A Study of Incorrect Paraphrases in Crowdsourced User Utterances (N19-1)

Copied to clipboard

Challenge: Developing bots requires high quality training samples, especially for unqualified crowd workers.
Approach: They propose an annotated dataset for detecting quality issues in crowdsourced paraphrasing . they propose to use existing tools and services to provide baselines for identifying issues .
Outcome: The proposed dataset provides a baseline for detecting unqualified paraphrases.

Similar Papers

Don’t paraphrase, detect! Rapid and Effective Data Collection for Semantic Parsing (D19-1)

Copied to clipboard

Challenge: a major hurdle on the road to conversational interfaces is the difficulty in collecting data that maps language utterances to logical forms . crowdsourcing and crowdsourcing have been used to generate pseudo-language paired with logical form . however, this data collection method often leads to low performance on real data .
Approach: They propose a method that uses crowdsourcing to map language utterances to logical forms . they quantify the effects of mismatches between the true and induced distributions .
Outcome: The proposed method leads to 70.6 accuracy on the true distribution, compared to 51.3 in paraphrase-based data collection.
Mining Crowdsourcing Problems from Discussion Forums of Workers (2020.coling-main)

Copied to clipboard

Challenge: Among the most widely used platforms are Upwork, Appen, and above all Amazon Mechanical Turk (MTurk) which host annotation tasks and collect huge sets of annotated data from workers.
Approach: They propose to use topic modeling to analyze workers' complaints from a new English corpus of workers’ forum discussions to identify problems in task design, task operation, and task evaluation that workers face with requesters in crowdsourcing processes.
Outcome: The findings form the basis for future research on how to improve crowdsourcing processes.
Crowdsourcing Beyond Annotation: Case Studies in Benchmark Data Collection (2021.emnlp-tutorials)

Copied to clipboard

Challenge: Developing a theory of crowdsourcing for practical language problems remains an open challenge .
Approach: This tutorial exposes NLP researchers to data collection crowdsourcing methods and principles through case studies.
Outcome: This tutorial exposes NLP researchers to various data collection crowdsourcing methods and practices through case studies.
What is wrong with you?: Leveraging User Sentiment for Automatic Dialog Evaluation (2022.findings-acl)

Copied to clipboard

Challenge: Existing metrics for dialog evaluation are trained on human annotations, which is cumbersome to collect.
Approach: They propose to use user sentiment and other information as proxy to measure the quality of previous dialogs.
Outcome: The proposed model is comparable to models trained on human annotated data.
Inconsistencies in Crowdsourced Slot-Filling Annotations: A Typology and Identification Methods (2020.coling-main)

Copied to clipboard

Challenge: Standard slot-filling models train or finetune on large datasets of carefully-annotated data that is domain specific.
Approach: They propose automatic methods to identify inconsistencies in crowd-annotated data . a slot-filling model can extract the tokens "New York" as a TO LOCATION slot in a query .
Outcome: The proposed methods reveal inconsistencies in data, though there is scope for improvement.
DialCrowd 2.0: A Quality-Focused Dialog System Crowdsourcing Toolkit (2022.lrec-1)

Copied to clipboard

Challenge: DialCrowd 2.0 helps requesters obtain higher quality data from human intelligence tasks.
Approach: They propose to use DialCrowd 2.0 to help requesters obtain higher quality data . they aim to improve the way requesters present tasks and facilitate effective communication with workers.
Outcome: The proposed toolkit enables requesters to obtain higher quality data by presenting tasks more clearly and facilitating effective communication with workers.
Multilingual Whispers: Generating Paraphrases with Translation (D19-55)

Copied to clipboard

Challenge: Humans naturally paraphrase, but they can generate approximately the same meaning with a different surface realization.
Approach: They compare translation-based paraphrase gathering using human, automatic, or hybrid techniques to monolingual paraphrasing by experts and non-experts.
Outcome: The proposed methods outperform human translation systems in a variety of translation tasks.
What Ingredients Make for an Effective Crowdsourcing Protocol for Difficult NLU Data Collection Tasks? (2021.acl-long)

Copied to clipboard

Challenge: Despite the importance of datasets for natural language understanding, there has been little attention on crowdsourcing methods for collecting datasets.
Approach: They compare the effectiveness of crowdsourcing methods for boosting NLU example difficulty with training crowdworkers instead of expert judgments.
Outcome: The proposed method is ineffective for boosting NLU example difficulty, but it is not effective for training crowdworkers and qualifying workers based on expert judgments.
Are We Modeling the Task or the Annotator? An Investigation of Annotator Bias in Natural Language Understanding Datasets (D19-1)

Copied to clipboard

Challenge: Having only a few workers generate the majority of dataset examples raises concerns about data diversity .
Approach: They perform a series of experiments to investigate annotator biases in recent NLU datasets . they find that models are able to recognize the most productive annotators .
Outcome: The results show that models can recognize the most productive annotators and do not generalize well to examples from annotator that did not contribute to the training set.
ChatGPT to Replace Crowdsourcing of Paraphrases for Intent Classification: Higher Diversity and Comparable Model Robustness (2023.emnlp-main)

Copied to clipboard

Challenge: generative large language models (LLMs) are replacing human workers for some tasks . crowdsourcing has several downsides: 1) the workforce is costly, 2) output quality is difficult to achieve, and 3) there are overheads related to the design and organization of the process.
Approach: They investigate whether ChatGPT-created paraphrases are more diverse and robust . they use a crowdsourcing tool to collect training or validation examples .
Outcome: The proposed models are more diverse and robust than the existing models.

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