Challenge: inessential words are unintentionally misjudged as attention-worthy words and assigned heavier attention weights than should be.
Approach: They propose a penalty-based method to regulate the attention learning process by integrating penalty coefficients into the computation of loss by means of overstability of attention weight distributions.
Outcome: The proposed method improves on the Penn Discourse TreeBank corpus and is competitive compared to the state-of-the-art methods.

Similar Papers

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.
Interactively-Propagative Attention Learning for Implicit Discourse Relation Recognition (2020.coling-main)

Copied to clipboard

Challenge: Existing models for discourse relation recognition use self-attention and interactive-attention mechanisms.
Approach: They develop a propagative attention learning model using a cross-coupled two-channel network.
Outcome: The proposed model improves on the baseline models on a Penn Discourse Treebank.
Attention for Implicit Discourse Relation Recognition (L18-1)

Copied to clipboard

Challenge: Existing approaches to implicit discourse relation recognition reach F1 scores of 9.95% to 37.67% . a neural network exploits the strong correlation between pairs of words that implicitly signal a discourse relation.
Approach: They propose a neural network which exploits strong correlation between pairs of words . they use an encoder-decoder model with attention to detect a latent discourse relation .
Outcome: The proposed model outperforms state-of-the-art models on fine-grained classification and fine-granular classification while computing parameters without pooling and fully connected layers.
CVAE-based Re-anchoring for Implicit Discourse Relation Classification (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing studies show that training implicit discourse relation classifiers suffers from data sparsity.
Approach: They propose a re-anchoring strategy to reduce the risk of erroneous sampling . they use Conditional VAE to estimate the risk and migrate the anchor to reduce it .
Outcome: The proposed method improves the baseline classifier performance on PDTB v2.0 .
Using active learning to expand training data for implicit discourse relation recognition (D18-1)

Copied to clipboard

Challenge: Existing methods to determine semantic relations between text spans are limited in the field of discourse-level relation recognition.
Approach: They propose to expand the training data set using the corpus of explicitly-related arguments by arbitrarily dropping the overtly presented discourse connectives.
Outcome: The proposed model expands the training data set using the corpus of explicitly-related arguments, by arbitrarily dropping the overtly presented discourse connectives.
Enhancing Reasoning Capabilities by Instruction Learning and Chain-of-Thoughts for Implicit Discourse Relation Recognition (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing models for implicit discourse relation recognition are based on generative models, but some studies suggest they do not perform as well as generic encoder-only models for NLU tasks.
Approach: They propose a classification method that is solely based on generative models and utilize Chain-of-Thoughts to partition the inference process into a sequence of three successive stages.
Outcome: The proposed model outperforms existing models on a natural language understanding task.
GPT-RE: In-context Learning for Relation Extraction using Large Language Models (2023.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to in-context learning (ICL) are lacking in relation extraction (RE) . emergence of large language models (LLMs) such as GPT-3 represents a significant advancement in natural language processing.
Approach: They propose to incorporate task-aware representations into demonstration retrieval and enrich the demonstrations with gold label-induced reasoning logic.
Outcome: The proposed model achieves SOTA and competitive performances on the Semeval and SciERC datasets.
Entity Enhancement for Implicit Discourse Relation Classification in the Biomedical Domain (2021.acl-short)

Copied to clipboard

Challenge: Discourse relation classification is a challenging task when the text domain is different from the standard Penn Discourse Treebank (PDTB) training corpus domain.
Approach: They propose to use the Biomedical Discourse Relation Bank to improve discourse relational argument representation by linking explicit instances of similar relations with a voting pipeline.
Outcome: The proposed model outperforms the pre-trained BioBERT model by 2% points.
Employing the Correspondence of Relations and Connectives to Identify Implicit Discourse Relations via Label Embeddings (P19-1)

Copied to clipboard

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.
Improving Implicit Discourse Relation Recognition with Semantics Confrontation (2024.lrec-main)

Copied to clipboard

Challenge: Existing methods for implicit discourse relation recognition (IDRR) are unsatisfactory for the task.
Approach: They propose a method that trains PLMs through two semantics enhancers to implicitly differentiate logical and general semantics.
Outcome: The proposed method exceeds baseline by 3.81% F1 score on PDTB 2.0 dataset . it infers discourse logical relations without explicit connectives, but performance remains unsatisfactory .

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