Learning Scalar Adjective Intensity from Paraphrases

Cocos, Anne; Wharton, Veronica; Pavlick, Ellie; Apidianaki, Marianna; Callison-Burch, Chris

doi:10.18653/v1/d18-1202

Cited by 10 publications

(34 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such resources can be manually created, like the SO-CAL lexicon (Taboada et al, 2011), or automatically compiled by mining adjective orderings from star-valued product reviews where people's comments have associated ratings (de Marneffe et al, 2010;Rill et al, 2012;Sharma et al, 2015;Ruppenhofer et al, 2014). Cocos et al (2018) combine knowledge from lexico-syntactic patterns and the SO-CAL lexicon with paraphrases in the Paraphrase Database (PPDB) (Ganitkevitch et al, 2013;Pavlick et al, 2015).…”

Section: Related Workmentioning

confidence: 99%

“…CROWD (Cocos et al, 2018). 3 The dataset consists of a set of adjective scales with high coverage of the PPDB vocabulary.…”

Section: Datamentioning

confidence: 99%

“…The original dataset contains full scales. We use its division in 21 half-scales (with 61 adjective pairs) proposed by Cocos et al (2018).…”

Section: Datamentioning

confidence: 99%

“…We compare our results to the (ukWaC, Flickr, Random) and with static (word2vec) vectors. We compare to the frequency (FREQ) and number of senses (SENSE) baselines, and to results from previous work (Cocos et al, 2018). Results for a dataset are missing (-) when the dataset was used for building the − −− → dV ec intensity vector.…”

Section: Ranking Without Specified Boundariesmentioning

confidence: 99%

“…We evaluate the representations generated by BERT against gold standard adjective intensity estimates (de Melo and Bansal, 2013;Wilkinson, 2017;Cocos et al, 2018) and apply them directly to a question answering task (de Marneffe et al, 2010). Our results show that BERT clearly encodes the intensity variation between adjectives on scales describing different properties.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

BERT Knows Punta Cana is not just beautiful, it’s gorgeous: Ranking Scalar Adjectives with Contextualised Representations

Soler¹,

Apidianaki²

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Self Cite

View full text Add to dashboard Cite

Adjectives like pretty, beautiful and gorgeous describe positive properties of the nouns they modify but with different intensity. These differences are important for natural language understanding and reasoning. We propose a novel BERT-based approach to intensity detection for scalar adjectives. We model intensity by vectors directly derived from contextualised representations and show they can successfully rank scalar adjectives. We evaluate our models both intrinsically, on gold standard datasets, and on an Indirect Question Answering task. Our results demonstrate that BERT encodes rich knowledge about the semantics of scalar adjectives, and is able to provide better quality intensity rankings than static embeddings and previous models with access to dedicated resources.

show abstract

Section: Related Workmentioning

confidence: 99%

“…CROWD (Cocos et al, 2018). 3 The dataset consists of a set of adjective scales with high coverage of the PPDB vocabulary.…”

Section: Datamentioning

confidence: 99%

“…The original dataset contains full scales. We use its division in 21 half-scales (with 61 adjective pairs) proposed by Cocos et al (2018).…”

Section: Datamentioning

confidence: 99%

Section: Ranking Without Specified Boundariesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

BERT Knows Punta Cana is not just beautiful, it’s gorgeous: Ranking Scalar Adjectives with Contextualised Representations

Soler¹,

Apidianaki²

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Self Cite

View full text Add to dashboard Cite

show abstract

Temporal Common Sense Acquisition with Minimal Supervision

Zhou¹,

Ning²,

Khashabi³

et al. 2020

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

View full text Add to dashboard Cite

Temporal common sense (e.g., duration and frequency of events) is crucial for understanding natural language. However, its acquisition is challenging, partly because such information is often not expressed explicitly in text, and human annotation on such concepts is costly. This work proposes a novel sequence modeling approach that exploits explicit and implicit mentions of temporal common sense, extracted from a large corpus, to build TACOLM, 1 a temporal common sense language model.Our method is shown to give quality predictions of various dimensions of temporal common sense (on UDST and a newly collected dataset from Real-News). It also produces representations of events for relevant tasks such as duration comparison, parent-child relations, event coreference and temporal QA (on TimeBank, HiEVE and MCTACO) that are better than using the standard BERT. Thus, it will be an important component of temporal NLP.

show abstract

A Formidable Ability: Detecting Adjectival Extremeness with DSMs

Samir¹,

Beekhuizen

Stevenson

2021

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

View full text Add to dashboard Cite

While distributional semantic models (DSMs) can successfully capture the similarity structure within a semantic domain, less is known about their ability to represent abstract semantic properties that hold across domains. Such properties can form the basis for abstract semantic classes that are a crucial aspect of human semantic knowledge. For example, the abstract class of extreme adjectives (such as brilliant and freezing) spans a wide range of domains (here, INTELLIGENCE and TEMPER-ATURE). Using a model that compares query items to an aggregate DSM representation of a set of extreme adjectives, we show that novel adjectives can be classified accurately, supporting the insight that a cross-domain property like extremeness can be captured in a word's DSM representation. We then use the extremeness classifier to model the emergence of intensifier meaning in adverbs, demonstrating, in a separate task, the effectiveness of detecting this abstract semantic property.

show abstract

Learning Scalar Adjective Intensity from Paraphrases

Cited by 10 publications

References 19 publications

BERT Knows Punta Cana is not just beautiful, it’s gorgeous: Ranking Scalar Adjectives with Contextualised Representations

BERT Knows Punta Cana is not just beautiful, it’s gorgeous: Ranking Scalar Adjectives with Contextualised Representations

Temporal Common Sense Acquisition with Minimal Supervision

A Formidable Ability: Detecting Adjectival Extremeness with DSMs

Contact Info

Product

Resources

About