Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userNeural Compound-Word (Sandhi) Generation and Splitting in Sanskrit Language
64
0
0.0
(
0
)
Added by
Arun Kumar Singh
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
This paper describes neural network based approaches to the process of the formation and splitting of word-compounding, respectively known as the Sandhi and Vichchhed, in Sanskrit language. Sandhi is an important idea essential to morphological analysis of Sanskrit texts. Sandhi leads to word transformations at word boundaries. The rules of Sandhi formation are well defined but complex, sometimes optional and in some cases, require knowledge about the nature of the words being compounded. Sandhi split or Vichchhed is an even more difficult task given its non uniqueness and context dependence. In this work, we propose the route of formulating the problem as a sequence to sequence prediction task, using modern deep learning techniques. Being the first fully data driven technique, we demonstrate that our model has an accuracy better than the existing methods on multiple standard datasets, despite not using any additional lexical or morphological resources. The code is being made available at https://github.com/IITD-DataScience/Sandhi_Prakarana
rate research
Read More
Recently, the supervised learning paradigms surprisingly remarkable performance has garnered considerable attention from Sanskrit Computational Linguists. As a result, the Sanskrit community has put laudable efforts to build task-specific labeled data for various downstream Natural Language Processing (NLP) tasks. The primary component of these approaches comes from representations of word embeddings. Word embedding helps to transfer knowledge learned from readily available unlabelled data for improving task-specific performance in low-resource setting. Last decade, there has been much excitement in the field of digitization of Sanskrit. To effectively use such readily available resources, it is very much essential to perform a systematic study on word embedding approaches for the Sanskrit language. In this work, we investigate the effectiveness of word embeddings. We classify word embeddings in broad categories to facilitate systematic experimentation and evaluate them on four intrinsic tasks. We investigate the efficacy of embeddings approaches (originally proposed for languages other than Sanskrit) for Sanskrit along with various challenges posed by language.
Recently, bidirectional recurrent network language models (bi-RNNLMs) have been shown to outperform standard, unidirectional, recurrent neural network language models (uni-RNNLMs) on a range of speech recognition tasks. This indicates that future word context information beyond the word history can be useful. However, bi-RNNLMs pose a number of challenges as they make use of the complete previous and future word context information. This impacts both training efficiency and their use within a lattice rescoring framework. In this paper these issues are addressed by proposing a novel neural network structure, succeeding word RNNLMs (su-RNNLMs). Instead of using a recurrent unit to capture the complete future word contexts, a feedforward unit is used to model a finite number of succeeding, future, words. This model can be trained much more efficiently than bi-RNNLMs and can also be used for lattice rescoring. Experimental results on a meeting transcription task (AMI) show the proposed model consistently outperformed uni-RNNLMs and yield only a slight degradation compared to bi-RNNLMs in N-best rescoring. Additionally, performance improvements can be obtained using lattice rescoring and subsequent confusion network decoding.
We present two supervised (pre-)training methods to incorporate gloss definitions from lexical resources into neural language models (LMs). The training improves our models performance for Word Sense Disambiguation (WSD) but also benefits general language understanding tasks while adding almost no parameters. We evaluate our techniques with seven different neural LMs and find that XLNet is more suitable for WSD than BERT. Our best-performing methods exceeds state-of-the-art WSD techniques on the SemCor 3.0 dataset by 0.5% F1 and increase BERTs performance on the GLUE benchmark by 1.1% on average.
Neural networks are among the state-of-the-art techniques for language modeling. Existing neural language models typically map discrete words to distributed, dense vector representations. After information processing of the preceding context words by hidden layers, an output layer estimates the probability of the next word. Such approaches are time- and memory-intensive because of the large numbers of parameters for word embeddings and the output layer. In this paper, we propose to compress neural language models by sparse word representations. In the experiments, the number of parameters in our model increases very slowly with the growth of the vocabulary size, which is almost imperceptible. Moreover, our approach not only reduces the parameter space to a large extent, but also improves the performance in terms of the perplexity measure.
Recent research analyzing the sensitivity of natural language understanding models to word-order perturbations have shown that the state-of-the-art models in several language tasks may have a unique way to understand the text that could seldom be explained with conventional syntax and semantics. In this paper, we investigate the insensitivity of natural language models to word-order by quantifying perturbations and analysing their effect on neural models performance on language understanding tasks in GLUE benchmark. Towards that end, we propose two metrics - the Direct Neighbour Displacement (DND) and the Index Displacement Count (IDC) - that score the local and global ordering of tokens in the perturbed texts and observe that perturbation functions found in prior literature affect only the global ordering while the local ordering remains relatively unperturbed. We propose perturbations at the granularity of sub-words and characters to study the correlation between DND, IDC and the performance of neural language models on natural language tasks. We find that neural language models - pretrained and non-pretrained Transformers, LSTMs, and Convolutional architectures - require local ordering more so than the global ordering of tokens. The proposed metrics and the suite of perturbations allow a systematic way to study the (in)sensitivity of neural language understanding models to varying degree of perturbations.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
