, SKK Santu - Proceedings of the 2022 …, 2022 - aclanthology.org
Recent work has introduced an important yet relatively under-explored NLP task called
Semantic Overlap Summarization (SOS) that entails generating a summary from multiple …

[PDF][PDF] Feature-driven question answering with natural language alignment

X Yao - 2014 - jscholarship.library.jhu.edu
Question Answering (QA) is the task of automatically generating answers to natural
language questions from humans, serving as one of the primary research areas in natural …

An NLP-based cross-document approach to narrative structure discovery

N Reiter, A Frank, O Hellwig - Literary and Linguistic Computing, 2014 - academic.oup.com
Structural similarities across narratives play an important role in many areas of humanities
research. In this article, we describe a methodology and an implementation to uncover such …

A consolidated open knowledge representation for multiple texts

R Wities, V Shwartz, G Stanovsky, M Adler… - Proceedings of the …, 2017 - aclanthology.org
We propose to move from Open Information Extraction (OIE) ahead to Open Knowledge
Representation (OKR), aiming to represent information conveyed jointly in a set of texts in an …

Inducing implicit arguments from comparable texts: A framework and its applications

M Roth, A Frank - Computational Linguistics, 2015 - direct.mit.edu
In this article, we investigate aspects of sentential meaning that are not expressed in local
predicate–argument structures. In particular, we examine instances of semantic arguments …