The NLP Group at Penn State

Maryam Zare (NLP Ph.D. Penn State) has a 2022 EMNLP paper based on her thesis: "A POMDP Dialogue Policy with 3-way Grounding and Adaptive Sensing for Learning through Communication " .  Maryam, who has been at Apple since her graduation in August 2021, developed a single dialogue policy for an artificial agent to learn board games from people through multimodal dialogue interaction. It adapts its questions to its evolving perception of how informative the current dialogue partner is, and it can continue learning across dialogues.

The NLP Lab's recent contributions to a collaboration with University of  Wisconsin's Center for Education Research  are featured in an October 2022 article in the PSU Engineering News.  The article describes two recent publications leading to deployment of our content assessment software,  PyrEval , in middle school classrooms in Wisconsin for assessment of students' understanding of physics ideas.

    Becky, Ruihao, Zhaohui, Berk and lovely Renno are enjoying the great view and nice weather On 10/09, we hiked for the first time this Fall to enjoy the weather and nice views. We hiked from Beaver Mills to Ralph's Majestic Vista of Allegheny Front Trail. It was a great social event as you can see from the pictures. Pretty good at Ralph's Majestic Vista

  Another NLP lab party! As a tradition, every year Dr. Passonneau invites all the NLP lab members to her house for students to get to know each other better as the school year begins. This year, the NLP lab party was an outdoor event with some grilled food!

  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.