Untitled

Stanojević, Miloš; Steedman, Mark

doi:10.18653/v1/n19-1020

Cited by 9 publications

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We extract binary relations of the form arg1predicate-arg2 using MONTEE, an open-domain modality-aware relation extraction system (Bijl de Vroe et al, 2021). MONTEE uses the Rotat-ingCCG parser (Stanojević and Steedman, 2019) as the basis for extracting binary relations and a modality lexicon to identify modality triggers. A relation is tagged as modal (MOD), propositional attitude (ATT_SAY, ATT_THINK) or conditional (COND) if the CCG dependency graph contains a path between a relation node and a node matching an entry in the MONTEE lexicon.…”

Section: Methodsmentioning

confidence: 99%

Blindness to Modality Helps Entailment Graph Mining

Guillou¹,

Vroe²,

Johnson³

et al. 2021

Proceedings of the Second Workshop on Insights From Negative Results in NLP

Self Cite

View full text Add to dashboard Cite

Understanding linguistic modality is widely seen as important for downstream tasks such as Question Answering and Knowledge Graph Population. Entailment Graph learning might also be expected to benefit from attention to modality. We build Entailment Graphs using a news corpus filtered with a modality parser, and show that stripping modal modifiers from predicates in fact increases performance. This suggests that for some tasks, the pragmatics of modal modification of predicates allows them to contribute as evidence of entailment.

show abstract

Section: Methodsmentioning

confidence: 99%

Blindness to Modality Helps Entailment Graph Mining

Guillou¹,

Vroe²,

Johnson³

et al. 2021

Proceedings of the Second Workshop on Insights From Negative Results in NLP

Self Cite

View full text Add to dashboard Cite

show abstract

“…Each sentence in the document is parsed using the RotatingCCG parser (Stanojević and Steedman, 2019) over which we construct a CCG dependency graph using a method similar to the one proposed by Clark et al (2002). (See Figure 2 for an example of a dependency graph and Figure 1 for the CCG parse tree from which it was extracted.)…”

Section: Event Extraction System Overviewmentioning

confidence: 99%

Modality and Negation in Event Extraction

Vroe¹,

Guillou²,

Stanojević³

et al. 2021

Proceedings of the 4th Workshop on Challenges and Applications of Automated Extraction of Socio-Political Events From Text (CAS

Self Cite

View full text Add to dashboard Cite

Language provides speakers with a rich system of modality for expressing thoughts about events, without being committed to their actual occurrence. Modality is commonly used in the political news domain, where both actual and possible courses of events are discussed. NLP systems struggle with these semantic phenomena, often incorrectly extracting events which did not happen, which can lead to issues in downstream applications. We present an opendomain, lexicon-based event extraction system that captures various types of modality. This information is valuable for Question Answering, Knowledge Graph construction and Factchecking tasks, and our evaluation shows that the system is sufficiently strong to be used in downstream applications.

show abstract

Max-Margin Incremental CCG Parsing

Stanojević¹,

Steedman²

2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

View full text Add to dashboard Cite

Incremental syntactic parsing has been an active research area both for cognitive scientists trying to model human sentence processing and for NLP researchers attempting to combine incremental parsing with language modelling for ASR and MT. Most effort has been directed at designing the right transition mechanism, but less has been done to answer the question of what a probabilistic model for those transition parsers should look like.A very incremental transition mechanism of a recently proposed CCG parser when trained in straightforward locally normalised discriminative fashion produces very bad results on English CCGbank. We identify three biases as the causes of this problem: label bias, exposure bias and imbalanced probabilities bias.While known techniques for tackling these biases improve results, they still do not make the parser state of the art. Instead, we tackle all of these three biases at the same time using an improved version of beam search optimisation that minimises all beam search violations instead of minimising only the biggest violation. The new incremental parser gives better results than all previously published incremental CCG parsers, and outperforms even some widely used non-incremental CCG parsers.

show abstract

Untitled

Cited by 9 publications

References 32 publications

Blindness to Modality Helps Entailment Graph Mining

Blindness to Modality Helps Entailment Graph Mining

Modality and Negation in Event Extraction

Max-Margin Incremental CCG Parsing

Contact Info

Product

Resources

About