The NLP Group at Penn State

  Our lab went to Shingleton Gap hiking trail which is just 10 minutes away. It was an adventurous and a fun trail. We got lost 2 times with no internet but thanks to Ruihao’s navigation skills using AllTrails app which ensured we were not lost for long. Chase, Zhaohui’s dog, ensured that we never took a long stop and completed our hike earlier than expected! Hiking is always fun!

  Current NLP models heavily rely on effective representation learning algorithms. Contrastive learning is one such technique to learn an embedding space such that similar data sample pairs have close representations while dissimilar samples stay far apart from each other. It can be used in supervised or unsupervised settings using different loss functions to produce task-specific or general-purpose representations. While it has originally enabled the success for vision tasks, recent years have seen a growing number of publications in contrastive NLP. This first line of works not only delivers promising performance improvements in various NLP tasks, but also provides desired characteristics such as task-agnostic sentence representation, faithful text generation, data-efficient learning in zero-shot and few-shot settings, interpretability and explainability.

  The NLP Lab had its first hiking event of the year 2022 on June 9, 2022 at the 1000 Steps Trail in Huntingdon County. The hike covers approximately 850 feet of elevation change over the course of 0.5 miles. Dr. Passonneau found this really beautiful and challenging hike and all the lab members enjoyed the incredible views from the top of the steps.

As is the tradition, Dr. Passonneau hosted the first NLP lab party in her backyard last Friday (10th September). All of the lab members and associates alongside the new faculty Dr. Zhang enjoyed a break from the weekly work and meet with out honorary lab member Renno!

  The NLP Lab had its first in person meeting of the semester on September 2, 2021 in the lab space at Westgate Building. The main presenter for the meeting was Zhaohui who talked about his work which recently got accepted at EMNLP 2021. More information about the paper can be found in the blog post here . We also had the pleasure of having a few guests from the Center for Language Science who will be collaborating with us over the course of the semester! 

  Congratulations! A paper by Zhaohui Li, Yajur Tomar, and Rebecca J. Passonneau,  "A Semantic Feature-Wise Transformation Relation Network for Automatic Short Answer Grading", has been accepted to the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021) Main conference.  This paper is about the Automatic short answer grading (ASAG), the task of assessing students’ short natural language responses to objective questions. In this paper, we propose a Semantic Feature-wise transformation Relation Network (SFRN) that exploits the multiple components of ASAG datasets more effectively. As shown in Figure 2, a neural network is applied to capture relational knowledge among the questions (Q), reference answers or rubrics (R), and labeled student answers (A). A relation network learns vector representations for the elements of QRA triples, then combines the learned representations using learned semantic feature-wise transformations. In addition, we appl...

Maryam successfully defended her thesis defense on 14th June 2021. The online copy of the thesis can be found online using the link: https://etda.libraries.psu.edu/catalog/22618muz50  Title:  AN AGENT LEARNING DIALOGUE POLICIES FOR SENSING PERCEIVING AND LEARNING THROUGH MULTI-MODAL COMMUNICATION Abstract: Language communication is an important part of human life and a natural and intuitive way of learning new things. It is easy to imagine intelligent agents that can learn through communication to for example, help us in rescue scenarios, surgery, or even agriculture. As natural as learning through language is to humans, developing such agents has numerous challenges: Language is ambiguous, and humans convey their intentions in different ways using different words. Tasks have different learning goals and some are more complex than others. Additionally, humans differ in their communicative skills, particularly, in how much information they share or know. Thus, th...