Sahar Vahdati

Sahar Vahdati

Auto-generated profile, based on publicly available information

Sahar Vahdati

TU Dresden

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 October 2023
Verified
Conference Paper
Open access
KMKarishma Mohiuddin
Karishma Mohiuddin
MAMirza Ariful Alam
Mirza Ariful Alam
MAMirza Mohtashim Alam
Mirza Mohtashim Alam
PWPascal Welke
Pascal Welke
MMMichael Martin
Michael Martin
SVSahar Vahdati
Sahar Vahdati
Skilled employees are the most important pillars of an organization. Despite this, most organizations face high attrition and turnover rates. While several machine learning models have been developed to analyze attrition and its causal factors, the interpretations of those models remain opaque. In this paper, we propose the HR-DSS approach, which stands for Human Resource (HR) Decision Support System, and uses explainable AI for employee attrition problems. The system is designed to assist HR departments in interpreting the predictions provided by machine learning models. In our experiments, we employ eight machine learning models to provide predictions. We further process the results achieved by the best-performing model by the SHAP explainability process and use the SHAP values to generate natural language explanations which can be valuable for HR. Furthermore, using "What-if-analysis", we aim to observe plausible causes for attrition of an individual employee. The results show that by adjusting the specific dominant features of each individual, employee attrition can turn into employee retention through informative business decisions.

28 September 2023
Verified
Book Chapter
Open access
PDF file
JLJens Lehmann
Jens Lehmann
PGPreetam Gattogi
Preetam Gattogi
DBDhananjay Bhandiwad
Dhananjay Bhandiwad
SFSébastien Ferré
Sébastien Ferré
SVSahar Vahdati
Sahar Vahdati
We propose the use of controlled natural language as a target for knowledge graph question answering (KGQA) semantic parsing via language models as opposed to using formal query languages directly. Controlled natural languages are close to (human) natural languages, but can be unambiguously translated into a formal language such as SPARQL. Our research hypothesis is that the pre-training of large language models (LLMs) on vast amounts of textual data leads to the ability to parse into controlled natural language for KGQA with limited training data requirements. We devise an LLM-specific approach for semantic parsing to study this hypothesis. To conduct our study, we created a dataset that allows the comparison of one formal and two different controlled natural languages. Our analysis shows that training data requirements are indeed substantially reduced when using controlled natural languages, which is relevant since collecting and maintaining high-quality KGQA semantic parsing training data is very expensive and time-consuming.

11 June 2024 in Transactions of the Association for Computational Linguistics
Verified
Journal Article
Open access
PDF file
JLJens Lehmann
Jens Lehmann
DBDhananjay Bhandiwad
Dhananjay Bhandiwad
PGPreetam Gattogi
Preetam Gattogi
SVSahar Vahdati
Sahar Vahdati
Answering factual questions from heterogenous sources, such as graphs and text, is a key capacity of intelligent systems. Current approaches either (i) perform question answering over text and structured sources as separate pipelines followed by a merge step or (ii) provide an early integration, giving up the strengths of particular information sources. To solve this problem, we present “HumanIQ”, a method that teaches language models to dynamically combine retrieved information by imitating how humans use retrieval tools. Our approach couples a generic method for gathering human demonstrations of tool use with adaptive few-shot learning for tool augmented models. We show that HumanIQ confers significant benefits, including i) reducing the error rate of our strongest baseline (GPT-4) by over 50% across 3 benchmarks, (ii) improving human preference over responses from vanilla GPT-4 (45.3% wins, 46.7% ties, 8.0% loss), and (iii) outperforming numerous task-specific baselines.

31 May 2022
Verified
Book Chapter
Closed access
PDF file
MNMojtaba Nayyeri
Mojtaba Nayyeri
SVSahar Vahdati
Sahar Vahdati
TKTansen Khan
Tansen Khan
MAMirza Mohtashim Alam
Mirza Mohtashim Alam
LWLisa Wenige
Lisa Wenige
JLJens Lehmann
Jens Lehmann

4 November 2016
Verified
Book Chapter
Open access
PDF file
SVSahar Vahdati
Sahar Vahdati
NANatanael Arndt
Natanael Arndt
SASören Auer
Sören Auer
CLChristoph Lange
Christoph Lange
Scholars often need to search for matching, high-profile scientific events to publish their research results. Information about topical focus and quality of events is not made sufficiently explicit in the existing communication channels where events are announced. Therefore, scholars have to spend a lot of time on reading and assessing calls for papers but might still not find the right event. Additionally, events might be overlooked because of the large number of events announced every day. We introduce OpenResearch, a crowd sourcing platform that supports researchers in collecting, organizing, sharing and disseminating information about scientific events in a structured way. It enables quality-related queries over a multidisciplinary collection of events according to a broad range of criteria such as acceptance rate, sustainability of event series, and reputation of people and organizations. Events are represented in different views using map extensions, calendar and time-line visualizations. We have systematically evaluated the timeliness, usability and performance of OpenResearch.

5 September 2018
Verified
Book Chapter
Closed access
PDF file
SVSahar Vahdati
Sahar Vahdati
GPGuillermo Palma
Guillermo Palma
RNRahul Jyoti Nath
Rahul Jyoti Nath
CLChristoph Lange
Christoph Lange
SASören Auer
Sören Auer
MVMaria-Esther Vidal
Maria-Esther Vidal