Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userEnd-to-end style-conditioned poetry generation: What does it take to learn from examples alone?
جيل الشعر المطهر على الطراز المنتهي: ما الذي يتطلبه الأمر للتعلم من أمثلة وحدها؟
139
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
في هذا العمل، نقوم بتصميم نموذج نهاية إلى نهاية لتوليد الشعر على أساس نماذج لغة الشبكة العصبية المتكررة مشروطة (RNN) تهدف إلى تعلم الميزات الأسلوبية (طول القصيدة والشعور والتقاليد والتقييم) من الأمثلة وحدها.نعرض أن هذا النموذج يتعلم بنجاح معنى "الطول والشعور، حيث يمكننا التحكم في ذلك لتوليد أطول أو أقصر بالإضافة إلى قصائد أكثر إيجابية أو أكثر سلبية.ومع ذلك، فإن النموذج لا يفهم الظواهر الصوتية مثل الجناس والقفا، ولكن بدلا من ذلك يغمر الإشارات الإحصائية ذات المستوى المنخفض.الأسباب المحتملة تشمل حجم بيانات التدريب، وتردد منخفض نسبيا وصعوبة هذه الظواهر الصربية وكذلك التحيزات النموذجية.نظهر أن نماذج GPT-2 الأخيرة لديها أيضا مشاكل في تعلم ظواهر soblexical مثل القافية من الأمثلة وحدها.
In this work, we design an end-to-end model for poetry generation based on conditioned recurrent neural network (RNN) language models whose goal is to learn stylistic features (poem length, sentiment, alliteration, and rhyming) from examples alone. We show this model successfully learns the meaning' of length and sentiment, as we can control it to generate longer or shorter as well as more positive or more negative poems. However, the model does not grasp sound phenomena like alliteration and rhyming, but instead exploits low-level statistical cues. Possible reasons include the size of the training data, the relatively low frequency and difficulty of these sublexical phenomena as well as model biases. We show that more recent GPT-2 models also have problems learning sublexical phenomena such as rhyming from examples alone.
References used
https://aclanthology.org/
rate research
Read More
Extracting relation triplets from raw text is a crucial task in Information Extraction, enabling multiple applications such as populating or validating knowledge bases, factchecking, and other downstream tasks. However, it usually involves multiple-s
tep pipelines that propagate errors or are limited to a small number of relation types. To overcome these issues, we propose the use of autoregressive seq2seq models. Such models have previously been shown to perform well not only in language generation, but also in NLU tasks such as Entity Linking, thanks to their framing as seq2seq tasks. In this paper, we show how Relation Extraction can be simplified by expressing triplets as a sequence of text and we present REBEL, a seq2seq model based on BART that performs end-to-end relation extraction for more than 200 different relation types. We show our model's flexibility by fine-tuning it on an array of Relation Extraction and Relation Classification benchmarks, with it attaining state-of-the-art performance in most of them.
For each goal-oriented dialog task of interest, large amounts of data need to be collected for end-to-end learning of a neural dialog system. Collecting that data is a costly and time-consuming process. Instead, we show that we can use only a small a
mount of data, supplemented with data from a related dialog task. Naively learning from related data fails to improve performance as the related data can be inconsistent with the target task. We describe a meta-learning based method that selectively learns from the related dialog task data. Our approach leads to significant accuracy improvements in an example dialog task.
Evaluation for many natural language understanding (NLU) tasks is broken: Unreliable and biased systems score so highly on standard benchmarks that there is little room for researchers who develop better systems to demonstrate their improvements. The
recent trend to abandon IID benchmarks in favor of adversarially-constructed, out-of-distribution test sets ensures that current models will perform poorly, but ultimately only obscures the abilities that we want our benchmarks to measure. In this position paper, we lay out four criteria that we argue NLU benchmarks should meet. We argue most current benchmarks fail at these criteria, and that adversarial data collection does not meaningfully address the causes of these failures. Instead, restoring a healthy evaluation ecosystem will require significant progress in the design of benchmark datasets, the reliability with which they are annotated, their size, and the ways they handle social bias.
A real-world information extraction (IE) system for semi-structured document images often involves a long pipeline of multiple modules, whose complexity dramatically increases its development and maintenance cost. One can instead consider an end-to-e
nd model that directly maps the input to the target output and simplify the entire process. However, such generation approach is known to lead to unstable performance if not designed carefully. Here we present our recent effort on transitioning from our existing pipeline-based IE system to an end-to-end system focusing on practical challenges that are associated with replacing and deploying the system in real, large-scale production. By carefully formulating document IE as a sequence generation task, we show that a single end-to-end IE system can be built and still achieve competent performance.
In the last few years, several methods have been proposed to build meta-embeddings. The general aim was to obtain new representations integrating complementary knowledge from different source pre-trained embeddings thereby improving their overall qua
lity. However, previous meta-embeddings have been evaluated using a variety of methods and datasets, which makes it difficult to draw meaningful conclusions regarding the merits of each approach. In this paper we propose a unified common framework, including both intrinsic and extrinsic tasks, for a fair and objective meta-embeddings evaluation. Furthermore, we present a new method to generate meta-embeddings, outperforming previous work on a large number of intrinsic evaluation benchmarks. Our evaluation framework also allows us to conclude that previous extrinsic evaluations of meta-embeddings have been overestimated.
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
