Interactive machine learning (IML) is a beneficial learning paradigm in cases of limited data availability, as human feedback is incrementally integrated into the training process. In this paper, we present an IML pipeline for image captioning which allows us to incrementally adapt a pre-trained image captioning model to a new data distribution based on user input. In order to incorporate user input into the model, we explore the use of a combination of simple data augmentation methods to obtain larger data batches for each newly annotated data instance and implement continual learning methods to prevent catastrophic forgetting from repeated updates. For our experiments, we split a domain-specific image captioning dataset, namely VizWiz, into non-overlapping parts to simulate an incremental input flow for continually adapting the model to new data. We find that, while data augmentation worsens results, even when relatively small amounts of data are available, episodic memory is an effective strategy to retain knowledge from previously seen clusters.

Towards Adaptable and Interactive Image Captioning with Data Augmentation and Episodic Memory
Aliki Anagnostopoulou, Mareike Hartmann and Daniel Sonntag (aliki.anagnostopoulou@dfki.de)
Status: Accept

Training a model with access to human explanations can improve data efficiency and model performance on in- and out-of-domain data. Adding to these empirical findings, similarity with the process of human learning makes learning from explanations a promising way to establish a fruitful human-machine interaction. Several methods have been proposed for improving natural language processing (NLP) models with human explanations, that rely on different explanation types and mechanism for integrating these explanations into the learning process. These methods are rarely compared with each other, making it hard for practitioners to choose the best combination of explanation type and integration mechanism for a specific use-case. In this paper, we give an overview of different methods for learning from human explanations, and discuss different factors that can inform the decision of which method to choose for a specific use-case.

A survey on improving NLP models with human explanations

The Natural Language Processing (NLP) community has, in recent years, demonstrated a notable focus on improving higher scores on standard benchmarks and taking the lead on community-wide leaderboards (e.g., GLUE, SentEval). While this aspiration has led to improvements in benchmark performance of (predominantly neural) models, it has also came at a cost, i.e., increased model complexity and the ever-growing amount of computational resources required for training and using the current state-of-the-art models. Moreover, the recent research efforts have, for the most part, failed to identify sources of empirical gains in models, often failing to empirically justify the model complexity beyond benchmark performance

Because of these easily observable trends, we have proposed the SustaiNLP workshop with the goal of promoting more sustainable NLP research and practices, with two main objectives: (1) encouraging development of more efficient NLP models; and (2) providing simpler architectures and empirical justification of model complexity. For both aspects, we will encourage submissions from all topical areas of NLP.

 For more details visit our workshop website: https://sites.google.com/view/sustainlp2023
#### [Visit GatherTown](https://app.gather.town/app/5OscLswEEuYf2Psb/ACL2023)

W6: The 4th Workshop on Simple and Efficient Natural Language Processing (SustaiNLP)

workshop paper

### 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.

**Organizers:** Jacob Andreas, Karthik Narasimhan, Aida Nematzadeh
 **Description:** To a growing extent, advances across machine learning application domains are driven by advances in NLP. In computer
vision, image captions are used to shape learned representations of images [Frome et al., 2013, Mu et al., 2020, Radford
et al., 2021, Desai and Johnson 2021]. In programming languages, textual code comments are used to guide and constrain models for example-based program synthesis [Yaghmazadeh et al., 2017, Austin et al., 2021, Wong et al., 2021].
In robotics and more general policy learning settings, rules and instructions are used to enable generalization to new
environments and goals [Zhong et al., 2020, Narasimhan et al., 2018, Sharma et al., 2020]. Within NLP, rich naturallanguage annotations and task descriptions are used to improve the performance and interpretability of models for text
categorization and question answering [Hancock et al., 2018, Weller et al., 2020, Efrat et al., 2020]. And in cognitive
science, experimental evidence suggests that language shapes many other aspects of human cognition (e.g. Jones et al.,
1991). At present, however, most research on learning from language takes place within individual application domains
(and mostly outside of the NLP community). While many approaches to language supervision are domain-general, and
closely connected to “core” NLP research, there are currently no venues where researchers from across the field can meet
to share ideas and draw connections between their disparate lines of research. Our workshop will offer a central meeting
point for research on language-based supervision, enabling researchers within and beyond NLP to discuss how language
processing models and algorithms can be brought to bear on problems beyond the textual realm (e.g. visual recognition,
robotics, program synthesis, sequential decision making). Existing workshops like RoboNLP, SPLU, and ViGiL focus on
models for multi-modality; inspired by the relationship between language and human cognitive development, our workshop will emphasize broader use of language not just as an input modality but a fundamental source of information about
the structure of tasks and problem domains. In keeping with this interdisciplinary focus, our proposed format differs
in two ways from a standard NLP workshop: first, with a special emphasis on speakers and attendees who would not
typically attend NLP conferences; second, by replacing the standard panel discussion with a series of workshop-wide
breakout sessions aimed at seeding cross-institutional collaborations around new tasks, datasets, and models. **Please visit our [website](https://sites.google.com/princeton.edu/nl-supervision)**

(NL_Supervision)        The First Workshop on Learning with Natural Language Supervision

# Welcome everyone to ACL 2022!

The 60th Annual Meeting of the Association for Computational Linguistics is taking place May 22-27, 2022 as a hybrid event, in Dublin and online. We are happy to welcome all of you to this anniversary edition with an almost 50-50 in-person and virtual participation. 
The main conference program features oral presentations, in-person and virtual posters and demo sessions, a plenary session for our best paper presentations and awards, three amazing keynote events and two new initiatives of invited talks: Spotlight Talks for Young Rising Stars (STIRS) and The Next Big Idea Talks. Posters (including Findings of ACL 2022) and demos are grouped by areas for both the in-person and the virtual sessions. For the virtual component, the talks will be on Zoom and the posters and the demos will be in GatherTown. The Student Research Workshop will have an oral session and a poster session as part of Poster Session 1. The program also features eight Tutorials and 28 Workshops. 

 
We wish you a wonderful conference! 
[**The ACL 2022 Organizing Committee**](https://www.2022.aclweb.org/organisers)
 
[**Conference Handbook**](https://drive.google.com/file/d/1_BUCMfhMVrjG9E2e71aHdHeE28KSje0l/view?usp=sharing) 
[**Mini Handbook**](https://drive.google.com/file/d/1qlBKl0wzmlVF1oCeMQl3BahLd9nLP5Ce/view?usp=sharing) 
[**Posters and Demo guides**](https://drive.google.com/file/d/1UucMAoCNncIOaH1rMMDa0owuG9qgvJTG/view?usp=sharing)

ACL 2022

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 (NLP). 

Mareike Hartmann

2

1

SHORT BIO

Presentations

Towards Adaptable and Interactive Image Captioning with Data Augmentation and Episodic Memory Aliki Anagnostopoulou, Mareike Hartmann and Daniel Sonntag (aliki.anagnostopoulou@dfki.de) Status: Accept

A survey on improving NLP models with human explanations

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES