Nikhil Mehta


2024

pdf bib
Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedback
Nikhil Mehta | Milagro Teruel | Xin Deng | Sergio Figueroa Sanz | Ahmed Awadallah | Julia Kiseleva
Findings of the Association for Computational Linguistics: EACL 2024

Many approaches to Natural Language Processing tasks often treat them as single-step problems, where an agent receives an instruction, executes it, and is evaluated based on the final outcome. However, language is inherently interactive, as evidenced by the back-and-forth nature of human conversations. In light of this, we posit that human-AI collaboration should also be interactive, with humans monitoring the work of AI agents and providing feedback that the agent can understand and utilize. Further, the AI agent should be able to detect when it needs additional information and proactively ask for help. Enabling this scenario would lead to more natural, efficient, and engaging human-AI collaboration.In this paper, we investigate these directions using the challenging task established by the IGLU competition, an interactive grounded language understanding task in a MineCraft-like world. We delve into multiple types of help players can give to the AI to guide it and analyze the impact of this help on behavior, resulting in performance improvements and an end-to-end interactive system.

2023

pdf bib
Interactively Learning Social Media Representations Improves News Source Factuality Detection
Nikhil Mehta | Dan Goldwasser
Findings of the Association for Computational Linguistics: IJCNLP-AACL 2023 (Findings)

2022

pdf bib
Tackling Fake News Detection by Continually Improving Social Context Representations using Graph Neural Networks
Nikhil Mehta | Maria Leonor Pacheco | Dan Goldwasser
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Easy access, variety of content, and fast widespread interactions are some of the reasons making social media increasingly popular. However, this rise has also enabled the propagation of fake news, text published by news sources with an intent to spread misinformation and sway beliefs. Detecting it is an important and challenging problem to prevent large scale misinformation and maintain a healthy society. We view fake news detection as reasoning over the relations between sources, articles they publish, and engaging users on social media in a graph framework. After embedding this information, we formulate inference operators which augment the graph edges by revealing unobserved interactions between its elements, such as similarity between documents’ contents and users’ engagement patterns. Our experiments over two challenging fake news detection tasks show that using inference operators leads to a better understanding of the social media framework enabling fake news spread, resulting in improved performance.

2021

pdf bib
Tackling Fake News Detection by Interactively Learning Representations using Graph Neural Networks
Nikhil Mehta | Dan Goldwasser
Proceedings of the First Workshop on Interactive Learning for Natural Language Processing

Easy access, variety of content, and fast widespread interactions are some of the reasons that have made social media increasingly popular in today’s society. However, this has also enabled the widespread propagation of fake news, text that is published with an intent to spread misinformation and sway beliefs. Detecting fake news is important to prevent misinformation and maintain a healthy society. While prior works have tackled this problem by building supervised learning systems, automatedly modeling the social media landscape that enables the spread of fake news is challenging. On the contrary, having humans fact check all news is not scalable. Thus, in this paper, we propose to approach this problem interactively, where human insight can be continually combined with an automated system, enabling better social media representation quality. Our experiments show performance improvements in this setting.

2019

pdf bib
Improving Natural Language Interaction with Robots Using Advice
Nikhil Mehta | Dan Goldwasser
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

Over the last few years, there has been growing interest in learning models for physically grounded language understanding tasks, such as the popular blocks world domain. These works typically view this problem as a single-step process, in which a human operator gives an instruction and an automated agent is evaluated on its ability to execute it. In this paper we take the first step towards increasing the bandwidth of this interaction, and suggest a protocol for including advice, high-level observations about the task, which can help constrain the agent’s prediction. We evaluate our approach on the blocks world task, and show that even simple advice can help lead to significant performance improvements. To help reduce the effort involved in supplying the advice, we also explore model self-generated advice which can still improve results.