نماذج الموضوع العصبي هي النماذج العصبية الأخيرة تهدف إلى استخراج الموضوعات الرئيسية من مجموعة من الوثائق.عادة ما تكون مقارنة هذه النماذج محدودة لأن فرط الدم محتجز ثابتة.في هذه الورقة، نقدم تحليلا تجريبي ومقارنة بين نماذج الموضوعات العصبية من خلال العثور على HyperParameters المثلى لكل نموذج لأربعة تدابير أداء مختلفة تبني تحسين بايزي هدف واحد.هذا يسمح لنا بتحديد متانة نموذج موضوع للعديد من مقاييس التقييم.كما أننا تظهر بشكل تجريبي تأثير طول الوثائق على مختلف المقاييس الأمثل واكتشف مقاييس التقييم الموجودة في صراع أو اتفاق مع بعضنا البعض.
Neural Topic Models are recent neural models that aim at extracting the main themes from a collection of documents. The comparison of these models is usually limited because the hyperparameters are held fixed. In this paper, we present an empirical analysis and comparison of Neural Topic Models by finding the optimal hyperparameters of each model for four different performance measures adopting a single-objective Bayesian optimization. This allows us to determine the robustness of a topic model for several evaluation metrics. We also empirically show the effect of the length of the documents on different optimized metrics and discover which evaluation metrics are in conflict or agreement with each other.
References used
https://aclanthology.org/
Incremental processing allows interactive systems to respond based on partial inputs, which is a desirable property e.g. in dialogue agents. The currently popular Transformer architecture inherently processes sequences as a whole, abstracting away th
Rapidly changing social media content calls for robust and generalisable abuse detection models. However, the state-of-the-art supervised models display degraded performance when they are evaluated on abusive comments that differ from the training co
From statistical to neural models, a wide variety of topic modelling algorithms have been proposed in the literature. However, because of the diversity of datasets and metrics, there have not been many efforts to systematically compare their performa
Contextualized representations based on neural language models have furthered the state of the art in various NLP tasks. Despite its great success, the nature of such representations remains a mystery. In this paper, we present an empirical property
The current recipe for better model performance within NLP is to increase model size and training data. While it gives us models with increasingly impressive results, it also makes it more difficult to train and deploy state-of-the-art models for NLP