Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userImproving Named Entity Recognition in Spoken Dialog Systems by Context and Speech Pattern Modeling
تحسين التعرف على الكيان المسمى في أنظمة الحوار المنطوق حسب النمذجة السياق ونمط الكلام
357
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في حين أن التعرف على الكيان المسمى (NER) من الكلام كان موجودا طالما أن NER من نص مكتوب لديه، فإن دقة NER من الكلام كانت أيضا أقل بكثير من NER من النص. يبرز ارتفاع شعبية أنظمة الحوار المنطوقة مثل Siri أو Alexa الحاجة إلى أكثر دقة من الكلام من الكلام لأن NER هو مكون أساسي لفهم ما قاله المستخدمون في الحوار. تتلقى أنظمة الحوار المنطوقة المنطوقة إدخال المستخدم في شكل نصوص التعرف على الكلام التلقائي (ASR)، وببساطة تطبيق نموذج NER المدربين على النص المكتوب إلى نصوص ASR غالبا ما يؤدي إلى دقة منخفضة لأنها مقارنة بالنص المكتبكي، تفتقر نصوص ASR إلى إشارات مهمة مثل علامات الترقيم والرسملة. علاوة على ذلك، فإن الأخطاء في نصوص العصر تجعل أيضا NER من الكلام الصعب. نقترح نماذجين تستغلوا أدلة سياق الحوار ونمط الكلام لاستخراج الكيانات المسماة بدقة أكثر دقة من مربعات الحوار المفتوحة في أنظمة الحوار المنطوقة. تظهر نتائجنا الاستفادة من سياق حوار النمذجة وأنماط الكلام في إعدادتين: إعداد قياسي مع قسم عشوائي من البيانات وأكثر واقعية من الإعداد ولكن أيضا أكثر صعوبة حيث تكون العديد من الكيانات المسماة التي تمت مواجهتها أثناء النشر غير مرئي أثناء التدريب.
While named entity recognition (NER) from speech has been around as long as NER from written text has, the accuracy of NER from speech has generally been much lower than that of NER from text. The rise in popularity of spoken dialog systems such as Siri or Alexa highlights the need for more accurate NER from speech because NER is a core component for understanding what users said in dialogs. Deployed spoken dialog systems receive user input in the form of automatic speech recognition (ASR) transcripts, and simply applying NER model trained on written text to ASR transcripts often leads to low accuracy because compared to written text, ASR transcripts lack important cues such as punctuation and capitalization. Besides, errors in ASR transcripts also make NER from speech challenging. We propose two models that exploit dialog context and speech pattern clues to extract named entities more accurately from open-domain dialogs in spoken dialog systems. Our results show the benefit of modeling dialog context and speech patterns in two settings: a standard setting with random partition of data and a more realistic but also more difficult setting where many named entities encountered during deployment are unseen during training.
References used
https://aclanthology.org/
rate research
Read More
Abstract In this work, we examine the ability of NER models to use contextual information when predicting the type of an ambiguous entity. We introduce NRB, a new testbed carefully designed to diagnose Name Regularity Bias of NER models. Our results
indicate that all state-of-the-art models we tested show such a bias; BERT fine-tuned models significantly outperforming feature-based (LSTM-CRF) ones on NRB, despite having comparable (sometimes lower) performance on standard benchmarks. To mitigate this bias, we propose a novel model-agnostic training method that adds learnable adversarial noise to some entity mentions, thus enforcing models to focus more strongly on the contextual signal, leading to significant gains on NRB. Combining it with two other training strategies, data augmentation and parameter freezing, leads to further gains.
We explore the application of state-of-the-art NER algorithms to ASR-generated call center transcripts. Previous work in this domain focused on the use of a BiLSTM-CRF model which relied on Flair embeddings; however, such a model is unwieldy in terms
of latency and memory consumption. In a production environment, end users require low-latency models which can be readily integrated into existing pipelines. To that end, we present two different models which can be utilized based on the latency and accuracy requirements of the user. First, we propose a set of models which utilize state-of-the-art Transformer language models (RoBERTa) to develop a high-accuracy NER system trained on custom annotated set of call center transcripts. We then use our best-performing Transformer-based model to label a large number of transcripts, which we use to pretrain a BiLSTM-CRF model and further fine-tune on our annotated dataset. We show that this model, while not as accurate as its Transformer-based counterpart, is highly effective in identifying items which require redaction for privacy law compliance. Further, we propose a new general annotation scheme for NER in the call-center environment.
Abstract We take a step towards addressing the under- representation of the African continent in NLP research by bringing together different stakeholders to create the first large, publicly available, high-quality dataset for named entity recognition
(NER) in ten African languages. We detail the characteristics of these languages to help researchers and practitioners better understand the challenges they pose for NER tasks. We analyze our datasets and conduct an extensive empirical evaluation of state- of-the-art methods across both supervised and transfer learning settings. Finally, we release the data, code, and models to inspire future research on African NLP.1
Current work in named entity recognition (NER) shows that data augmentation techniques can produce more robust models. However, most existing techniques focus on augmenting in-domain data in low-resource scenarios where annotated data is quite limite
d. In this work, we take this research direction to the opposite and study cross-domain data augmentation for the NER task. We investigate the possibility of leveraging data from high-resource domains by projecting it into the low-resource domains. Specifically, we propose a novel neural architecture to transform the data representation from a high-resource to a low-resource domain by learning the patterns (e.g. style, noise, abbreviations, etc.) in the text that differentiate them and a shared feature space where both domains are aligned. We experiment with diverse datasets and show that transforming the data to the low-resource domain representation achieves significant improvements over only using data from high-resource domains.
The use of Named Entity Recognition (NER) over archaic Arabic texts is steadily increasing. However, most tools have been either developed for modern English or trained over English language documents and are limited over historical Arabic text. Even
Arabic NER tools are often trained on modern web-sourced text, making their fit for a historical task questionable. To mitigate historic Arabic NER resource scarcity, we propose a dynamic ensemble model utilizing several learners. The dynamic aspect is achieved by utilizing predictors and features over NER algorithm results that identify which have performed better on a specific task in real-time. We evaluate our approach against state-of-the-art Arabic NER and static ensemble methods over a novel historical Arabic NER task we have created. Our results show that our approach improves upon the state-of-the-art and reaches a 0.8 F-score on this challenging task.
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
