Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userIGA: An Intent-Guided Authoring Assistant
IGA: مساعد التأليف الموجهة إلى النوايا
102
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
على الرغم من أن نماذج اللغة المحددة مسبقا على نطاق واسع تحسنت بشكل كبير في تحسين وظائف المساعدة مثل الإكمال التلقائي، إلا أنه لم يتم استكشاف مساعدي الكتابة أكثر تعقيدا ويمكن التحكم فيه بعد. نستفيد من التطورات في النمذجة اللغوية لبناء مساعد كتابة تفاعلي ينشئ النص وإعادة صياغة النص وفقا لمواصفات المؤلف المحبوس بشكل جيد. يقدم المستخدمون مدخلات لمساعدنا الموجه في النوايا (IGA) في شكل نص يتعايش مع العلامات التي تتوافق مع توجيهات خطابية محددة (على سبيل المثال، إضافة الوصف أو التباين، أو إعادة تصوير جملة معينة). نحن نؤيد نموذج لغة على مجموعة بيانات مثبتة مسبقا مع نية المؤلف، والتي تسمح IGA بملء هذه العلامات مع نص تم إنشاؤه يستخدم المستخدمون في وقت لاحق تحرير لتروقهم. تؤكد سلسلة من التقييمات التلقائية والتعبئة الجودة جودة مخرجات IGA التي تم إنشاؤها، في حين أن دراسة مستخدمين على نطاق صغير توضح تفضيلات المؤلف ل IGA على أساليب خط الأساس في مهمة كتابة إبداعية. نطلق سراح البيانات الخاصة بنا ورمزها وإيضا لتحديد مزيد من البحث في الكتابة بمساعدة منظمة العفو الدولية.
While large-scale pretrained language models have significantly improved writing assistance functionalities such as autocomplete, more complex and controllable writing assistants have yet to be explored. We leverage advances in language modeling to build an interactive writing assistant that generates and rephrases text according to fine-grained author specifications. Users provide input to our Intent-Guided Assistant (IGA) in the form of text interspersed with tags that correspond to specific rhetorical directives (e.g., adding description or contrast, or rephrasing a particular sentence). We fine-tune a language model on a dataset heuristically-labeled with author intent, which allows IGA to fill in these tags with generated text that users can subsequently edit to their liking. A series of automatic and crowdsourced evaluations confirm the quality of IGA's generated outputs, while a small-scale user study demonstrates author preference for IGA over baseline methods in a creative writing task. We release our dataset, code, and demo to spur further research into AI-assisted writing.
References used
https://aclanthology.org/
rate research
Read More
One of the first building blocks to create a voice assistant relates to the task of tagging entities or attributes in user queries. This can be particularly challenging when entities are in the tenth of millions, as is the case of e.g. music catalogs
. Training slot tagging models at an industrial scale requires large quantities of accurately labeled user queries, which are often hard and costly to gather. On the other hand, voice assistants typically collect plenty of unlabeled queries that often remain unexploited. This paper presents a weakly-supervised methodology to label large amounts of voice query logs, enhanced with a manual filtering step. Our experimental evaluations show that slot tagging models trained on weakly-supervised data outperform models trained on hand-annotated or synthetic data, at a lower cost. Further, manual filtering of weakly-supervised data leads to a very significant reduction in Sentence Error Rate, while allowing us to drastically reduce human curation efforts from weeks to hours, with respect to hand-annotation of queries. The method is applied to successfully bootstrap a slot tagging system for a major music streaming service that currently serves several tens of thousands of daily voice queries.
Reliable tagging of Temporal Expressions (TEs, e.g., Book a table at L'Osteria for Sunday evening) is a central requirement for Voice Assistants (VAs). However, there is a dearth of resources and systems for the VA domain, since publicly-available te
mporal taggers are trained only on substantially different domains, such as news and clinical text. Since the cost of annotating large datasets is prohibitive, we investigate the trade-off between in-domain data and performance in DA-Time, a hybrid temporal tagger for the English VA domain which combines a neural architecture for robust TE recognition, with a parser-based TE normalizer. We find that transfer learning goes a long way even with as little as 25 in-domain sentences: DA-Time performs at the state of the art on the news domain, and substantially outperforms it on the VA domain.
A critical point of multi-document summarization (MDS) is to learn the relations among various documents. In this paper, we propose a novel abstractive MDS model, in which we represent multiple documents as a heterogeneous graph, taking semantic node
s of different granularities into account, and then apply a graph-to-sequence framework to generate summaries. Moreover, we employ a neural topic model to jointly discover latent topics that can act as cross-document semantic units to bridge different documents and provide global information to guide the summary generation. Since topic extraction can be viewed as a special type of summarization that summarizes'' texts into a more abstract format, i.e., a topic distribution, we adopt a multi-task learning strategy to jointly train the topic and summarization module, allowing the promotion of each other. Experimental results on the Multi-News dataset demonstrate that our model outperforms previous state-of-the-art MDS models on both Rouge scores and human evaluation, meanwhile learns high-quality topics.
Natural Language Generation (NLG) for task-oriented dialogue systems focuses on communicating specific content accurately, fluently, and coherently. While these attributes are crucial for a successful dialogue, it is also desirable to simultaneously
accomplish specific stylistic goals, such as response length, point-of-view, descriptiveness, sentiment, formality, and empathy. In this work, we focus on stylistic control and evaluation for schema-guided NLG, with joint goals of achieving both semantic and stylistic control. We experiment in detail with various controlled generation methods for large pretrained language models: specifically, conditional training, guided fine-tuning, and guided decoding. We discuss their advantages and limitations, and evaluate them with a broad range of automatic and human evaluation metrics. Our results show that while high style accuracy and semantic correctness are easier to achieve for more lexically-defined styles with conditional training, stylistic control is also achievable for more semantically complex styles using discriminator-based guided decoding methods. The results also suggest that methods that are more scalable (with less hyper-parameters tuning) and that disentangle context generation and stylistic variations are more effective at achieving semantic correctness and style accuracy.
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.
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
