Singapore

Large language models (LLMs) have shown increasing capacity at planning and executing a high-level goal in a live computer environment (e.g. MiniWoB++). To perform a task, recent works often require a model to learn from trace examples of the task via either supervised learning or few/many-shot prompting. Without these trace examples, it remains a challenge how an agent can autonomously learn and improve its control on a computer, which limits the ability of an agent to perform a new task. We approach this problem with a zero-shot agent that requires no given expert traces. Our agent plans for executable actions on a partially observed environment, and iteratively progresses a task by identifying and learning from its mistakes via self-reflection and structured thought management. On the easy tasks of MiniWoB++, we show that our zero-shot agent often outperforms recent SoTAs, with more efficient reasoning. For tasks with more complexity, our reflective agent performs on par with prior best models, even though previous works had the advantages of accessing expert traces or additional screen information.

EMNLP 2023

A Zero-Shot Language Agent for Computer Control with Structured Reflection

language agent

miniwob

reflection

workshop paper

**Welcome to EMNLP 2023!**

On behalf of the EMNLP 2023 Organizing Committee, I extend a warm and heartfelt welcome to all of you to the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP). It is with immense pleasure and excitement that we gather here in Singapore, a vibrant hub of innovation and technological advancement.

The conference program is packed with insightful presentations, thought-provoking workshops, and engaging networking opportunities. In addition to the technical sessions, we have also planned several social events that will provide you with the opportunity to connect with your colleagues.

The conference is held in person at the Resorts World Convention Centre in Singapore, and available on-line with the help of Underline.

For those in Singapore, I hope that you will find time to explore the exciting Sentosa Island, Gardens by the Bay, Singapore Botanic Gardens and the many other attractions unique to Singapore.

Of course, we are grateful to our sponsors and partners for their generous support of EMNLP 2023, whose contributions make it possible for us to host this world-class event.

Yuji Matsumoto (RIKEN AIP) 
EMNLP 2023 General Chair

To access the **EMNLP 2023** event page on Underline, you need to register for the Conference. 
Please follow **[this link](https://2023.emnlp.org/registration/)** for more details.

EMNLP 2023 took place in Singapore from Dec 6th to Dec 10th, 2023.

Instruction following language models have shown a remarkable ability to perform a wide range of tasks with little to no additional training data. Do these abilities come from a revolution in pre-training and instruction-following, or are there other more mundane explanations for how these models work? In this talk, I will discuss our efforts to answer these questions by replicating instruction-following models that generalize across tasks, studying the consistency of these models across different task formats, and building tests for benchmark contamination in pretraining.

Understanding generalization for instruction following and black-box language models | VIDEO

Evaluation after the LLM boom: frustrations, fallacies, and the future | VIDEO

One of the frequent points in the mainstream narrative about large language models is that they have “emergent properties” (sometimes even dangerous enough to be considered existential risk to mankind). However, there is much disagreement about even the very definition of such properties. If they are understood as a kind of generalization beyond training data - as something that a model does without being explicitly trained for it - I argue that we have not in fact established the existence of any such properties, and at the moment we do not even have the methodology for doing so.

A sanity check on emergent properties

Open-domain dialogue system usually requires different sources of knowledge to generate more informative and evidential responses. However, existing knowledge-grounded dialogue systems either focus on a single knowledge source or overlook the dependency between multiple sources of knowledge, which may result in generating inconsistent or even paradoxical responses. To incorporate multiple knowledge sources and dependencies between them, we propose SAFARI, a novel framework that leverages the exceptional capabilities of large language models (LLMs) in planning, understanding, and incorporating under both supervised and unsupervised settings. Specifically, SAFARI decouples the knowledge grounding into multiple sources and response generation, which allows easy extension to various knowledge sources including the possibility of not using any sources. To study the problem, we construct a personalized knowledge-grounded dialogue dataset Knowledge Behind Persona (KBP), which is the first to consider the dependency between persona and implicit knowledge. Experimental results on the KBP dataset demonstrate that the SAFARI framework can effectively produce persona-consistent and knowledge-enhanced responses.

Large Language Models as Source Planner for Personalized Knowledge-grounded Dialogues

Natural language is an instrument of interaction, where interlocutors produce and comprehend language to relay information to accomplish their intents. Both opportunities and challenges arise from the interactive nature of language. The response of participants to the language they comprehend can form a strong learning signal: did I achieve my intent? In the first part, I will define a simple, and general framework to rapidly learn from interaction feedback, and show how to use this signal to learn to produce natural language instructions. I will then discuss the problem of language-conditioned reinforcement learning, where benchmark development has been hindered because computing rewards requires resolving language semantics. I will describe a new approach to address this challenge.

Natural Language Learning via Interaction

Ontonotes has served as the most important benchmark for coreference resolution. However, for ease of annotation, several long documents in Ontonotes were split into smaller parts. In this work, we build a corpus of coreference-annotated documents of significantly longer length than what is currently available. We do so by providing an accurate, manually-curated, merging of annotations from documents that were split into multiple parts in the original Ontonotes annotation process. The resulting corpus, which we call LongtoNotes contains documents in multiple genres of the English language with varying lengths, the longest of which are up to 8x the length of documents in Ontonotes, and 2x those in Litbank. We evaluate state-of-the-art neural coreference systems on this new corpus, analyze the relationships between model architectures/hyperparameters and document length on performance and efficiency of the models, and demonstrate areas of improvement in long-document coreference modeling revealed by our new corpus.

LongtoNotes: OntoNotes with Longer Coreference Chain

Oral Presentations of Contextual Bangla Neural Stemmer: Finding Contextualized Root Word Representations for Bangla Words

Oral Presentation of CNS Model-Paper ID: 68 | VIDEO

The prevalence and salience of LMs has changed the way many researchers in NLP think about our work, causing many issues for model evaluation. This presentation presents a retrospective of recent past approaches to modeling text, and discusses what has changed, and what the current evaluation challenges are. Next, it discusses common pitfalls that LM-based research falls into, highlighting several fallacies, and suggesting ways to avoid them. Finally, this presentation highlights the importance of meta-evaluation research (the evaluation of our evaluations) as one crucial component to overcoming LM evaluation challenges in the post LM-boom.

Evaluation after the LM boom: Frustrations, fallacies andthe future

Emotion arcs capture how an individual (or a population) feels over time. They are widely used in industry and research; however, there is little work on evaluating the automatically generated arcs. This is because of the difficulty of establishing the true (gold) emotion arc. Our work, for the first time, systematically and quantitatively evaluates automatically generated emotion arcs. We also compare two common ways of generating emotion arcs: Machine-Learning (ML) models and Lexicon-Only (LexO) methods. By running experiments on 18 diverse datasets in 9 languages, we show that despite being markedly poor at instance level emotion classification, LexO methods are highly accurate at generating emotion arcs when aggregating information from hundreds of instances. We also show, through experiments on six indigenous African languages, as well as Arabic, and Spanish, that automatic translations of English emotion lexicons can be used to generate high-quality emotion arcs in less-resource languages. This opens up avenues for work on emotions in languages from around the world; which is crucial for commerce, public policy, and health research in service of speakers often left behind. Code and resources: https://github.com/dteodore/EmotionArcs

Premium content

A Zero-Shot Language Agent for Computer Control with Structured Reflection

Downloads

Next from EMNLP 2023

Understanding generalization for instruction following and black-box language models | VIDEO

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES