Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSimple or Complex? Complexity-controllable Question Generation with Soft Templates and Deep Mixture of Experts Model
بسيطة أو معقدة؟توليد سؤال قابل للتحكم في التعقيد مع قوالب ناعمة ومزيج عميق من نموذج الخبراء
333
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
إن القدرة على توليد أسئلة باللغة الطبيعية مع مستويات التعقيد التي تسيطر عليها مرغوب فيه للغاية لأنها توزع تطبيق تطبيق سؤال. في هذه الورقة، نقترح نموذجا من جيلات السؤال العصبي المرتعل من نهاية إلى نهج، مما يشتمل على مزيج من الخبراء (MOE) كمحدد قوالب ناعمة لتحسين دقة مراقبة التعقيد ونوعية الأسئلة التي تم إنشاؤها. القوالب الناعمة تلتقط التشابه السؤال مع تجنب البناء باهظ الثمن للقوالب الفعلية. تقدم طريقتنا رواية ومقدر تعقيد عبر المجال لتقييم تعقيد سؤال، مع مراعاة المقطع والسؤال والإجابة وتفاعلاتها. تظهر النتائج التجريبية على مجموعات بيانات QA القياسية على أن نموذج QG الخاص بنا متفوقا على الأساليب الحديثة في كل من التقييم التلقائي واليدوي. علاوة على ذلك، فإن مقدر التعقيد لدينا أكثر دقة بكثير من خطوط الأساس في كلا من إعدادات المجال والخروج.
The ability to generate natural-language questions with controlled complexity levels is highly desirable as it further expands the applicability of question generation. In this paper, we propose an end-to-end neural complexity-controllable question generation model, which incorporates a mixture of experts (MoE) as the selector of soft templates to improve the accuracy of complexity control and the quality of generated questions. The soft templates capture question similarity while avoiding the expensive construction of actual templates. Our method introduces a novel, cross-domain complexity estimator to assess the complexity of a question, taking into account the passage, the question, the answer and their interactions. The experimental results on two benchmark QA datasets demonstrate that our QG model is superior to state-of-the-art methods in both automatic and manual evaluation. Moreover, our complexity estimator is significantly more accurate than the baselines in both in-domain and out-domain settings.
References used
https://aclanthology.org/
rate research
Read More
Text Simplification improves the readability of sentences through several rewriting transformations, such as lexical paraphrasing, deletion, and splitting. Current simplification systems are predominantly sequence-to-sequence models that are trained
end-to-end to perform all these operations simultaneously. However, such systems limit themselves to mostly deleting words and cannot easily adapt to the requirements of different target audiences. In this paper, we propose a novel hybrid approach that leverages linguistically-motivated rules for splitting and deletion, and couples them with a neural paraphrasing model to produce varied rewriting styles. We introduce a new data augmentation method to improve the paraphrasing capability of our model. Through automatic and manual evaluations, we show that our proposed model establishes a new state-of-the-art for the task, paraphrasing more often than the existing systems, and can control the degree of each simplification operation applied to the input texts.
Simultaneous machine translation (SiMT) generates translation before reading the entire source sentence and hence it has to trade off between translation quality and latency. To fulfill the requirements of different translation quality and latency in
practical applications, the previous methods usually need to train multiple SiMT models for different latency levels, resulting in large computational costs. In this paper, we propose a universal SiMT model with Mixture-of-Experts Wait-k Policy to achieve the best translation quality under arbitrary latency with only one trained model. Specifically, our method employs multi-head attention to accomplish the mixture of experts where each head is treated as a wait-k expert with its own waiting words number, and given a test latency and source inputs, the weights of the experts are accordingly adjusted to produce the best translation. Experiments on three datasets show that our method outperforms all the strong baselines under different latency, including the state-of-the-art adaptive policy.
In this paper, we propose a controllable neural generation framework that can flexibly guide dialogue summarization with personal named entity planning. The conditional sequences are modulated to decide what types of information or what perspective t
o focus on when forming summaries to tackle the under-constrained problem in summarization tasks. This framework supports two types of use cases: (1) Comprehensive Perspective, which is a general-purpose case with no user-preference specified, considering summary points from all conversational interlocutors and all mentioned persons; (2) Focus Perspective, positioning the summary based on a user-specified personal named entity, which could be one of the interlocutors or one of the persons mentioned in the conversation. During training, we exploit occurrence planning of personal named entities and coreference information to improve temporal coherence and to minimize hallucination in neural generation. Experimental results show that our proposed framework generates fluent and factually consistent summaries under various planning controls using both objective metrics and human evaluations.
Recent work on opinion summarization produces general summaries based on a set of input reviews and the popularity of opinions expressed in them. In this paper, we propose an approach that allows the generation of customized summaries based on aspect
queries (e.g., describing the location and room of a hotel). Using a review corpus, we create a synthetic training dataset of (review, summary) pairs enriched with aspect controllers which are induced by a multi-instance learning model that predicts the aspects of a document at different levels of granularity. We fine-tune a pretrained model using our synthetic dataset and generate aspect-specific summaries by modifying the aspect controllers. Experiments on two benchmarks show that our model outperforms the previous state of the art and generates personalized summaries by controlling the number of aspects discussed in them.
In practical applications of semantic parsing, we often want to rapidly change the behavior of the parser, such as enabling it to handle queries in a new domain, or changing its predictions on certain targeted queries. While we can introduce new trai
ning examples exhibiting the target behavior, a mechanism for enacting such behavior changes without expensive model re-training would be preferable. To this end, we propose ControllAble Semantic Parser via Exemplar Retrieval (CASPER). Given an input query, the parser retrieves related exemplars from a retrieval index, augments them to the query, and then applies a generative seq2seq model to produce an output parse. The exemplars act as a control mechanism over the generic generative model: by manipulating the retrieval index or how the augmented query is constructed, we can manipulate the behavior of the parser. On the MTOP dataset, in addition to achieving state-of-the-art on the standard setup, we show that CASPER can parse queries in a new domain, adapt the prediction toward the specified patterns, or adapt to new semantic schemas without having to further re-train the model.
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
