Papers with classification approach
Automatic Focus Annotation: Bringing Formal Pragmatics Alive in Analyzing the Information Structure of Authentic Data (N18-1)
Copied to clipboard
| Challenge: | Using focus-background dichotomy, discourse and information structure of sentences are being studied in context. |
| Approach: | They propose to automate the analysis of focus in authentic written data by using a range of lexical, syntactic, and semantic features to achieve an accuracy of 78.1%. |
| Outcome: | The proposed approach achieves 78.1% accuracy for identifying focus in authentic written data. |
Generative Knowledge Selection for Knowledge-Grounded Dialogues (2023.findings-eacl)
Copied to clipboard
| Challenge: | Knowledge selection is the key in knowledge-grounded dialogues (KGD), which aims to select an appropriate knowledge snippet to be used in the utterance based on dialogue history. |
| Approach: | They propose a generative approach for knowledge selection called GenKS that learns to select snippets by generating their identifiers with a sequence-to-sequence model. |
| Outcome: | The proposed approach captures intra-knowledge interaction inherently through attention mechanisms while generating their identifiers with a sequence-to-sequence model. |
Predicting Degrees of Technicality in Automatic Terminology Extraction (2020.acl-main)
Copied to clipboard
| Challenge: | a recent study has focused on term technicality, but there are still few studies on it. |
| Approach: | They semi-automatically create a German gold standard of technicality across four domains . they propose two new models to exploit general- vs. domain-specific comparisons based on vector spaces . |
| Outcome: | The proposed model outperforms previous methods in terms of general- vs. domain-specific comparisons. |
Embarrassingly Simple Performance Prediction for Abductive Natural Language Inference (2022.naacl-main)
Copied to clipboard
| Challenge: | a method for learning an NLI model is time-consuming and resource-intensive, but it can save time and resources. |
| Approach: | They propose a method for predicting model performance without fine-tuning it . they compare sentence embeddings with cosine similarity to classifiers . |
| Outcome: | The proposed method can save time and resources by comparing pre-trained models to real-world datasets. |
Do Nuclear Submarines Have Nuclear Captains? A Challenge Dataset for Commonsense Reasoning over Adjectives and Objects (D19-1)
Copied to clipboard
| Challenge: | a dataset of human judgments is used to test the ability to construct models with an understanding of commonsense knowledge. |
| Approach: | They crowdsource sentences that answer a question about adjectives and their transitivity . they build strong baselines for the task using a classification approach . |
| Outcome: | The proposed model outperforms word-level models on commonsense reasoning tasks. |