Mining User-Generated Repair Instructions from Automotive Web Communities

Wambsganss, Thiemo; Fromm, Hansjörg

doi:10.24251/hicss.2019.144

Cited by 4 publications

(4 citation statements)

References 21 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…following Kim et al 2019 [12]. To measure the syntactic readability of texts, several measures have been used in research [11,28]. We selected the Flesh-Reading-Ease (FRE) [5] to capture the readability of received responses since this score combines language complexity measurements such as the average sentence lengths and the average syllables per word into one number [5].…”

Section: Measurement and Analysismentioning

confidence: 99%

A Conversational Agent to Improve Response Quality in Course Evaluations

Wambsganss

Winkler

Söllner

et al. 2020

Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems

Self Cite

View full text Add to dashboard Cite

Recent advances in Natural Language Processing (NLP) bear the opportunity to design new forms of human-computer interaction with conversational interfaces. We hypothesize that these interfaces can interactively engage students to increase response quality of course evaluations in education compared to the common standard of web surveys. Past research indicates that web surveys come with disadvantages, such as poor response quality caused by inattention, survey fatigue or satisficing behavior. To test if conversational interfaces have a positive impact on the level of enjoyment and the response quality, we design an NLPbased conversational agent and deploy it in a field experiment with 127 students in our lecture and compare it with a web survey as a baseline. Our findings indicate that using conversational agents for evaluations are resulting in higher levels of response quality and level of enjoyment, and are therefore, a promising approach to increase the effectiveness of surveys in general.

show abstract

Section: Measurement and Analysismentioning

confidence: 99%

A Conversational Agent to Improve Response Quality in Course Evaluations

Wambsganss

Winkler

Söllner

et al. 2020

Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…The language of statutes is related to procedural language, which describes steps in a process. Zhang et al (2012) collect how-to instructions in a variety of domains, while Wambsganss and Fromm (2019) focus on automotive repair instructions. Branavan et al (2012) exploit instructions in a game manual to improve an agent's performance.…”

Section: Related Workmentioning

confidence: 99%

Factoring Statutory Reasoning as Language Understanding Challenges

Holzenberger

Durme

2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

Statutory reasoning is the task of determining whether a legal statute, stated in natural language, applies to the text description of a case. Prior work introduced a resource that approached statutory reasoning as a monolithic textual entailment problem, with neural baselines performing nearly at-chance. To address this challenge, we decompose statutory reasoning into four types of language-understanding challenge problems, through the introduction of concepts and structure found in Prolog programs. Augmenting an existing benchmark, we provide annotations for the four tasks, and baselines for three of them. Models for statutory reasoning are shown to benefit from the additional structure, improving on prior baselines. Further, the decomposition into subtasks facilitates finer-grained model diagnostics and clearer incremental progress.

show abstract

“…To the best of our knowledge, no works have tackled so far the problem of detecting procedural sentences in surgical documents. However, approaches for detecting procedural sentences have been proposed in other domains and applied to typologies of textual content substantially different than the description of a surgical procedure, such as repair instructions [17,27,30], technical support documenta-tion [2,8,17], instructions for nanomaterials' synthesis [28], cooking recipes [17,30] and medical abstracts [24].…”

Section: State Of the Artmentioning

confidence: 99%

“…In [27], the authors pursue the detection of repair instructions in user-generated text from automotive web communities. Various features (bag-of-words, bag-of-bigrams, post length, readability index), including structural ones (repair instructions are often provided as bulleted or numbered lists) are fed to several ML methods, from classical ones (e.g., Random Forest) to Neural-Networks (single and multilayer perceptrons).…”

Section: State Of the Artmentioning

confidence: 99%

Automatic detection of procedural knowledge in robotic-assisted surgical texts

et al. 2021

View full text Add to dashboard Cite

Purpose The automatic extraction of knowledge about intervention execution from surgical manuals would be of the utmost importance to develop expert surgical systems and assistants. In this work we assess the feasibility of automatically identifying the sentences of a surgical intervention text containing procedural information, a subtask of the broader goal of extracting intervention workflows from surgical manuals. Methods We frame the problem as a binary classification task. We first introduce a new public dataset of 1958 sentences from robotic surgery texts, manually annotated as procedural or non-procedural. We then apply different classification methods, from classical machine learning algorithms, to more recent neural-network approaches and classification methods exploiting transformers (e.g., BERT, ClinicalBERT). We also analyze the benefits of applying balancing techniques to the dataset. Results The architectures based on neural-networks fed with FastText’s embeddings and the one based on ClinicalBERT outperform all the tested methods, empirically confirming the feasibility of the task. Adopting balancing techniques does not lead to substantial improvements in classification. Conclusion This is the first work experimenting with machine / deep learning algorithms for automatically identifying procedural sentences in surgical texts. It also introduces the first public dataset that can be used for benchmarking different classification methods for the task.

show abstract

Mining User-Generated Repair Instructions from Automotive Web Communities

Cited by 4 publications

References 21 publications

A Conversational Agent to Improve Response Quality in Course Evaluations

A Conversational Agent to Improve Response Quality in Course Evaluations

Factoring Statutory Reasoning as Language Understanding Challenges

Automatic detection of procedural knowledge in robotic-assisted surgical texts

Contact Info

Product

Resources

About