Papers with manual evaluation
Generating Hypothetical Events for Abductive Inference (2021.starsem-1)
Copied to clipboard
| Challenge: | Abductive reasoning is inference to the best explanation given an incomplete set of observations about everyday situations. |
| Approach: | They propose a model that generates what could happen next from a hypothetical scenario and then proposes the most plausible explanation from varying hypothetical scenarios. |
| Outcome: | The proposed model improves over previous vanilla pre-trained models fine-tuned on Abductive NLI. |
Belief-based Generation of Argumentative Claims (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing methods to generate argument with the ability to encode beliefs are limited by the noise generated by the automatic collection of bag-of-words. |
| Approach: | They propose to augment argument generation technology with ability to encode beliefs . they model users' beliefs via their stances on big issues and extend text generation models with extra input reflecting user's beliefs. |
| Outcome: | The proposed approach is low in effectiveness because of the noise produced by the automatic collection of bag-of-words. |
RETAIN: Interactive Tool for Regression Testing Guided LLM Migration (2024.emnlp-demo)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are increasingly integrated into diverse applications. |
| Approach: | They propose a tool specifically designed for regression testing during LLM migrations. |
| Outcome: | RETAIN (REgression Testing guided LLM migrAtIoN) provides a tool specifically designed for regression testing during LLM migrations. |
Translate and Label! An Encoder-Decoder Approach for Cross-lingual Semantic Role Labeling (D19-1)
Copied to clipboard
| Challenge: | Unlike annotation projection techniques, our model does not need parallel data during inference time. |
| Approach: | They propose a cross-lingual Encoder-Decoder model that simultaneously translates and generates sentences with semantic role annotations in a resource-poor target language. |
| Outcome: | The proposed model can be applied in monolingual, multilingual and cross-lingual settings and produces dependency-based and span-based annotations. |
A Large-Scale Benchmark for Vietnamese Sentence Paraphrases (2025.findings-naacl)
Copied to clipboard
| Challenge: | 1.2M original–paraphrase pairs were generated using a hybrid approach to generate high-quality paraphrases. |
| Approach: | They present a high-quality Vietnamese dataset for sentence paraphrasing . they used automatic paraphrase generation and manual evaluation to ensure high quality . |
| Outcome: | The proposed dataset is the first large-scale study on Vietnamese paraphrasing . it combines automatic paraphrase generation with manual evaluation to ensure high quality . |
Crowdsourcing Lightweight Pyramids for Manual Summary Evaluation (N19-1)
Copied to clipboard
Ori Shapira, David Gabay, Yang Gao, Hadar Ronen, Ramakanth Pasunuru, Mohit Bansal, Yael Amsterdamer, Ido Dagan
| Challenge: | Manual evaluation methods are perceived as insufficient due to the high cost of the Pyramid method and the required expertise. |
| Approach: | They propose a crowdsourced method that compares system summaries to references and uses crowdsourced scripts to analyze the results. |
| Outcome: | The proposed method shows higher correlation relative to the original Pyramid method. |
Manual Evaluation Matters: Reviewing Test Protocols of Distantly Supervised Relation Extraction (2021.findings-acl)
Copied to clipboard
Tianyu Gao, Xu Han, Yuzhuo Bai, Keyue Qiu, Zhiyu Xie, Yankai Lin, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou
| Challenge: | Distantly supervised relation extraction (RE) has attracted much attention in the past few years . previous methods to evaluate models manually or directly on autolabeled data have produced inaccurate evaluations . |
| Approach: | They propose to use distant supervision to generate large-scale autolabeled data . they build manually-annotated test sets for two DS-RE datasets and evaluate models . |
| Outcome: | The proposed method produces 53% wrong labels at the entity pair level in the popular NYT10 dataset. |
Varifocal Question Generation for Fact-checking (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent question generation approaches assume that the answer is known . however, such passages are what is being sought when verifying a claim. |
| Approach: | They propose a method that generates questions based on different focal points within a claim . they demonstrate that the method generates more relevant and informative questions . |
| Outcome: | The proposed method outperforms previous work on a fact-checking question generation dataset on measurable evaluation metrics. |
Definition Modelling for Appropriate Specificity (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing definition generation techniques have faced various problems such as the out-of-vocabulary problem and over/under-specificity problems. |
| Approach: | They propose to leverage a pre-trained encoder-decoder model and introduce a re-ranking mechanism to model specificity in definitions. |
| Outcome: | The proposed method significantly outperforms the state-of-the-art method on standard evaluation datasets and shows that it addresses the over/under-specificity problems. |
Teacher Perception of Automatically Extracted Grammar Concepts for L2 Language Learning (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Language teachers need to be accessible and have the necessary resources to create effective content for their students. |
| Approach: | They propose to extract grammar descriptions from a natural text corpus that answer questions about morphosyntax and semantics from lexical corpus. |
| Outcome: | The proposed method is applied to two Indian languages, Kannada and Marathi, which, unlike English, do not have well-developed resources for second language learning. |
Reinforcement Learning Based Text Style Transfer without Parallel Training Corpus (N19-1)
Copied to clipboard
| Challenge: | Existing methods for text style transfer have demonstrated considerable success, but a parallel corpus may not always be available for a transfer task. |
| Approach: | They propose a text style transfer model that uses an attention-based encoder-decoder to transfer a sentence from the source style to the target style. |
| Outcome: | The proposed model outperforms state-of-the-art methods on two different style transfer tasks. |
HighRES: Highlight-based Reference-less Evaluation of Summarization (P19-1)
Copied to clipboard
| Challenge: | Existing methods for summarizing documents are inconsistent due to the difficulty of manual evaluation. |
| Approach: | They propose a method where summaries are evaluated by multiple annotators against the source document via manually highlighted salient content. |
| Outcome: | The proposed method improves inter-annotator agreement while highlighting differences among systems. |
Merely Judging Metaphor is Not Enough: Research on Reasonable Metaphor Detection (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Current metaphor detection tasks only provide labels without interpreting how to understand them. |
| Approach: | They propose to improve the current metaphor detection task by using mainstream Large Language Models. |
| Outcome: | The proposed model is based on the original sentence, target word, and usage . the model is then evaluated using manual evaluation . |
Challenge Dataset of Cognates and False Friend Pairs from Indian Languages (2020.lrec-1)
Copied to clipboard
| Challenge: | Cognates are words that have a common etymological origin and can facilitate the Second Language Acquisition (SLA) however, they also pose a challenge to various NLP applications such as Machine Translation and Cross-lingual Sense Disambiguation. |
| Approach: | They create two cognate datasets for twelve Indian languages and use them to generate cognate sets. |
| Outcome: | The proposed datasets are curated using previously available baseline cognate detection approaches and evaluated with the help of lexicographers. |
Consecutive Question Generation via Dynamic Multitask Learning (2022.findings-emnlp)
Copied to clipboard
| Challenge: | , . ; ) ()((); ()) .())((2): ""(). |
| Approach: | They propose a sequential sequential question-answer generation task with auxiliary tasks generating other elements to generate logically related question-anchor pairs to understand a passage. |
| Outcome: | The proposed framework improves question generation significantly and benefit multiple related tasks. |
Finding a Balanced Degree of Automation for Summary Evaluation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Automated summarization metrics are reliable but often poorly correlated with human judgment. |
| Approach: | They propose a semi-automatic to automatic summary evaluation metrics, following the Pyramid human evaluation method. |
| Outcome: | The proposed metrics are semi-automatic to automatic summary evaluation metrics, following the Pyramid human evaluation method. |
GeezSwitch: Language Identification in Typologically Related Low-resourced East African Languages (2022.lrec-1)
Copied to clipboard
| Challenge: | Low-resourced languages with similar typologies are often confused with each other in real-world applications such as machine translation, affecting the user’s experience. |
| Approach: | They propose to build a dataset for five typologically and phylogenetically related low-resourced East African languages using the Ge’ez script as a writing system. |
| Outcome: | The proposed dataset is built automatically from selected data sources, but also performed a manual evaluation to assess its quality. |
LAiW: A Chinese Legal Large Language Models Benchmark (2025.coling-main)
Copied to clipboard
Yongfu Dai, Duanyu Feng, Jimin Huang, Haochen Jia, Qianqian Xie, Yifang Zhang, Weiguang Han, Wei Tian, Hao Wang
| Challenge: | Xie et al., 2023) show that large language models (LLMs) can generate legal text, but lack the legal syllogism . legal experts are cautious about their practical application due to the opaque nature of the LLMs. |
| Approach: | They propose a Chinese legal LLM benchmark structured around the legal syllogism . they evaluate LLMs across three levels of capability, each reflecting a more complex stage of legal . |
| Outcome: | The proposed benchmark identifies that LLMs lack the legal syllogism, which hinders trust and understanding from legal experts. |
Making Science Simple: Corpora for the Lay Summarisation of Scientific Literature (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing datasets for lay summarisation are limited in size and scope, hindering the development of data-driven approaches. |
| Approach: | They propose to use two new datasets for the lay summarisation of biomedical research articles to characterise their lay summaries. |
| Outcome: | The proposed datasets are compared with existing datasets and show they can be leveraged to support different audiences and applications. |
Re-evaluating Evaluation in Text Summarization (2020.emnlp-main)
Copied to clipboard
| Challenge: | Automated evaluation metrics are an essential part of the development of text-generation tasks such as summarization. |
| Approach: | They propose to use top-scoring system outputs to assess the reliability of automatic evaluation metrics for text summarization. |
| Outcome: | The proposed evaluation method is based on human judgments from 25 top-scoring neural summarization systems. |
LLMs to Replace Crowdsourcing For Parallel Data Creation? The Case of Text Detoxification (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Manual annotation methods, such as crowdsourcing, are costly and require intricate task design skills. |
| Approach: | They propose to use open source LLMs to annotate parallel data for text detoxification . they generate a pseudo-parallel detoxification dataset using activation patching . |
| Outcome: | The proposed model performs comparable to the original dataset in automatic detoxification evaluation metrics and superior quality in manual evaluation and side-by-side comparisons. |
TaPaCo: A Corpus of Sentential Paraphrases for 73 Languages (2020.lrec-1)
Copied to clipboard
| Challenge: | a crowdsourcing project aimed at language learners has created a paraphrase corpus for 73 languages . the corpus contains 1.9 million sentences, with 200 - 250 000 sentences per language . |
| Approach: | They propose to use a Tatoeba-based dataset to create a paraphrase corpus for 73 languages. |
| Outcome: | The proposed dataset contains 1.9 million sentences and 200 - 250 000 sentences per language. |