Challenge: Existing models for implicit discourse relation recognition lack the ability to accurately map connectives into discourse relations.
Approach: They propose a multi-task learning framework where relations and connectives are simultaneously predicted and leveraged to transfer knowledge between the two prediction tasks.
Outcome: The proposed framework yields state-of-the-art performance on several settings of the Penn Discourse Treebank dataset.

Similar Papers

Connective Prediction for Implicit Discourse Relation Recognition via Knowledge Distillation (2023.acl-long)

Copied to clipboard

Challenge: Existing methods for implicit discourse relation recognition (IDRR) lack connectives, which is a major challenge in discourse analysis research.
Approach: They propose a method to predict latent correlations between connectives and discourse relations using a knowledge distillation approach.
Outcome: The proposed method outperforms state-of-the-art models on coarse-grained and fine-grain discourse relations and can be transferred to explicit discourse relation recognition and achieve acceptable performance.
Implicit Sense-labeled Connective Recognition as Text Generation (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for identifying implicit discourse relations are limited by the number of possible categories and sense labels.
Approach: They propose a method for identifying the sense label of an implicit connective between adjacent text spans by using an encoder-decoder model.
Outcome: The proposed method outperforms the conventional classification-based method on a shallow discourse parsing dataset.
Not Just Classification: Recognizing Implicit Discourse Relation on Joint Modeling of Classification and Generation (2021.emnlp-main)

Copied to clipboard

Challenge: Existing methods of implicit discourse relation recognition (IDRR) focus on three aspects: enhancing discourse units representation, enhancing semantic interaction, and joint learning with other tasks.
Approach: They propose a joint model to recognize the relation label and generate the target sentence containing the meaning of relations simultaneously.
Outcome: The proposed model achieves the best performance against several state-of-the-art systems on Chinese and English datasets.
What Causes the Failure of Explicit to Implicit Discourse Relation Recognition? (2024.naacl-long)

Copied to clipboard

Challenge: Prior work claimed that explicit classifiers perform poorly in implicit scenarios . a label shift occurs after connectives are removed, but no empirical evidence supports this claim .
Approach: They propose to prove that the discourse relations expressed by some explicit instances will change when connectives disappear.
Outcome: The proposed methods outperform strong baselines on PDTB 2.0, PDTT 3.0, and the GUM dataset.
Prompt-based Connective Prediction Method for Fine-grained Implicit Discourse Relation Recognition (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing methods to aid implicit discourse relation recognition (IDRR) lack explicit connectives and are difficult to implement on fine-grained IDRR.
Approach: They propose a Prompt-based Connective Prediction method that instructs large-scale pre-trained models to use knowledge relevant to discourse relation and utilizes strong correlation between connectives and discourse relation to help the model recognize implicit discourse relations.
Outcome: The proposed method surpasses the state-of-the-art model and achieves significant improvements on those fine-grained few-shot discourse relation classes.
Adapting BERT to Implicit Discourse Relation Classification with a Focus on Discourse Connectives (2020.lrec-1)

Copied to clipboard

Challenge: Existing studies on the performance of BERT for implicit discourse relation classification have not been conducted.
Approach: They propose to apply BERT to implicit discourse relation classification by performing additional pre-training on text tailored to discourse relations.
Outcome: The proposed methods outperform previous state-of-the-art models in many tasks.
Multi-Label Classification for Implicit Discourse Relation Recognition (2024.findings-acl)

Copied to clipboard

Challenge: Prior research in discourse relation recognition has treated these instances as separate examples during training, with a gold-standard prediction matching one of the labels considered correct at test time.
Approach: They propose to use multiple labels to annotate an example when multiple relations are believed to hold simultaneously.
Outcome: The proposed frameworks don't depress performance for single-label prediction.
Prompt-based Logical Semantics Enhancement for Implicit Discourse Relation Recognition (2023.emnlp-main)

Copied to clipboard

Challenge: Existing methods for identifying discourse relations without explicit connectives are limited by the availability of annotated data.
Approach: They propose a method that injects knowledge relevant to discourse relation into pre-trained language models through prompt-based connective prediction.
Outcome: The proposed method achieves outstanding performance against the current state-of-the-art models.
Annotation-Inspired Implicit Discourse Relation Classification with Auxiliary Discourse Connective Generation (2023.acl-long)

Copied to clipboard

Challenge: Discourse connectives are words or phrases that signal the presence of a discourse relation.
Approach: They propose a model that generates discourse connectives between arguments and predicts discourse relations based on the generated connectives.
Outcome: The proposed model outperforms baselines on three datasets and is highly accurate.
Implicit Discourse Relation Classification: We Need to Talk about Evaluation (2020.acl-main)

Copied to clipboard

Challenge: Lack of consistency in preprocessing and evaluation poses challenges to fair comparison of results in literature.
Approach: They propose an improved evaluation protocol for implicit relation classification on PDTB 2.0 . they report strong baseline results from pretrained sentence encoders .
Outcome: The proposed evaluation protocol improves the existing framework and provides strong baseline results.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations