More Like this

1. Mungojerrie: Linear-Time Objectives in Model-Free Reinforcement Learning.

   https://doi.org/10.1007/978-3-031-30823-9_27  

   Hahn, Ernst Moritz; Perez, Mateo; Schewe, Sven; Somenzi, Fabio; Trivedi, Ashutosh; Wojtczak, Dominik (April 2023, Tools and Algorithms for the Construction and Analysis of Systems. TACAS 2023.)

   Sankaranarayanan, S.; Sharygina, N. (Ed.)

   Mungojerrie is an extensible tool that provides a framework to translate linear-time objectives into reward for reinforcement learning (RL). The tool provides convergent RL algorithms for stochastic games, reference implementations of existing reward translations for omega-regular objectives, and an internal probabilistic model checker for omega-regular objectives. This functionality is modular and operates on shared data structures, which enables fast development of new translation techniques. Mungojerrie supports finite models specified in PRISM and omega-automata specified in the HOA format, with an integrated command line interface to external linear temporal logic translators. Mungojerrie is distributed with a set of benchmarks for omega-regular objectives in RL. 

   more » « less
2. Cultural and Geographical Influences on Image Translatability of Words across Languages

   https://doi.org/10.18653/v1/2021.naacl-main.19  

   Khani, Nikzad; Tourni, Isidora; Rasooli, Mohammad Sadegh; Callison-Burch, Chris; Wijaya, Derry Tanti (January 2021, The 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies)

   null (Ed.)

   Neural Machine Translation (NMT) models have been observed to produce poor translations when there are few/no parallel sentences to train the models. In the absence of parallel data, several approaches have turned to the use of images to learn translations. Since images of words, e.g., horse may be unchanged across languages, translations can be identified via images associated with words in different languages that have a high degree of visual similarity. However, translating via images has been shown to improve upon text-only models only marginally. To better understand when images are useful for translation, we study image translatability of words, which we define as the translatability of words via images, by measuring intra- and inter-cluster similarities of image representations of words that are translations of each other. We find that images of words are not always invariant across languages, and that language pairs with shared culture, meaning having either a common language family, ethnicity or religion, have improved image translatability (i.e., have more similar images for similar words) compared to its converse, regardless of their geographic proximity. In addition, in line with previous works that show images help more in translating concrete words, we found that concrete words have improved image translatability compared to abstract ones. 

   more » « less
3. Explaining with Contrastive Phrasal Highlighting: A Case Study in Assisting Humans to Detect Translation Differences

   https://doi.org/10.18653/v1/2023.emnlp-main.690  

   Briakou, Eleftheria; Goyal, Navita; Carpuat, Marine (December 2023, Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing)

   Explainable NLP techniques primarily explain by answering “Which tokens in the input are responsible for this prediction?”. We argue that for NLP models that make predictions by comparing two input texts, it is more useful to explain by answering “What differences between the two inputs explain this prediction?”. We introduce a technique to generate contrastive phrasal highlights that explain the predictions of a semantic divergence model via phrase alignment guided erasure. We show that the resulting highlights match human rationales of cross-lingual semantic differences better than popular post-hoc saliency techniques and that they successfully help people detect fine-grained meaning differences in human translations and critical machine translation errors. 

   more » « less
4. SimQA: Detecting Simultaneous MT Errors through Word-by-Word Question Answering

   https://doi.org/10.18653/v1/2022.emnlp-main.378  

   Han, HyoJung; Carpuat, Marine; Boyd-Graber, Jordan (January 2022, Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing)

   Detractors of neural machine translation admit that while its translations are fluent, it sometimes gets key facts wrong. This is particularly important in simultaneous interpretation where translations have to be provided as fast as possible: before a sentence is complete. Yet, evaluations of simultaneous machine translation (SimulMT) fail to capture if systems correctly translate the most salient elements of a question: people, places, and dates. To address this problem, we introduce a downstream word-by-word question answering evaluation task (SimQA): given a source language question, translate the question word by word into the target language, and answer as soon as possible. SimQA jointly measures whether the SimulMT models translate the question quickly and accurately, and can reveal shortcomings in existing neural systems—hallucinating or omitting facts. 

   more » « less
5. How Transgender People and Communities Were Involved in Trans Technology Design Processes

   https://doi.org/10.1145/3544548.3580972  

   Haimson, Oliver L.; Nham, Kai; Thach, Hibby; DeGuia, Aloe (April 2023, Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems)

   Trans technology – technology created to help address challenges that trans people face – is an important area for innovation that can help improve marginalized people’s lives. We conducted 104 interviews with 115 creators of trans technology to understand how they involved trans people and communities in design processes. We describe projects that used human-centered design processes, as well as design processes that involved trans people in smaller ways, including gathering feedback from users, conducting user testing, or the creators being trans themselves. We show how involving trans people and communities in design is vital for trans technologies to realize their potential for addressing trans needs. Yet we highlight a frequent gap between trans technology design and deployment, and discuss ways to bridge this gap. We argue for the importance of involving community in trans technology design to ensure that trans technology achieves its promise of helping address trans needs and challenges. 

   more » « less