Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userFrom Masked Language Modeling to Translation: Non-English Auxiliary Tasks Improve Zero-shot Spoken Language Understanding
من النمذجة اللغوية المعقدة إلى الترجمة: المهام الإضافية غير الإنجليزية تعمل على تحسين فهم اللغة المنطوقة صفرية
309
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يعادل الافتقار إلى بيانات التقييم المتاحة للجمهور لغات الموارد المنخفضة التقدم المحرز في فهم اللغة المنطوقة (SLU).نظرا لأن المهام الرئيسية مثل تصنيف النوايا وملء الفتحات تتطلب بيانات تدريبية وفيرة، فمن المستحسن إعادة استخدام البيانات الحالية بلغات الموارد عالية الوزن لتطوير نماذج لسيناريوهات الموارد المنخفضة.نقدم XSID، معيار جديد للفتحة عبر اللغات (x) والكشف عن النوايا في 13 لغة من 6 أسر لغوية، بما في ذلك لهجة الموارد المنخفضة للغاية.لمعالجة التحدي، نقترح نهجا تعليميا مشتركا، مع بيانات تدريب Slu الإنجليزية والمهام المساعدة غير الإنجليزية من النص الخام، بناء الجملة والترجمة للنقل.نقوم بدراسة اثنين من الإعدادات التي تختلف عن طريق تغطية النوع واللغة من المبيعات المدربة مسبقا.تظهر نتائجنا أن تعلم المشترك التعلم بالمهام الرئيسية ذات النمذجة اللغوية المعقدة فعالة للفتحات، في حين أن تحويل الترجمة الآلية يعمل بشكل أفضل لتصنيف النية.
The lack of publicly available evaluation data for low-resource languages limits progress in Spoken Language Understanding (SLU). As key tasks like intent classification and slot filling require abundant training data, it is desirable to reuse existing data in high-resource languages to develop models for low-resource scenarios. We introduce xSID, a new benchmark for cross-lingual (x) Slot and Intent Detection in 13 languages from 6 language families, including a very low-resource dialect. To tackle the challenge, we propose a joint learning approach, with English SLU training data and non-English auxiliary tasks from raw text, syntax and translation for transfer. We study two setups which differ by type and language coverage of the pre-trained embeddings. Our results show that jointly learning the main tasks with masked language modeling is effective for slots, while machine translation transfer works best for intent classification.
References used
https://aclanthology.org/
rate research
Read More
Abstract We introduce Generative Spoken Language Modeling, the task of learning the acoustic and linguistic characteristics of a language from raw audio (no text, no labels), and a set of metrics to automatically evaluate the learned representations
at acoustic and linguistic levels for both encoding and generation. We set up baseline systems consisting of a discrete speech encoder (returning pseudo-text units), a generative language model (trained on pseudo- text), and a speech decoder (generating a waveform from pseudo-text) all trained without supervision and validate the proposed metrics with human evaluation. Across 3 speech encoders (CPC, wav2vec 2.0, HuBERT), we find that the number of discrete units (50, 100, or 200) matters in a task-dependent and encoder- dependent way, and that some combinations approach text-based systems.1
With the early success of query-answer assistants such as Alexa and Siri, research attempts to expand system capabilities of handling service automation are now abundant. However, preliminary systems have quickly found the inadequacy in relying on si
mple classification techniques to effectively accomplish the automation task. The main challenge is that the dialogue often involves complexity in user's intents (or purposes) which are multiproned, subject to spontaneous change, and difficult to track. Furthermore, public datasets have not considered these complications and the general semantic annotations are lacking which may result in zero-shot problem. Motivated by the above, we propose a Label-Aware BERT Attention Network (LABAN) for zero-shot multi-intent detection. We first encode input utterances with BERT and construct a label embedded space by considering embedded semantics in intent labels. An input utterance is then classified based on its projection weights on each intent embedding in this embedded space. We show that it successfully extends to few/zero-shot setting where part of intent labels are unseen in training data, by also taking account of semantics in these unseen intent labels. Experimental results show that our approach is capable of detecting many unseen intent labels correctly. It also achieves the state-of-the-art performance on five multi-intent datasets in normal cases.
Spoken language understanding, usually including intent detection and slot filling, is a core component to build a spoken dialog system. Recent research shows promising results by jointly learning of those two tasks based on the fact that slot fillin
g and intent detection are sharing semantic knowledge. Furthermore, attention mechanism boosts joint learning to achieve state-of-the-art results. However, current joint learning models ignore the following important facts: 1. Long-term slot context is not traced effectively, which is crucial for future slot filling. 2. Slot tagging and intent detection could be mutually rewarding, but bi-directional interaction between slot filling and intent detection remains seldom explored. In this paper, we propose a novel approach to model long-term slot context and to fully utilize the semantic correlation between slots and intents. We adopt a key-value memory network to model slot context dynamically and to track more important slot tags decoded before, which are then fed into our decoder for slot tagging. Furthermore, gated memory information is utilized to perform intent detection, mutually improving both tasks through global optimization. Experiments on benchmark ATIS and Snips datasets show that our model achieves state-of-the-art performance and outperforms other methods, especially for the slot filling task.
Lack of training data presents a grand challenge to scaling out spoken language understanding (SLU) to low-resource languages. Although various data augmentation approaches have been proposed to synthesize training data in low-resource target languag
es, the augmented data sets are often noisy, and thus impede the performance of SLU models. In this paper we focus on mitigating noise in augmented data. We develop a denoising training approach. Multiple models are trained with data produced by various augmented methods. Those models provide supervision signals to each other. The experimental results show that our method outperforms the existing state of the art by 3.05 and 4.24 percentage points on two benchmark datasets, respectively. The code will be made open sourced on github.
We study how masking and predicting tokens in an unsupervised fashion can give rise to linguistic structures and downstream performance gains. Recent theories have suggested that pretrained language models acquire useful inductive biases through mask
s that implicitly act as cloze reductions for downstream tasks. While appealing, we show that the success of the random masking strategy used in practice cannot be explained by such cloze-like masks alone. We construct cloze-like masks using task-specific lexicons for three different classification datasets and show that the majority of pretrained performance gains come from generic masks that are not associated with the lexicon. To explain the empirical success of these generic masks, we demonstrate a correspondence between the Masked Language Model (MLM) objective and existing methods for learning statistical dependencies in graphical models. Using this, we derive a method for extracting these learned statistical dependencies in MLMs and show that these dependencies encode useful inductive biases in the form of syntactic structures. In an unsupervised parsing evaluation, simply forming a minimum spanning tree on the implied statistical dependence structure outperforms a classic method for unsupervised parsing (58.74 vs. 55.91 UUAS).
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
