Related papers: Misspelling Semantics In Thai
Across multiple language pairings (English $\to$ \{Spanish, French, German, Mandarin, Japanese, Urdu, Cantonese\}), we find reasoning errors in translation. To quantify how often these reasoning errors occur, we leverage an automated…
Sparse coding refers to the pursuit of the sparsest representation of a signal in a typically overcomplete dictionary. From a Bayesian perspective, sparse coding provides a Maximum a Posteriori (MAP) estimate of the unknown vector under a…
The goal of Text-to-Speech (TTS) synthesis in a particular language is to convert arbitrary input text to intelligible and natural sounding speech. However, for a particular language like Hindi, which is a highly confusing language (due to…
The rapid advancement of large language models (LLMs) has highlighted the need for robust evaluation frameworks that assess their core capabilities, such as reasoning, knowledge, and commonsense, leading to the inception of certain…
Recent work in cross-lingual contextual word embedding learning cannot handle multi-sense words well. In this work, we explore the characteristics of contextual word embeddings and show the link between contextual word embeddings and word…
This paper investigates data selection and model merging methodologies aimed at incorporating advanced reasoning capabilities such as those of DeepSeek R1 into language-specific large language models (LLMs), with a particular focus on the…
Plagiarism involves using another person's work or concepts without proper attribution, presenting them as original creations. With the growing amount of data communicated in regional languages such as Marathi -- one of India's regional…
Recent advances in voice cloning and text-to-speech synthesis have made partial speech manipulation - where an adversary replaces a few words within an utterance to alter its meaning while preserving the speaker's identity - an increasingly…
Sense embedding learning methods learn different embeddings for the different senses of an ambiguous word. One sense of an ambiguous word might be socially biased while its other senses remain unbiased. In comparison to the numerous prior…
This paper reports on the recognition component of an intelligent tutoring system that is designed to help foreign language speakers learn standard English. The system models the grammar of the learner, with this instantiation of the system…
Paraphrasing is rooted in semantics. We show the effectiveness of transformers (Vaswani et al. 2017) for paraphrase generation and further improvements by incorporating PropBank labels via a multi-encoder. Evaluating on MSCOCO and…
Modern large language models demonstrate impressive capabilities in text generation and generalization. However, they often struggle with solving text editing tasks, particularly when it comes to correcting spelling errors and mistypings.…
The incorporation of pseudo data in the training of grammatical error correction models has been one of the main factors in improving the performance of such models. However, consensus is lacking on experimental configurations, namely,…
This paper illustrates how the overall sentiment of a text may be shifted in translation and the implications for automated sentiment analyses, particularly those that utilize machine translation and assess findings via semantic similarity…
Detecting lexical semantic change in smaller data sets, e.g. in historical linguistics and digital humanities, is challenging due to a lack of statistical power. This issue is exacerbated by non-contextual embedding models that produce one…
Machine Translation (MT) and automatic MT evaluation have improved dramatically in recent years, enabling numerous novel applications. Automatic evaluation techniques have evolved from producing scalar quality scores to precisely locating…
The performance of Neural Machine Translation (NMT) depends significantly on the size of the available parallel corpus. Due to this fact, low resource language pairs demonstrate low translation performance compared to high resource language…
The elastic-input neuro tagger and hybrid tagger, combined with a neural network and Brill's error-driven learning, have already been proposed for the purpose of constructing a practical tagger using as little training data as possible.…
Machine Translation (MT) plays a pivotal role in cross-lingual information access, public policy communication, and equitable knowledge dissemination. However, critical meaning errors, such as factual distortions, intent reversals, or…
This paper studies contextual biasing with Large Language Models (LLMs), where during second-pass rescoring additional contextual information is provided to a LLM to boost Automatic Speech Recognition (ASR) performance. We propose to…