Large language models capture knowledge and abilities learned from their pre-training data, which is typically limited to text and code. We present approaches for *grounding* these LLMs to carry out tasks that involve visual perception and reasoning. Our methods leverage LLMs' abilities to generate (1) dialogue (2) questions and (3) code, putting these to use in a series of visual dialogue tasks where people interact with models in perceptually-complex settings.

Interacting with LLMs for Grounded Tasks

Symbolic Planning and Code Generation for Grounded Dialogue

Given a language model (LM), maximum probability is a poor decoding objective for open-ended generation, because it produces short and repetitive text. On the other hand, sampling can often produce incoherent text that drifts from the original topics. We propose contrastive decoding (CD), a reliable decoding approach that optimizes a contrastive objective subject to a plausibility constraint. The contrastive objective returns the difference between the likelihood under a large LM (called the expert, e.g. OPT-13B) and a small LM (called the amateur, e.g. OPT-125M), and the constraint ensures that the outputs are plausible. CD is inspired by the fact that the failures of larger LMs (e.g., repetition, inco- herence) are even more prevalent in smaller LMs, and that this difference signals which texts should be preferred. CD requires zero additional training, and produces higher quality text than decoding from the larger LM alone. It also works across model scales (OPT-13B and GPT2-1.5B) and significantly outperforms four strong decoding algorithms (e.g., nucleus, top-k) in automatic and human evaluations across wikipedia, news and story domains.

<iframe src="https://app.sli.do/event/or9aypsi961h595NQtD7kk/embed/polls/d9219db4-af70-4cf4-a60f-453c1f306be5" width="300" height="400"></iframe>

Contrastive Decoding: Open-ended Text Generation as Optimization

Generative models of code, pretrained on large corpora of programs, have shown great success in translating natural language to code (Chen et al., 2021; Austin et al., 2021; Li et al., 2022, inter alia). While these models do not explicitly incorporate program semantics (i.e., execution results) during training, they are able to generate correct solutions for many problems. However, choosing a single correct program from a generated set for each problem remains challenging. In this work, we introduce execution result--based minimum Bayes risk decoding (MBR-EXEC) for program selection and show that it improves the few-shot performance of pretrained code models on natural-language-to-code tasks. We select output programs from a generated candidate set by marginalizing over program implementations that share the same semantics. Because exact equivalence is intractable, we execute each program on a small number of test inputs to approximate semantic equivalence. Across datasets, execution or simulated execution significantly outperforms the methods that do not involve program semantics. We find that MBR-EXEC consistently improves over all execution-unaware selection methods, suggesting it as an effective approach for natural language to code translation.

Natural Language to Code Translation with Execution

**Workshop Organizers:** Prasanna Parthasarathi, Koustuv Sinha, Khyathi Raghavi Chandu, Chinnadhurai Sankar, Adina Williams, Marc-Alexandre Côté, Sarath Chandar and Joelle Pineau
 *Coffee Break 10:30 am* 
*Lunch Break 12:30 pm* 
*Coffee Break 3:30 pm* [**Workshop Website**](https://cs.mcgill.ca/~pparth2/nilli_workshop_2023/) Collaborative dialogues [1, 2, 3] with automated systems through language interactions have become ubiquitous, wherein it is becoming common from setting an alarm to planning one’s day through language interactions. With recent advances in dialogue research [1, 2, 3], embodied learning [4, 5, 6] and using language as a mode of instruction for learning agents [4, 7, 8] there is, now, a scope for realizing domains that can assume agents with primitive task knowledge and a continual interact-and-learn procedure to systematically acquire knowledge through verbal/non-verbal interactions [9, 10, 11, 12]. The research direction of building interactive learning agents [4, 7, 8, 13] facilitates the possibility of agents to have advanced interactions like taking instructions by being a pragmatic listener, asking for more samples, generating rationales for predictions, interactions to interpret learning dynamics, or even identifying or modifying a new task that can be used towards building effective learning-to-learn mechanisms. In a way, with verbal/non-verbal interactive medium this interdisciplinary field unifies research paradigms of lifelong learning, natural language processing, embodied learning, reinforcement learning, robot learning and multi-modal learning towards building interactive and interpretable AI. [**Schedule**](https://cs.mcgill.ca/~pparth2/nilli_workshop_2023/#schedule)


 [**Go to Gather**](https://app.gather.town/app/ROH1myZvp9ba7a3C/EMNLP2023?spawnToken=1aoY4ZmvSdat93h-R2-w)

W19: Novel Ideas in Learning to Learn through Interaction (NILLI)

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

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

**Workshop Organizers:** Mihai Surdeanu, Laura Chiticariu, Dayne Freitag, Gus Hahn-Powell, Clayton Morrison, Enrique Noriega, Ellen Riloff, Becky Sharp and Marco A. Valenzuela Escárcega
 *Coffee Break 10:30 am* 
*Lunch Break 12:30 pm* 
*Coffee Break 3:30 pm* [**Workshop Website**](https://pan-dl.github.io/2023/about) This workshop will focus on all aspects of pattern-based approaches, including their application, representation, and interpretability, as well as their strengths and weaknesses relative to state-of-the-art machine learning approaches. It will also explore ways of combining the strengths of pattern-based, deep learning and other statistical methods. We wish the workshop to be the first step in building a community of researchers from different areas of NLP, both applied and theoretical, who are interested in pattern-based approaches and who use them in their work (e.g., industry practitioners and domain experts). As such, beyond the standard keynote talks and user-contributed presentations, we plan for the workshop to include a panel discussion, breakout sessions on different sub-topics, and a meeting to discuss a potential shared task for future events.
 [**Go to Gather**](https://app.gather.town/app/ROH1myZvp9ba7a3C/EMNLP2023?spawnToken=IXHhoRVZTdGROtO5t26n)

W08: The Pattern-based Approaches to NLP in the Age of Deep Learning Workshop (Pan-DL)

Virtual Poster Session 3

poster

### Welcome to ACL 2023, the 61st Annual Meeting of the Association for Computational Linguistics! 
 The conference will be held in Toronto, Canada, July 9-14, 2023. 
Following the succession of the recent conferences in our field, ACL 2023 will adopt a hybrid format.
While the impact of Covid has considerably diminished in terms of traveling, obtaining visas to Canada
entails a very long process. Moreover, the global economic conditions pose challenges for many individuals to travel to conferences. Recognizing these circumstances, we know many participants may not be
able to attend the conference in person. Therefore, we are committed to providing a great virtual platform
so everyone has the opportunity to interact with other participants and enjoy the conference. Based on the
current registered participants, approxiately 30% have chosen to attend the conference virtually. Whether
you join us in person or virtually, we sincerely hope everyone has a remarkable conference experience. 
This General Chair’s message is where I express my gratitude to the many individuals who have made
enormous contributions to the conference over the past year.

Read [**ACL 2023 General Chair's message**](https://docs.google.com/document/d/1WobYM7norbG4dI48s75HfJoD89qgX5a_F-6U8AteLSA/edit?usp=sharing/) in full.

##### **[Conference Handbook](https://2023.aclweb.org/downloads/acl2023-handbook.pdf)**

ACL 2023

The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing.

**Topics:** Commonsense Reasoning
 Dialogue and Interactive Systems
 Discourse and Pragmatics
 Efficient Methods for NLP
 Ethics
 Information Extraction
 Information Retrieval and Text Mining
 Interpretability, Interactivity and Analysis of Models for NLP
 Language Modeling and Analysis of Language Models
 Linguistic Theories, Cognitive Modeling and Psycholinguistics
 Machine Learning for NLP
 Machine Learning for NLP (CL)
 Machine Translation
 Multilinguality

Poster Session 1

## Welcome to EMNLP 2022!
I am delighted to welcome you to EMNLP 2022! I believe this conference has been complicated beyond any precedent. Over the past year, it’s been thrilling to see the organization team approach each new puzzle with creativity and enthusiasm. We hope that those participating in Abu Dhabi as well as those joining remotely will leave the conference feeling newly inspired by the program and newly connected to our ever-growing community. Following EMNLP 2021 and major NLP conferences since, EMNLP 2022 is “hybrid,” serving both virtual and in-person participants.

Our key innovations for EMNLP 2022 include:

* EMNLP 2022 is “hybrid” in a second sense, as well: we allowed both direct and rolling review paper submissions, building on the pilot experiment of EMNLP 2021, which considered a small number of ARR submissions. 
* Familiar from NAACL but new to EMNLP, we’ve added an industry track.
* During the conference, “portals” will link virtual poster sessions to in-person conference participants during poster sessions each day.
* The first ACL-family conference in the United Arab Emirates.

 *Message from Noah A. Smith, University of Washington and Allen Institute for AI, Seattle, Washington, USA* 
***EMNLP 2022 General Chair***
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/9eec7d4a287ee18c278b08229290aa83.png)](https://drive.google.com/file/d/1OlPv6QBeo62VVTughj2jkiLeyHd1WnUt/view)
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/a3db7a768409f05192210d98601edb25.png)](https://emnlp2022.rocket.chat/)

To access this site you need to register. Please register [here](https://2022.emnlp.org/registration/).

Register here

EMNLP 2022

Welcome!
EMNLP 2022 will take place in Abu Dhabi from December 7th to December 11th, 2022. And it will be held in hybrid mode, both online and offline.

Daniel Fried

4

2

SHORT BIO

Presentations

Interacting with LLMs for Grounded Tasks

Symbolic Planning and Code Generation for Grounded Dialogue

Contrastive Decoding: Open-ended Text Generation as Optimization

Natural Language to Code Translation with Execution

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES