Elad Ben Avraham, ChangHao Li, Ron Dorfman, Roy Ganz, Oren Nuriel, Amir Dudai, Aviad Aberdam, Noah Flynn, Elman Mansimov, Aditya Kalyanpur, Ron Litman. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Raphael Schumann, Elman Mansimov, Yi-An Lai, Nikolaos Pappas, Xibin Gao, Yi Zhang. Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

Mujeen Sung, James Gung, Elman Mansimov, Nikolaos Pappas, Raphael Shu, Salvatore Romeo, Yi Zhang, Vittorio Castelli. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

Shamik Roy, Raphael Shu, Nikolaos Pappas, Elman Mansimov, Yi Zhang, Saab Mansour, Dan Roth. Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

We introduce a Recursive INsertion-based Encoder (RINE), a novel approach for semantic parsing in task-oriented dialog. Our model consists of an encoder network that incrementally builds the semantic parse tree by predicting the non-terminal label and its positions in the linearized tree. At the generation time, the model constructs the semantic parse tree by recursively inserting the predicted non-terminal labels at the predicted positions until termination. RINE achieves state-of-the-art exact match accuracy on low- and high-resource versions of the conversational semantic parsing benchmark TOP, outperforming strong sequence-to-sequence models and transition-based parsers. We also show that our model design is applicable to nested named entity recognition task, where it performs on par with state-of-the-art approach designed for that task. Finally, we demonstrate that our approach is 2-3.5 times faster than the sequence-to-sequence model at inference time.

Aaron Mueller, Jason Krone, Salvatore Romeo, Saab Mansour, Elman Mansimov, Yi Zhang, Dan Roth. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2022.

Pre-trained language models have been recently shown to benefit task-oriented dialogue (TOD) systems.Despite their success, existing methods often formulate this task as a cascaded generation problem which can lead to error accumulation across different sub-tasks and greater data annotation overhead.In this study, we present PPTOD, a unified plug-andplay model for task-oriented dialogue.In addition, we introduce a new dialogue multi-task pre-training strategy that allows the model to learn the primary TOD task completion skills from heterogeneous dialog corpora.We extensively test our model on three benchmark TOD tasks, including end-to-end dialogue modelling, dialogue state tracking, and intent classification.Experimental results show that PPTOD achieves new state of the art on all evaluated tasks in both high-resource and lowresource scenarios.Furthermore, comparisons against previous SOTA methods show that the responses generated by PPTOD are more factually correct and semantically coherent as judged by human annotators. 1

Recent advance in deep learning has led to rapid adoption of machine learning based NLP models in a wide range of applications. Despite the continuous gain in accuracy, backward compatibility is also an important aspect for industrial applications, yet it received little research attention. Backward compatibility requires that the new model does not regress on cases that were correctly handled by its predecessor. This work studies model update regression in structured prediction tasks. We choose syntactic dependency parsing and conversational semantic parsing as representative examples of structured prediction tasks in NLP. First, we measure and analyze model update regression in different model update settings. Next, we explore and benchmark existing techniques for reducing model update regression including model ensemble and knowledge distillation. We further propose a simple and effective method, Backward-Congruent Re-ranking (BCR), by taking into account the characteristics of structured output. Experiments show that BCR can better mitigate model update regression than model ensemble and knowledge distillation approaches.

We propose a conditional non-autoregressive neural sequence model based on iterative refinement.The proposed model is designed based on the principles of latent variable models and denoising autoencoders, and is generally applicable to any sequence generation task.We extensively evaluate the proposed model on machine translation (En$De and En$Ro) and image caption generation, and observe that it significantly speeds up decoding while maintaining the generation quality comparable to the autoregressive counterpart.

Limited literacy and visual impairment reduce the ability of many to read on their own. Current e-reader solutions rely on either unnatural synthetic voices or professionally produced audio e-books. Neither provide the same enjoyment as having a family member read to a user, especially when the user requires assistive reading (following printed text while listening to it being read). Unfortunately, the support for non-commercial production of such e-books is limited and requires significant effort. We evaluate a novel, assistive mobile interaction technique that facilitates the recording of audio e-books and their synchronization with the read text. We show that a technique based on a finger tracking metaphor provides optimal support with respect to reading speed. These human-in-the-loop, adaptive techniques can now be used to reduce the content-creation burden that is associated with supporting those who cannot read on their own.

In this work, we propose to apply trust region optimization to deep reinforcement learning using a recently proposed Kronecker-factored approximation to the curvature. We extend the framework of natural policy gradient and propose to optimize both the actor and the critic using Kronecker-factored approximate curvature (K-FAC) with trust region; hence we call our method Actor Critic using Kronecker-Factored Trust Region (ACKTR). To the best of our knowledge, this is the first scalable trust region natural gradient method for actor-critic methods. It is also the method that learns non-trivial tasks in continuous control as well as discrete control policies directly from raw pixel inputs. We tested our approach across discrete domains in Atari games as well as continuous domains in the MuJoCo environment. With the proposed methods, we are able to achieve higher rewards and a 2- to 3-fold improvement in sample efficiency on average, compared to previous state-of-the-art on-policy actor-critic methods. Code is available at https://github.com/openai/baselines

We use Long Short Term Memory (LSTM) networks to learn representations of video sequences. Our model uses an encoder LSTM to map an input sequence into a fixed length representation. This representation is decoded using single or multiple decoder LSTMs to perform different tasks, such as reconstructing the input sequence, or predicting the future sequence. We experiment with two kinds of input sequences – patches of image pixels and high-level representations (“percepts") of video frames extracted using a pretrained convolutional net. We explore different design choices such as whether the decoder LSTMs should condition on the generated output. We analyze the outputs of the model qualitatively to see how well the model can extrapolate the learned video representation into the future and into the past. We further evaluate the representations by finetuning them for a supervised learning problem – human action recognition on the UCF-101 and HMDB-51 datasets. We show that the representations help improve classification accuracy, especially when there are only few training examples. Even models pretrained on unrelated datasets (300 hours of YouTube videos) can help action recognition performance.