Apple sponsored the 58th Annual Meeting of the Association for Computational Linguistics (ACL) from July 5 - 10. ACL is the premier conference of the field of computational linguistics, covering a broad spectrum of research areas regarding computational approaches to natural language.
Bo-Hsiang Tseng, Yimai Fang, Jianpeng Cheng, David Vandyke
Natural language understanding (NLU) and natural language generation (NLG) are two fundamental and related tasks in building task-oriented dialogue systems with opposite objectives: NLU tackles the transformation from natural language to formal representations, whereas NLG does the reverse. A key to success in either task is parallel training data which is expensive to obtain at a large scale. In this work, we propose a gener- ative model which couples NLU and NLG through a shared latent variable. This approach allows us to explore both spaces of natural language and formal representations, and facilitates information sharing through the latent space to eventually benefit NLU and NLG. Our model achieves state-of-the-art per- formance on two dialogue datasets with both flat and tree-structured formal representations. We also show that the model can be trained in a semi-supervised fashion by utilising unla- belled data to boost its performance.
Matthias Sperber, Matthias Paulik
Over its three decade history, speech translation has experienced several shifts in its primary research themes; moving from loosely coupled cascades of speech recognition and machine translation, to exploring questions of tight coupling, and finally to end-to-end models that have recently attracted much attention. This paper provides a brief survey of these developments, along with a discussion of the main challenges of traditional approaches which stem from committing to intermediate representations from the speech recognizer, and from training cascaded models separately towards different objectives. Recent end-to-end modeling techniques promise a principled way of overcoming these issues by allowing joint training of all model components and removing the need for explicit intermediate representations. However, a closer look reveals that many end-to-end models fall short of solving these issues, due to compromises made to address data scarcity. This paper provides a unifying categorization and nomenclature that covers both traditional and recent approaches and that may help researchers by highlighting both trade-offs and open research questions.
Hendra Setiawan, Matthias Sperber, Udhay Nallasamy, Matthias Paulik
Variational Neural Machine Translation (VNMT) is an attractive framework for modeling the generation of target translations, conditioned not only on the source sentence but also on some latent random variables. The latent variable modeling may introduce useful statistical dependencies that can improve translation accuracy. Unfortunately, learning informative latent variables is non-trivial, as the latent space can be prohibitively large, and the latent codes are prone to be ignored by many translation models at training time. Previous works impose strong assumptions on the distribution of the latent code and limit the choice of the NMT architecture. In this paper, we propose to apply the VNMT framework to the state-of-the-art Transformer and introduce a more flexible approximate posterior based on normalizing flows. We demonstrate the efficacy of our proposal under both in-domain and out-of-domain conditions, significantly outperforming strong baselines.
The 2nd Workshop on NLP for Conversational AI workshop brought together NLP researchers and practitioners in different fields alongside experts in speech and machine learning. The workshop features keynotes, posters, and panel sessions to discuss the state-of-the-art in conversational artificial intelligence, to share insights and challenges, to bridge the gap between academic research and real-world product deployment, and to shed light on where the field is going.
Jason Williams from Apple gave a virtual keynote talk entitled Label Accuracy and Dialog State Tracking on July 9.
Apple sponsored the Widening Natural Language Processing (WiNLP) workshop on July 5. WiNLP seeks to highlight diversity in scientific background, discipline, training, obtained degrees, and seniority. The full-day event includee invited talks, panel discussion, and poster sessions. The workshop provided an excellent opportunity for junior members in the community to showcase their work and connect with senior mentors for feedback and career advice. The workshop was open to everyone working in NLP at all levels.