Learning to Explicitate Connectives with Seq2Seq Network for Implicit Discourse Relation Classification

Wei, Shi; Demberg, Vera

doi:10.18653/v1/w19-0416

Cited by 25 publications

(21 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…for the training split of Ji is one short of what has been reported in Shi and Demberg (2019) and also the count obtained by using Qin et al (2017)'s preprocessing code. This is due to a duplicate example with label EXPANSION.ALTERNATIVE, which our preprocessing code does not generate.…”

Section: Discussionmentioning

confidence: 99%

Implicit Discourse Relation Classification: We Need to Talk about Evaluation

Kim

Feng

Gunasekara

et al. 2020

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

View full text Add to dashboard Cite

Implicit relation classification on Penn Discourse TreeBank (PDTB) 2.0 is a common benchmark task for evaluating the understanding of discourse relations. However, the lack of consistency in preprocessing and evaluation poses challenges to fair comparison of results in the literature. In this work, we highlight these inconsistencies and propose an improved evaluation protocol. Paired with this protocol, we report strong baseline results from pretrained sentence encoders, which set the new state-of-the-art for PDTB 2.0. Furthermore, this work is the first to explore fine-grained relation classification on PDTB 3.0. We expect our work to serve as a point of comparison for future work, and also as an initiative to discuss models of larger context and possible data augmentations for downstream transferability.

show abstract

Section: Discussionmentioning

confidence: 99%

Implicit Discourse Relation Classification: We Need to Talk about Evaluation

Kim

Feng

Gunasekara

et al. 2020

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

View full text Add to dashboard Cite

show abstract

“…The successful usage of a memory network in Shi and Demberg (2019a) showed that instances that share the same relation have close representations.…”

Section: Unsupervised Methods With Information Retrieval Systemmentioning

confidence: 99%

Entity Enhancement for Implicit Discourse Relation Classification in the Biomedical Domain

Wei¹,

Demberg²

2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

Self Cite

View full text Add to dashboard Cite

Implicit discourse relation classification is a challenging task, in particular when the text domain is different from the standard Penn Discourse Treebank (PDTB;Prasad et al., 2008) training corpus domain (Wall Street Journal in 1990s). We here tackle the task of implicit discourse relation classification on the biomedical domain, for which the Biomedical Discourse Relation Bank (BioDRB; Prasad et al., 2011) is available. We show that entity information can be used to improve discourse relational argument representation. In a first step, we show that explicitly marked instances that are content-wise similar to the target relations can be used to achieve good performance in the cross-domain setting using a simple unsupervised voting pipeline. As a further step, we show that with the linked entity information from the first step, a transformer which is augmented with entity-related information (K-BERT; Liu et al., 2020) sets the new state of the art performance on the dataset, outperforming the large pre-trained BioBERT (Lee et al., 2020) model by 2% points.

show abstract

“…Так, в [Cartoni et al 2013] показано, что переводной эквивалент коннектора может дать дополнительную информацию о его семантике и снять неоднозначность интерпретации в случае полисемичных коннекторов. В [Shi et al 2017: 484] подчёркивается, насколько трудным является распознавание имплицитных ЛСО и что нейронные сети плохо справляются с этой задачей из-за нехватки аннотированных данных. Для решения этой практической проблемы в работе предлагается оригинальный метод использования параллельных корпусов (в данном случае англо-французского корпуса).…”

Section: метод поиска имплицитных лсо в параллельных текстахunclassified

“…Несмотря на то, что изменения контекста при переводе, приводящие к соответствиям типа 2. и 3., могут быть оправданными, мы не рассматриваем их как случаи имплицитных ЛСО. Тем не менее, в [Shi et al 2017: 491] особо отмечается важность исследования контекстов, сходных с теми, которые мы относим к типу 2. Хотя такие контексты 1) не включают никакого коннектора, 2) имеют структуру, не позволяющую его добавить, и 3) могут не рассматриваться как содержащие какое-либо ЛСО, они вызывают появление коннектора в переводе, а потому могут дать новую информацию о механизмах функционирования ЛСО в целом и расширить имеющиеся знания о спектре контекстов, включающих ЛСО.…”

Section: анализ полученных результатовunclassified

Implicit Logical-Semantic Relations and a Method of Their Identification in Parallel Texts

Goncharov¹,

Inkova²

2020

Computational Linguistics and Intellectual Technologies

View full text Add to dashboard Cite

One of the main characteristics of logical-semantic relations (LSRs) between two fragments of a text is that these relations can be either explicit (expressed by some marker, e.g. a connective) or implicit (derived from the interrelation of these fragments’ semantics). Since implicit LSRs do not have any marker, it is difficult to find them in a text (whether automatically or not). In this paper, approaches to analysing implicit LSRs are compared, an original definition for them is offered and differences between implicit LSRs and LSRs expressed by non-prototypical means are described. A method is proposed to identify implicit LSRs using a parallel corpus and a supracorpora database of connectives. Based on the well-known statement that LSRs can be explicitated by adding connectives in the translation, it is argued here that through selecting pairs in which fragments where a connective is used to express an LSR in the translation correspond to those containing any of the translation stimuli standard for this connective in the source language, it is possible to get an array of contexts in which this LSR is implicit in the source text (or expressed by means other than connectives). This method is then applied to study the French causal connectives car, parce que and puisque using a Russian-French parallel corpus. The corpus data are analysed to obtain information about LSRs particularly about cases where the causal LSR in Russian is implicit, as well as about the use of causal connectives in French. These results are used to show that the method proposed allows to quickly create a representative array of contexts with implicit LSRs, which can be useful in both text analysis and in machine learning.

show abstract

Learning to Explicitate Connectives with Seq2Seq Network for Implicit Discourse Relation Classification

Cited by 25 publications

References 25 publications

Implicit Discourse Relation Classification: We Need to Talk about Evaluation

Implicit Discourse Relation Classification: We Need to Talk about Evaluation

Entity Enhancement for Implicit Discourse Relation Classification in the Biomedical Domain

Implicit Logical-Semantic Relations and a Method of Their Identification in Parallel Texts

Contact Info

Product

Resources

About