Papers by Hassan Sawaf

5 papers
EvolveMT: an Ensemble MT Engine Improving Itself with Usage Only (2023.acl-industry)

Copied to clipboard

Challenge: EvolveMT is a method for the efficient combination of multiple machine translation engines.
Approach: They propose a method that selects the output from one engine for each segment and uses online learning techniques to predict the most appropriate system for each translation request.
Outcome: The proposed method achieves similar translation accuracy at a lower cost than selecting the best translation of each segment from all translations using an MT quality estimator.
Bel Esprit: Multi-Agent Framework for Building AI Model Pipelines (2025.acl-demo)

Copied to clipboard

Challenge: a single AI model is often insufficient for complex tasks, requiring integration of multiple models into pipelines . a conversational agent can build pipelines composed of diverse AI models based on user requirements .
Approach: They propose a conversational agent that constructs AI model pipelines based on user requirements.
Outcome: The proposed agent can build AI model pipelines from human-curated and synthetic data.
Media-to-Insights: A Multi-Agent AI System for Continuous Media Monitoring, Analysis, and Reporting (2026.acl-demo)

Copied to clipboard

Challenge: Existing systems that use keyword-based media monitoring miss semantically relevant articles and are expensive at scale.
Approach: They propose a multi-agent media monitoring system that processes streaming articles through three stages: article matching, batched feature extraction, and report generation with deterministic deduplication and density-based clustering.
Outcome: The proposed system reduces agent invocations by 20% and reduces core feature extraction calls from 7 to 2 per article - a 71% reduction - with bounded quality tradeoffs .
Agentic AI for Human Resources: LLM-Driven Candidate Assessment (2026.eacl-demo)

Copied to clipboard

Challenge: Current systems rely on keyword matching and shallow keyword-based screening, leading to missed opportunities and inconsistent evaluations.
Approach: They propose a framework that uses Large Language Models to automate candidate assessment in recruitment.
Outcome: The proposed framework outputs detailed assessment reports, candidate comparisons, and ranked recommendations that are transparent, auditable, and suitable for real-world hiring workflows.
MTLens: Machine Translation Output Debugging (2022.lrec-1)

Copied to clipboard

Challenge: a demo demonstrates a system for quantitatively evaluating MT systems in isolation or multiple MT models collectively . performance of machine translation systems varies significantly with inputs of diverging features, such as genres, genres and surface properties.
Approach: They propose a benchmarking interface that quantitatively evaluates MT systems in isolation or collectively . the interface can be extended to include additional filters such as lexical, morphological, and syntactic features.
Outcome: The proposed system quantitatively evaluates MT systems on multiple domains and evaluation metrics.

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