We are excited to host an Exclusive Event on the latest trends in AI featuring Nathan Lambert, Alessio Fanelli, and Dylan Patel, where they’ll dive deep into the latest trends shaping the future of AI. From cutting-edge innovations to real-world applications, this session will provide valuable insights for AI enthusiasts, industry leaders, and anyone curious about the transformative power of artificial intelligence.

 Date: Friday, March 7, 2025
 Time: 3:15 – 6:30 PM PST
 Location: 3175 Bowers Ave., Santa Clara, CA or Livestream on YouTube@NLP_UCSC
 Register here: bit.ly/3QmOSwC

It’s a fascinating time to work in natural language processing. In recent years, we’ve witnessed incredible advances in AI and a growing global interest in the NLP methods and technologies driving recent innovations. This year, industry experts and research scientists gathered in Toronto at the 61st Annual Meeting of the Association for Computational Linguistics to discuss the field’s emerging trends and developments, and to showcase important contributions to state-of-the-art research in NLP, computational linguistics, and machine learning.

We’re proud to share that UCSC faculty and students presented six papers at the conference. Keep reading to learn more about each paper and the high-impact research conducted by UCSC’s NLP community.

CausalDialogue: Modeling Utterance-level Causality in Conversations

Yi-Lin Tuan, Alon Albalak, Wenda Xu, Michael Saxon, Connor Pryor, Lise Getoor, William Yang Wang

Abstract preview: Despite their widespread adoption, neural conversation models have yet to exhibit natural chat capabilities with humans. In this research, we examine user utterances as causes and generated responses as effects, recognizing that changes in a cause should produce a different effect. To further explore this concept, we have compiled and expanded upon a new dataset called CausalDialogue through crowd-sourcing. Read the full abstract and paper in the ACL Anthology.

Aerial Vision-and-Dialog Navigation

Yue Fan, Winson Chen, Tongzhou Jiang, Chun Zhou, Yi Zhang, Xin Wang

Abstract preview: The ability to converse with humans and follow natural language commands is crucial for intelligent unmanned aerial vehicles (a.k.a. drones). It can relieve people’s burden of holding a controller all the time, allow multitasking, and make drone control more accessible for people with disabilities or with their hands occupied. To this end, we introduce Aerial Vision-and-Dialog Navigation (AVDN), to navigate a drone via natural language conversation. Read the full abstract and paper in the ACL Anthology.

Automatic Identification of Code-Switching Functions in Speech Transcripts

Ritu Belani, Jeffrey Flanigan

Abstract preview: Code-switching, or switching between languages, occurs for many reasons and has important linguistic, sociological, and cultural implications. Multilingual speakers code-switch for a variety of communicative functions, such as expressing emotions, borrowing terms, making jokes, introducing a new topic, etc. The function of code-switching may be quite useful for the analysis of linguists, cognitive scientists, speech therapists, and others, but is not readily apparent. To remedy this situation, we annotate and release a new dataset of functions of code-switching in Spanish-English. Read the full abstract and paper in the ACL Anthology.

Diverse Retrieval-Augmented In-Context Learning for Dialogue State Tracking

Brendan King, Jeffrey Flanigan

Abstract preview: There has been significant interest in zero and few-shot learning for dialogue state tracking (DST) due to the high cost of collecting and annotating task-oriented dialogues. Recent work has demonstrated that in-context learning requires very little data and zero parameter updates, and even outperforms trained methods in the few-shot setting. We propose RefPyDST, which advances the state of the art with three advancements to in-context learning for DST. Read the full abstract and paper in the ACL Anthology.

ACL 2023 poster prepared by Brendan King and NLP faculty member, Professor Jeffrey Flanigan, showcasing their paper, “Diverse Retrieval-Augmented In-Context Learning for Dialogue State Tracking”

T2IAT: Measuring Valence and Stereotypical Biases in Text-to-Image Generation

Jialu Wang, Xinyue Liu, Zonglin Di, Yang Liu, Xin Wang

Abstract preview: *Warning: This paper contains several contents that may be toxic, harmful, or offensive.* In the last few years, text-to-image generative models have gained remarkable success in generating images with unprecedented quality accompanied by a breakthrough of inference speed. Despite their rapid progress, human biases that manifest in the training examples, particularly with regard to common stereotypical biases, like gender and skin tone, still have been found in these generative models. In this work, we seek to measure more complex human biases existing in the task of text-to-image generations. Inspired by the well-known Implicit Association Test (IAT) from social psychology, we propose a novel Text-to-Image Association Test (T2IAT) framework that quantifies the implicit stereotypes between concepts and valence, and those in the images. Read the full abstract and paper in the ACL Anthology.

Using Domain Knowledge to Guide Dialog Structure Induction via Neural Probabilistic Soft Logic

Connor Pryor, Quan Yuan, Jeremiah Liu, Mehran Kazemi, Deepak Ramachandran, Tania Bedrax-Weiss, Lise Getoor

Abstract preview: Dialog Structure Induction (DSI) is the task of inferring the latent dialog structure (i.e., a set of dialog states and their temporal transitions) of a given goal-oriented dialog. It is a critical component for modern dialog system design and discourse analysis. Existing DSI approaches are often purely data-driven, deploy models that infer latent states without access to domain knowledge, underperform when the training corpus is limited/noisy, or have difficulty when test dialogs exhibit distributional shifts from the training domain. This work explores a neural-symbolic approach as a potential solution to these problems. Read the full abstract and paper in the ACL Anthology.

Congratulations to all who presented at the 2023 ACL Conference! We are tremendously proud of our UCSC faculty and students for their important contributions to high-impact research in NLP, AI, and machine learning.

If you are relocating to Silicon Valley, you are not alone! Many students before you have done the same. In this post, Pranjali Basmatkar (NLP student 2022-2023), shares her advice for moving to Santa Clara, California. Please note that the views and opinions expressed on this page represent the author’s views and do not necessarily represent the official position or views of UC Santa Cruz or the NLP MS Program.

Moving to a new place or country, such as Santa Clara, can be exciting but challenging. The thought of starting fresh in an unfamiliar environment can feel daunting, especially for students; however, with the right information and resources, this transition can be made much smoother.

A little about me: I am Pranjali Basmatkar, a current Natural Language Processing Master’s student at the University of California, Santa Cruz. Most of my classes take place in the Silicon Valley Campus located in Santa Clara. As someone who made the move from India less than a year ago, I have some tips from my personal experience that can help you settle down with ease. So if you are an incoming UCSC graduate student, keep reading!

Preparing for the Move

Proactively preparing for your move to Santa Clara is crucial to ensure a smooth transition. Personally, I focused on three main aspects: researching the area, finding suitable housing, and budgeting for living expenses. This preparation can help you alleviate stress and make the most of your move.

Getting to know the area

I found the best way to familiarize myself with a new area was by checking a map! I relied on Google Maps to understand the location of the campus and the areas that are easily accessible from the campus. The campus is surrounded by various eateries and is very well connected to residential areas such as Rivermark and El Camino, and is a 10-minute drive from the buzzing San Jose Downtown.

Finding housing

Finding the right house was one of my biggest challenges while making the move, and it is important to prepare for this in advance. There are two main ways to find housing: find a spare room in an existing house or find roommates.

The NLP Graduate Student Handbook lists a variety of sites you can use as part of your housing search, like Apartments.com and other online platforms. There are also numerous Bay Area Facebook groups you can use to connect with people.

The best way to find a house can be by looking for roommates from your cohort or existing students who study at the campus! The Slack Workspace for incoming students is a great place to introduce yourself to potential roommates and finalize your housing in Santa Clara. Make sure to consider factors such as proximity to your educational institution, safety, amenities, and affordability when choosing your housing option.

Budgeting for living expenses

Moving to a new place involves financial considerations. It is essential to create a budget for your living expenses in Santa Clara. Research the cost of living in the area, including rent, utilities, groceries, transportation, and other necessities. You can use online budgeting tools or create a spreadsheet to estimate your monthly expenses and compare them with your available financial resources. Setting a realistic budget will help you manage your finances effectively and avoid any financial strains while living in Santa Clara.