Zero-shot transfer for implicit discourse relation classification

Kurfalı, Murathan; Östling, Robert

doi:10.18653/v1/w19-5927

Cited by 10 publications

(8 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the golden labeled data are few and the synthetic data may contain some linguistically dissimilarity, they can be iteratively used for model training [8,22,32,56,59,71,102,169]. For example, Fisher et al [22] and Zhou et al [169] used the bootstrapping method in an iterative training model.…”

Section: Joint Data Expansion and Model Trainingmentioning

confidence: 99%

“…The main idea is to first recognize English implicit discourse relations, then project the predicted sense labels in English onto the corresponding Chinese samples. Kurfali and Ostling [56] represented arguments with multi-language sentence embedding via a pre-trained LASER model [1], and fed them into a feed forward network [116]. She et al [120] employed a distributed representation of hierarchical semantic components from different languages as classification triggers.…”

Section: Joint Data Expansion and Model Trainingmentioning

confidence: 99%

See 1 more Smart Citation

A Survey of Implicit Discourse Relation Recognition

Wang¹,

Wang²

2022

Preprint

View full text Add to dashboard Cite

A discourse containing one or more sentences describes daily issues and events for people to communicate their thoughts and opinions. As sentences are normally consist of multiple text segments, correct understanding of the theme of a discourse should take into consideration of the relations in between text segments. Although sometimes a connective exists in raw texts for conveying relations, it is more often the cases that no connective exists in between two text segments but some implicit relation does exist in between them. The task of implicit discourse relation recognition (IDRR) is to detect implicit relation and classify its sense between two text segments without a connective. Indeed, the IDRR task is important to diverse downstream natural language processing tasks, such as text summarization, machine translation and so on. This article provides a comprehensive and up-to-date survey for the IDRR task. We first summarize the task definition and data sources widely used in the field. We categorize the main solution approaches for the IDRR task from the viewpoint of its development history. In each solution category, we present and analyze the most representative methods, including their origins, ideas, strengths and weaknesses. We also present performance comparisons for those solutions experimented on a public corpus with standard data processing procedures. Finally, we discuss future research directions for discourse relation analysis.

show abstract

Section: Joint Data Expansion and Model Trainingmentioning

confidence: 99%

Section: Joint Data Expansion and Model Trainingmentioning

confidence: 99%

A Survey of Implicit Discourse Relation Recognition

Wang¹,

Wang²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Looking at implicit relations in the PDTB-3, Prasad et al (2017) consider the difficulty in extending implicit relations to relations that cross paragraph boundaries. Kurfalı and Östling (2019) examine whether implicit relation annotation in the PDTB-3 can be used as a basis for learning to classify implicit relations in languages that lack discourse annotation. Kim et al (2020) explored whether the PDTB-3 could be used to learn finegrained (Level-2) sense classification in general, while Liang et al (2020) looked at whether separating inter-sentential implicits from intra-sentential implicits could improve their sense classification.…”

Section: Related Workmentioning

confidence: 99%

Revisiting Shallow Discourse Parsing in the PDTB-3: Handling Intra-sentential Implicits

Zhang¹,

Webber²

2022

Preprint

View full text Add to dashboard Cite

In the PDTB-3, several thousand implicit discourse relations were newly annotated within individual sentences, adding to the over 15,000 implicit relations annotated across adjacent sentences in the PDTB-2. Given that the position of the arguments to these intra-sentential implicits is no longer as well-defined as with inter-sentential implicits, a discourse parser must identify both their location and their sense. That is the focus of the current work. The paper provides a comprehensive analysis of our results, showcasing model performance under different scenarios, pointing out limitations and noting future directions.

show abstract

“…Due to the small size of the test sets, we confine ourselves to the top-level senses: Contingency, Comparison, Expansion, Temporal which is also the most common setting for this task. Despite the limited size of TED-MDB, zero-shot transfer is possible and yields meaningful results as shown in (Kurfalı and Östling, 2019). In total, seven languages are evaluated in this task: English, German, Lithuanian 4 , Portuguese, Polish, Russian and Chinese.…”

Section: Implicit Discourse Relation Classification (Pdtb)mentioning

confidence: 99%

Probing Multilingual Language Models for Discourse

Kurfalı¹,

Östling²

2021

Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)

Self Cite

View full text Add to dashboard Cite

Pre-trained multilingual language models have become an important building block in multilingual natural language processing. In the present paper, we investigate a range of such models to find out how well they transfer discourse-level knowledge across languages. This is done with a systematic evaluation on a broader set of discourse-level tasks than has been previously been assembled. We find that the XLM-RoBERTa family of models consistently show the best performance, by simultaneously being good monolingual models and degrading relatively little in a zero-shot setting. Our results also indicate that model distillation may hurt the ability of cross-lingual transfer of sentence representations, while language dissimilarity at most has a modest effect. We hope that our test suite, covering 5 tasks with a total of 22 languages in 10 distinct families, will serve as a useful evaluation platform for multilingual performance at and beyond the sentence level.

show abstract

Zero-shot transfer for implicit discourse relation classification

Cited by 10 publications

References 15 publications

A Survey of Implicit Discourse Relation Recognition

A Survey of Implicit Discourse Relation Recognition

Revisiting Shallow Discourse Parsing in the PDTB-3: Handling Intra-sentential Implicits

Probing Multilingual Language Models for Discourse

Contact Info

Product

Resources

About