A computationally expensive and memory intensive neural network lies behind the recent success of language representation learning. Knowledge distillation, a major technique for deploying such a vast language model in resource-scarce environments, tr
ansfers the knowledge on individual word representations learned without restrictions. In this paper, inspired by the recent observations that language representations are relatively positioned and have more semantic knowledge as a whole, we present a new knowledge distillation objective for language representation learning that transfers the contextual knowledge via two types of relationships across representations: Word Relation and Layer Transforming Relation. Unlike other recent distillation techniques for the language models, our contextual distillation does not have any restrictions on architectural changes between teacher and student. We validate the effectiveness of our method on challenging benchmarks of language understanding tasks, not only in architectures of various sizes but also in combination with DynaBERT, the recently proposed adaptive size pruning method.
Providing pretrained language models with simple task descriptions in natural language enables them to solve some tasks in a fully unsupervised fashion. Moreover, when combined with regular learning from examples, this idea yields impressive few-shot
results for a wide range of text classification tasks. It is also a promising direction to improve data efficiency in generative settings, but there are several challenges to using a combination of task descriptions and example-based learning for text generation. In particular, it is crucial to find task descriptions that are easy to understand for the pretrained model and to ensure that it actually makes good use of them; furthermore, effective measures against overfitting have to be implemented. In this paper, we show how these challenges can be tackled: We introduce GenPET, a method for text generation that is based on pattern-exploiting training, a recent approach for combining textual instructions with supervised learning that only works for classification tasks. On several summarization and headline generation datasets, GenPET gives consistent improvements over strong baselines in few-shot settings.
Dialogue-based relation extraction (RE) aims to extract relation(s) between two arguments that appear in a dialogue. Because dialogues have the characteristics of high personal pronoun occurrences and low information density, and since most relationa
l facts in dialogues are not supported by any single sentence, dialogue-based relation extraction requires a comprehensive understanding of dialogue. In this paper, we propose the TUrn COntext awaRE Graph Convolutional Network (TUCORE-GCN) modeled by paying attention to the way people understand dialogues. In addition, we propose a novel approach which treats the task of emotion recognition in conversations (ERC) as a dialogue-based RE. Experiments on a dialogue-based RE dataset and three ERC datasets demonstrate that our model is very effective in various dialogue-based natural language understanding tasks. In these experiments, TUCORE-GCN outperforms the state-of-the-art models on most of the benchmark datasets. Our code is available at https://github.com/BlackNoodle/TUCORE-GCN.
Word embedding is essential for neural network models for various natural language processing tasks. Since the word embedding usually has a considerable size, in order to deploy a neural network model having it on edge devices, it should be effective
ly compressed. There was a study for proposing a block-wise low-rank approximation method for word embedding, called GroupReduce. Even if their structure is effective, the properties behind the concept of the block-wise word embedding compression were not sufficiently explored. Motivated by this, we improve GroupReduce in terms of word weighting and structuring. For word weighting, we propose a simple yet effective method inspired by the term frequency-inverse document frequency method and a novel differentiable method. Based on them, we construct a discriminative word embedding compression algorithm. In the experiments, we demonstrate that the proposed algorithm more effectively finds word weights than competitors in most cases. In addition, we show that the proposed algorithm can act like a framework through successful cooperation with quantization.
Sentence Compression (SC), which aims to shorten sentences while retaining important words that express the essential meanings, has been studied for many years in many languages, especially in English. However, improvements on Chinese SC task are sti
ll quite few due to several difficulties: scarce of parallel corpora, different segmentation granularity of Chinese sentences, and imperfect performance of syntactic analyses. Furthermore, entire neural Chinese SC models have been under-investigated so far. In this work, we construct an SC dataset of Chinese colloquial sentences from a real-life question answering system in the telecommunication domain, and then, we propose a neural Chinese SC model enhanced with a Self-Organizing Map (SOM-NCSCM), to gain a valuable insight from the data and improve the performance of the whole neural Chinese SC model in a valid manner. Experimental results show that our SOM-NCSCM can significantly benefit from the deep investigation of similarity among data, and achieve a promising F1 score of 89.655 and BLEU4 score of 70.116, which also provides a baseline for further research on Chinese SC task.
Hyperpartisan news show an extreme manipulation of reality based on an underlying and extreme ideological orientation. Because of its harmful effects at reinforcing one's bias and the posterior behavior of people, hyperpartisan news detection has bec
ome an important task for computational linguists. In this paper, we evaluate two different approaches to detect hyperpartisan news. First, a text masking technique that allows us to compare style vs. topic-related features in a different perspective from previous work. Second, the transformer-based models BERT, XLM-RoBERTa, and M-BERT, known for their ability to capture semantic and syntactic patterns in the same representation. Our results corroborate previous research on this task in that topic-related features yield better results than style-based ones, although they also highlight the relevance of using higher-length n-grams. Furthermore, they show that transformer-based models are more effective than traditional methods, but this at the cost of greater computational complexity and lack of transparency. Based on our experiments, we conclude that the beginning of the news show relevant information for the transformers at distinguishing effectively between left-wing, mainstream, and right-wing orientations.
The adoption of Transformer-based models in natural language processing (NLP) has led to great success using a massive number of parameters. However, due to deployment constraints in edge devices, there has been a rising interest in the compression o
f these models to improve their inference time and memory footprint. This paper presents a novel loss objective to compress token embeddings in the Transformer-based models by leveraging an AutoEncoder architecture. More specifically, we emphasize the importance of the direction of compressed embeddings with respect to original uncompressed embeddings. The proposed method is task-agnostic and does not require further language modeling pre-training. Our method significantly outperforms the commonly used SVD-based matrix-factorization approach in terms of initial language model Perplexity. Moreover, we evaluate our proposed approach over SQuAD v1.1 dataset and several downstream tasks from the GLUE benchmark, where we also outperform the baseline in most scenarios. Our code is public.
Abstract Recent improvements in the predictive quality of natural language processing systems are often dependent on a substantial increase in the number of model parameters. This has led to various attempts of compressing such models, but existing m
ethods have not considered the differences in the predictive power of various model components or in the generalizability of the compressed models. To understand the connection between model compression and out-of-distribution generalization, we define the task of compressing language representation models such that they perform best in a domain adaptation setting. We choose to address this problem from a causal perspective, attempting to estimate the average treatment effect (ATE) of a model component, such as a single layer, on the model's predictions. Our proposed ATE-guided Model Compression scheme (AMoC), generates many model candidates, differing by the model components that were removed. Then, we select the best candidate through a stepwise regression model that utilizes the ATE to predict the expected performance on the target domain. AMoC outperforms strong baselines on dozens of domain pairs across three text classification and sequence tagging tasks.1
This paper discusses a geothermobarometry modeling computer software called
Thermocalc through an applied example from the southern Syria volcanism, specifically
from Tal Al-Ashaer volcano, is given. A graphical P-T diagram for a given chemical bul
k
composition of some spinel-bearing peridotite rocks (from Tal Al-Ashaer) is created. The
results and their interpretation, in addition to limitations and constraints are discussed.
Based on the mineralogical analysis linked to the studied mineral assemblage modes, the
bulk-rock chemical composition is calculated and a geothermobarometry model using
Thermocalc is made. The created model shows that the general conditions at which the
rock-forming minerals (coexisting in equilibrium) define a field of stability with a range of
temperature goes from 700 to 1100 C° corresponding a range of pressure between 8 and 15
Kbar. Using one of Thermocalc tools (composition isopleths) the most precise P-T
conditions at which the rock was formed are estimated; T = 892 C° and P = 10.5 Kbar. The
corresponding depth at which the studied samples were formed is about 36 Km.
Accordingly, the crust-upper mantle boundary in the studied region is placed at that depth.
The research seeks to identify the relationship between work
pressure and organizational loyalty among faculty members at Al-
Baath University. In order to achieve the objectives of the research,
the work pressure and organizational loyalty indices were used. The
research was carried out on a sample of 237 faculty members with
38% the original.
