Papers with EC
Findings of the Association for Computational Linguistics: EACL 2023 (2023.findings-eacl)
Copied to clipboard
| Challenge: | a technical review committee flagged 21 papers for ethical concerns . 10 papers were flagged for ethical issues . |
| Approach: | a technical review committee flagged 21 papers for ethical concerns . 10 papers were flagged by the technical review panel . |
| Outcome: | a technical review committee flagged 21 papers for ethical concerns . 10 papers were flagged for ethical issues . |
Robust ASR Error Correction with Conservative Data Filtering (2024.emnlp-industry)
Copied to clipboard
| Challenge: | Error correction (EC) based on large language models is an emerging technology to enhance the performance of automatic speech recognition systems. |
| Approach: | They propose to pair large set of ASR hypotheses with gold references to improve linguistic acceptability over sources and be inferable from available context. |
| Outcome: | The proposed approach significantly reduces overcorrection and improves quality in out-of-domain (OOD) settings. |
Efficient Nearest Neighbor Emotion Classification with BERT-whitening (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for retrieval-based methods use pre-trained models for similarity search, but they perform poorly in retrieving semantically similar sentences. |
| Approach: | They propose a non-parametric emotion classification method using nearest neighbor retrieval that can be added to any pre-trained model without further training. |
| Outcome: | The proposed method improves the pre-trained model by 1.17 F1-macro on two emotion classification datasets. |
PMKI: an European Commission action for the interoperability, maintainability and sustainability of Language Resources (L18-1)
Copied to clipboard
| Challenge: | Public Multilingual Knowledge Management Infrastructure (PMKI) is a project launched by the European Commission to promote the digital single market in the EU. |
| Approach: | The paper presents the Public Multilingual Knowledge Management Infrastructure (PMKI) action launched by the European Commission to promote the Digital Single Market in the European Union. |
| Outcome: | The proposed public multilingual knowledge management infrastructure (PMKI) is a pilot project launched by the European Commission to promote the digital single market in the European Union. |
Unsupervised Sentence Textual Similarity with Compositional Phrase Semantics (2022.coling-1)
Copied to clipboard
| Challenge: | Sentence Textual Similarity (STS) is a classic task that can be applied to downstream NLP applications such as text generation and retrieval. |
| Approach: | They propose a light-weighted Expectation-Correction (EC) formulation for STS computation. |
| Outcome: | The proposed approach is more efficient and scalable than previous approaches. |
EC-RAFT: Automated Generation of Clinical Trial Eligibility Criteria through Retrieval-Augmented Fine-Tuning (2025.findings-acl)
Copied to clipboard
| Challenge: | Eligibility criteria (EC) are critical components of clinical trial design, specifying parameters for participant inclusion and exclusion. |
| Approach: | They propose a method that utilizes Retrieval-Augmented Fine-Tuning to generate structured and cohesive EC directly from clinical trial titles and descriptions. |
| Outcome: | The proposed method outperforms Llama-3.1-8B-Instruct and Llm-as-a-Judge models in BERTScore and EC score. |
Rethinking Negative Sampling for Handling Missing Entity Annotations (2022.acl-long)
Copied to clipboard
| Challenge: | Empirical studies show low missampling rate and high uncertainty are both essential for achieving promising performances with negative sampling. |
| Approach: | They propose an adaptive and weighted sampling distribution that further improves negative sampling by introducing missampling and uncertainty concepts. |
| Outcome: | The proposed approach improves on synthetic and well-annotated datasets in terms of F1 score and loss convergence. |