49 citations · 53 across the 6 of their papers we have counts for
8 papers
Python Code Generation by Asking Clarification Questions
Haau-Sing Li, Mohsen Mesgar, André F. T. Martins +1
Code generation from text requires understanding the user's intent from a natural language description and generating an executable code snippet that satisfies this intent. While r…
The Devil is in the Details: On Models and Training Regimes for Few-Shot Intent Classification
Mohsen Mesgar, Thy Thy Tran, Goran Glavas +1
Few-shot Intent Classification (FSIC) is one of the key challenges in modular task-oriented dialog systems. While advanced FSIC methods are similar in using pretrained language mod…
ArgSciChat: A Dataset for Argumentative Dialogues on Scientific Papers
Federico Ruggeri, Mohsen Mesgar, Iryna Gurevych
The applications of conversational agents for scientific disciplines (as expert domains) are understudied due to the lack of dialogue data to train such agents. While most data col…
Improving Factual Consistency Between a Response and Persona Facts
Mohsen Mesgar, Edwin Simpson, Iryna Gurevych
Neural models for response generation produce responses that are semantically plausible but not necessarily factually consistent with facts describing the speaker's persona. These…
When is ACL's Deadline? A Scientific Conversational Agent
Mohsen Mesgar, Paul Youssef, Lin Li +4
Our conversational agent UKP-ATHENA assists NLP researchers in finding and exploring scientific literature, identifying relevant authors, planning or post-processing conference vis…
Dialogue Coherence Assessment Without Explicit Dialogue Act Labels
Mohsen Mesgar, Sebastian Bücker, Iryna Gurevych
Recent dialogue coherence models use the coherence features designed for monologue texts, e.g. nominal entities, to represent utterances and then explicitly augment them with dialo…
Reward Learning for Efficient Reinforcement Learning in Extractive Document Summarisation
Yang Gao, Christian M. Meyer, Mohsen Mesgar +1
Document summarisation can be formulated as a sequential decision-making problem, which can be solved by Reinforcement Learning (RL) algorithms. The predominant RL paradigm for sum…
Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems
Steffen Eger, Gözde Gül Şahin, Andreas Rücklé +6
Visual modifications to text are often used to obfuscate offensive comments in social media (e.g., "!d10t") or as a writing style ("1337" in "leet speak"), among other scenarios. W…