Papers by Mohsen Mesgar
Python Code Generation by Asking Clarification Questions (2023.acl-long)
Copied to clipboard
| Challenge: | Recent work addresses text-to-code generation using pretrained language models (PLMs) for large-scale NLD: Logistic Regression. |
| Approach: | They propose a dataset containing pairs of natural language descriptions and code with created synthetic clarification questions and answers to solve the under-specified nature of a natural language description. |
| Outcome: | The proposed model improves on previous models, while introducing new challenges to the community, including when and what clarification questions should be asked. |
A Neural Local Coherence Model for Text Quality Assessment (D18-1)
Copied to clipboard
| Challenge: | Existing approaches to local coherence modeling capture text relatedness at the level of sentence-to-sentence transitions. |
| Approach: | They propose a local coherence model that captures the flow of what connects adjacent sentences . they represent the semantics of a sentence by a vector and capture its state at each word . |
| Outcome: | The proposed model is beneficial for readability assessment and essay scoring tasks. |
Efficient Multi-Agent Collaboration with Tool Use for Online Planning in Complex Table Question Answering (2025.findings-naacl)
Copied to clipboard
| Challenge: | Recent studies on complex table question answering focus more and more on complex instances, as they are ubiquitous in table data analysis. |
| Approach: | They propose a framework that requires neither fine-tuning nor closed-source models to solve complex table question answering (TQA) their framework outperforms previous SoTA systems on three out of four benchmarks and performs comparably to the larger and more expensive closed-sourced model GPT-4 on two benchmarks. |
| Outcome: | The proposed framework outperforms closed-source models and closed-sourced models on three out of four benchmarks and performs comparable to the larger and more expensive closed-Source model GPT-4 on two benchmarks. |
The Devil is in the Details: On Models and Training Regimes for Few-Shot Intent Classification (2023.eacl-main)
Copied to clipboard
| Challenge: | Recent methods for task-oriented dialog (ToD) intent classification use pretrained language models . but lack of informative ablations prevents identification of factors that drive performance . |
| Approach: | They propose a framework to evaluate components of Few-Shot Intent Classification . they propose to combine cross-encoder architecture and episodic meta-learning . |
| Outcome: | The proposed framework evaluates cross-encoder architecture and episodic meta-learning . it also shows that splitting episodes into support and query sets outperforms non-episodic counterparts. |
Texts or Images? A Fine-grained Analysis on the Effectiveness of Input Representations and Models for Table Question Answering (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing studies on table question answering use either serialized text or images . lack of controlled setups limits fine-grained distinctions between these approaches. |
| Approach: | They propose a method selecting table representations dynamically and compare their performance to previous studies. |
| Outcome: | The proposed method improves performance 10% compared to using both representations indiscriminately. |
Table Question Answering in the Era of Large Language Models: A Comprehensive Survey of Tasks, Methods, and Evaluation (2026.acl-long)
Copied to clipboard
| Challenge: | Table Question Answering (TQA) aims to answer natural language questions using tabular data. |
| Approach: | They propose a systematic overview of TQA research using large language models and summarize available benchmarks based on task features. |
| Outcome: | The proposed framework provides a comprehensive overview of the current state of the art in the field of Table Question Answering. |
LLMs Beyond English: Scaling the Multilingual Capability of LLMs with Cross-Lingual Feedback (2024.findings-acl)
Copied to clipboard
| Challenge: | Recent multilingual models support limited number of human languages due to lack of training data for low resource languages. |
| Approach: | They propose a multilingual multilingual LLM that scales to 100 languages . they use a human feedback dataset and a data set to perform multilingual instruction tuning . |
| Outcome: | The proposed model outperforms its peers on five multilingual benchmarks. |
Dialogue Coherence Assessment Without Explicit Dialogue Act Labels (2020.acl-main)
Copied to clipboard
| Challenge: | Recent dialogue coherence models use coherency features designed for monologue texts to represent utterances and then explicitly augment them with dialogue-relevant features, e.g., dialogue act labels. |
| Approach: | They propose a multi-task learning approach that uses dialogue act prediction to obtain informative utterance representations for coherence assessment. |
| Outcome: | The proposed model outperforms its strong competitors on the DailyDialogue corpus and performs on par with them on the SwitchBoard corpus for ranking dialogues concerning their coherence. |
Is the Answer in the Text? Challenging ChatGPT with Evidence Retrieval from Instructive Text (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Generative language models have recently shown remarkable success in generating answers to questions in a given textual context, but they suffer from hallucination, wrongly cite evidence, and spread misleading information. |
| Approach: | They propose a benchmark to evaluate an annotated WikiHow article and use it to retrieve answers to questions from trustworthy texts. |
| Outcome: | The proposed model can retrieve answers to lexically varied and open-ended questions from trustworthy instructive texts. |
A Cost-Efficient Modular Sieve for Extracting Product Information from Company Websites (2024.emnlp-industry)
Copied to clipboard
Anna Hätty, Dragan Milchevski, Kersten Döring, Marko Putnikovic, Mohsen Mesgar, Filip Novović, Maximilian Braun, Karina Borimann, Igor Stranjanac
| Challenge: | Existing methods for extracting product information are resource-intensive and computationally prohibitive due to website structure differences and numerous non-product pages. |
| Approach: | They propose a modular method that leverages low-cost classification models to filter out company web pages. |
| Outcome: | The proposed method improves on a new dataset of 7000 product and non-product web pages and reduces computational time and costs. |
Improving Factual Consistency Between a Response and Persona Facts (2021.eacl-main)
Copied to clipboard
| Challenge: | Neural models for response generation produce responses that are semantically plausible but not necessarily factually consistent with persona facts. |
| Approach: | They propose to fine-tune these models by reinforcement learning and an efficient reward function that explicitly captures the consistency between a response and persona facts as well as semantic plausibility. |
| Outcome: | The proposed model improves the rate of responses that are factually consistent with persona facts over its supervised counterpart while maintaining the language quality of responses. |
A Neural Graph-based Local Coherence Model (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Entity grids and entity graphs are two frameworks for modeling local coherence . many approaches to local cohesion modeling rely on entity relations between sentences . |
| Approach: | They propose to use Relational Graph Convolutional Networks to encode entity graphs for measuring local coherence. |
| Outcome: | The proposed model outperforms the neural grid-based model on two coherence evaluation tasks while using 50% fewer parameters. |
Exploring Generative Process Reward Modeling for Semi-Structured Data: A Case Study of Table Question Answering (2026.eacl-short)
Copied to clipboard
| Challenge: | Recent advances in process reward models (PRMs) have demonstrated remarkable improvements in the reasoning capabilities of large language models (LLMs). |
| Approach: | They evaluate state-of-the-art generative PRMs on table question answering from answer and step perspectives and compare their results to previous studies. |
| Outcome: | The proposed model can aid solution selection but struggle to generalize to out-of-domain data. |
Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems (N19-1)
Copied to clipboard
Steffen Eger, Gözde Gül Şahin, Andreas Rücklé, Ji-Ung Lee, Claudia Schulz, Mohsen Mesgar, Krishnkant Swarnkar, Edwin Simpson, Iryna Gurevych
| Challenge: | Recent studies show that visual similarity can play a decisive role in assessing the meaning of characters. |
| Approach: | They investigate the impact of visual adversarial attacks on current NLP systems . they explore three shielding methods that significantly improve the robustness of the models . |
| Outcome: | The proposed methods improve performance but still fall behind non-attack scenarios. |
FREB-TQA: A Fine-Grained Robustness Evaluation Benchmark for Table Question Answering (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing benchmarks for Table Question Answering lack robustness . current systems generate inconsistent responses by performing coarse-grained changes in tables and questions. |
| Approach: | They formalize three major desiderata for a fine-grained evaluation of robustness of TQA systems . they aim to evaluate TQA responses on the content of relevant cells rather than on biases . |
| Outcome: | The proposed benchmarks show that state-of-the-art TQA systems fail in three aspects . the benchmarks are released publicly and are expected to improve over time . |
A Dataset of Argumentative Dialogues on Scientific Papers (2023.acl-long)
Copied to clipboard
| Challenge: | Recent advances in question-answering models have made them a great asset in accessing the content of scientific papers. |
| Approach: | They propose to use a dataset of 41 argumentative dialogues between scientists on 20 NLP papers to improve and evaluate their question-answering models. |
| Outcome: | The proposed dataset includes both exploratory and argumentative questions and answers in a dialogue discourse on a scientific paper. |