Related papers: Semantically Cohesive Word Grouping in Indian Lang…
Parallel text is required for building high-quality machine translation (MT) systems, as well as for other multilingual NLP applications. For many South Asian languages, such data is in short supply. In this paper, we described a new…
The use of subword-level information (e.g., characters, character n-grams, morphemes) has become ubiquitous in modern word representation learning. Its importance is attested especially for morphologically rich languages which generate a…
This thesis investigates how the sub-structure of words can be accounted for in probabilistic models of language. Such models play an important role in natural language processing tasks such as translation or speech recognition, but often…
Chinese word segmentation is a foundational task in natural language processing (NLP), with far-reaching effects on syntactic analysis. Unlike alphabetic languages like English, Chinese lacks explicit word boundaries, making segmentation…
The performance of a text-to-speech (TTS) synthesis model depends on various factors, of which the quality of the training data is of utmost importance. Millions of data are collected around the globe for various languages, but resources…
Large language models (LLMs) take sequences of subwords as input, requiring them to effective compose subword representations into meaningful word-level representations. In this paper, we present a comprehensive set of experiments to probe…
Sentence ordering is a general and critical task for natural language generation applications. Previous works have focused on improving its performance in an external, downstream task, such as multi-document summarization. Given its…
Word segmentation stands as a cornerstone of Natural Language Processing (NLP). Based on the concept of "comprehend first, segment later", we propose a new framework to explore the limit of unsupervised word segmentation with Large Language…
As neural language models approach human performance on NLP benchmark tasks, their advances are widely seen as evidence of an increasingly complex understanding of syntax. This view rests upon a hypothesis that has not yet been empirically…
We present sentence aligned parallel corpora across 10 Indian Languages - Hindi, Telugu, Tamil, Malayalam, Gujarati, Urdu, Bengali, Oriya, Marathi, Punjabi, and English - many of which are categorized as low resource. The corpora are…
Distributed representations of meaning are a natural way to encode covariance relationships between words and phrases in NLP. By overcoming data sparsity problems, as well as providing information about semantic relatedness which is not…
Clustering a lexicon of words is a well-studied problem in natural language processing (NLP). Word clusters are used to deal with sparse data in statistical language processing, as well as features for solving various NLP tasks (text…
Tokenization plays a pivotal role in multilingual NLP. However, existing tokenizers are often skewed towards high-resource languages, limiting their effectiveness for linguistically diverse and morphologically rich languages such as those…
We investigate the problem of parsing conversational data of morphologically-rich languages such as Hindi where argument scrambling occurs frequently. We evaluate a state-of-the-art non-linear transition-based parsing system on a new…
Representing words and phrases into dense vectors of real numbers which encode semantic and syntactic properties is a vital constituent in natural language processing (NLP). The success of neural network (NN) models in NLP largely rely on…
Previous work has shown that isolated non-canonical sentences with Object-before-Subject (OSV) order are initially harder to process than their canonical counterparts with Subject-before-Object (SOV) order. Although this difficulty…
As the use of natural language processing increases in our day-to-day life, the need to address gender bias inherent in these systems also amplifies. This is because the inherent bias interferes with the semantic structure of the output of…
Several explanation methods such as Integrated Gradients (IG) can be characterised as path-based methods, as they rely on a straight line between the data and an uninformative baseline. However, when applied to language models, these…
Conceptual combination performs a fundamental role in creating the broad range of compound phrases utilized in everyday language. This article provides a novel probabilistic framework for assessing whether the semantics of conceptual…
Most unsupervised NLP models represent each word with a single point or single region in semantic space, while the existing multi-sense word embeddings cannot represent longer word sequences like phrases or sentences. We propose a novel…