Combining Contextual and Structural Information for Supersense Tagging of Chinese Unknown Words

Qiu, Likun; Wu, Yunfang; Shao, Yanqiu

doi:10.1007/978-3-642-19400-9_2

Cited by 12 publications

(12 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…its reimplementation by Heilman 2 , was widely used in applied tasks (Agirre et al, 2011;Surdeanu et al, 2011;Laparra and Rigau, 2013). Supersense taggers have then been built also for Italian (Picca et al, 2008), Chinese (Qiu et al, 2011) and Arabic (Schneider et al, 2013). Tsvetkov et al (2015) proposes the usage of SemCor supersense frequencies as a way to evaluate word embedding models, showing that a good alignment of embedding dimensions to supersenses correlates with performance of the vectors in word similarity and text classification tasks.…”

Section: Supersense Taggingmentioning

confidence: 99%

Supersense Embeddings: A Unified Model for Supersense Interpretation, Prediction, and Utilization

Flek¹,

Gurevych²

2016

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

Coarse-grained semantic categories such as supersenses have proven useful for a range of downstream tasks such as question answering or machine translation. To date, no effort has been put into integrating the supersenses into distributional word representations. We present a novel joint embedding model of words and supersenses, providing insights into the relationship between words and supersenses in the same vector space. Using these embeddings in a deep neural network model, we demonstrate that the supersense enrichment leads to a significant improvement in a range of downstream classification tasks.

show abstract

Section: Supersense Taggingmentioning

confidence: 99%

Supersense Embeddings: A Unified Model for Supersense Interpretation, Prediction, and Utilization

Flek¹,

Gurevych²

2016

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

show abstract

“…Evaluation was against manually sensetagged data that had been automatically converted to the coarser supersenses. Similar taggers have since been built for Italian (Picca et al, 2008) and Chinese (Qiu et al, 2011), both of which have their own WordNets mapped to English WordNet.…”

Section: Background: Supersense Tagsmentioning

confidence: 99%

“…They also find benefit from constraining the label space according to WordNet for in-vocabulary words (with what they call "lumped labels"). Though our focus in this paper is on English, automatic supersense tagging has also been explored in Italian (Picca et al, 2008(Picca et al, , 2009Attardi et al, 2010Attardi et al, , 2013, Chinese (Qiu et al, 2011), and Arabic (Schneider et al, 2013).…”

Section: Background: Supersense Tagging With a Discriminative Sequencmentioning

confidence: 99%

A Corpus and Model Integrating Multiword Expressions and Supersenses

Schneider¹,

Smith²

2015

Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Langua

View full text Add to dashboard Cite

This paper introduces a task of identifying and semantically classifying lexical expressions in running text. We investigate the online reviews genre, adding semantic supersense annotations to a 55,000 word English corpus that was previously annotated for multiword expressions. The noun and verb supersenses apply to full lexical expressions, whether single-or multiword. We then present a sequence tagging model that jointly infers lexical expressions and their supersenses. Results show that even with our relatively small training corpus in a noisy domain, the joint task can be performed to attain 70% class labeling F 1 .

show abstract

“…For example, spill the beans in its literal interpretation would receive supersenses V:CONTACT and N:FOOD, whereas the idiomatic interpretation, 'divulge a secret', is represented as an MWE holistically tagged as V:COMMUNICATION. Schneider and Smith (2015) develop this idea at 3 Evaluations used English SemCor (Ciaramita and Altun, 2006;Paaß and Reichartz, 2009), English-Italian MultiSemCor (Picca et al, 2008(Picca et al, , 2009Attardi et al, 2010), the Italian Syntactic-Semantic Treebank and Italian Wikipedia (Attardi et al, 2010;Rossi et al, 2013), Chinese Cilin (Qiu et al, 2011), Arabic Wikipedia , and the Danish CLARIN Reference Corpus (Martínez Alonso et al, 2015). length, and provide a web reviews data set with the integrated annotation.…”

Section: Supersensesmentioning

confidence: 99%

SemEval-2016 Task 10: Detecting Minimal Semantic Units and their Meanings (DiMSUM)

Schneider¹,

Hovy²,

Johannsen³

et al. 2016

Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)

View full text Add to dashboard Cite

This task combines the labeling of multiword expressions and supersenses (coarse-grained classes) in an explicit, yet broad-coverage paradigm for lexical semantics. Nine systems participated; the best scored 57.7% F 1 in a multi-domain evaluation setting, indicating that the task remains largely unresolved. An error analysis reveals that a large number of instances in the data set are either hard cases, which no systems get right, or easy cases, which all systems correctly solve.

show abstract

Combining Contextual and Structural Information for Supersense Tagging of Chinese Unknown Words

Cited by 12 publications

References 12 publications

Supersense Embeddings: A Unified Model for Supersense Interpretation, Prediction, and Utilization

Supersense Embeddings: A Unified Model for Supersense Interpretation, Prediction, and Utilization

A Corpus and Model Integrating Multiword Expressions and Supersenses

SemEval-2016 Task 10: Detecting Minimal Semantic Units and their Meanings (DiMSUM)

Contact Info

Product

Resources

About