Related papers: Techniques for Vocabulary Expansion in Hybrid Spee…
A straightforward pipeline for zero-shot out-of-distribution (OOD) detection involves selecting potential OOD labels from an extensive semantic pool and then leveraging a pre-trained vision-language model to perform classification on both…
Multilingual pretrained representations generally rely on subword segmentation algorithms to create a shared multilingual vocabulary. However, standard heuristic algorithms often lead to sub-optimal segmentation, especially for languages…
Out-of-vocabulary (OOV) words can pose serious challenges for machine translation (MT) tasks, and in particular, for low-resource language (LRL) pairs, i.e., language pairs for which few or no parallel corpora exist. Our work adapts…
Due to the ubiquitous use of embeddings as input representations for a wide range of natural language tasks, imputation of embeddings for rare and unseen words is a critical problem in language processing. Embedding imputation involves…
Publicly available TTS datasets for low-resource languages like Hindi and Tamil typically contain 10-20 hours of data, leading to poor vocabulary coverage. This limitation becomes evident in downstream applications where domain-specific…
Pointer-generator network is an extremely popular method of text summarization. More recent works in this domain still build on top of the baseline pointer generator by augmenting a content selection phase, or by decomposing the decoder…
We present a new approach for neural machine translation (NMT) using the morphological and grammatical decomposition of the words (factors) in the output side of the neural network. This architecture addresses two main problems occurring in…
In embedding-matching acoustic-to-word (A2W) ASR, every word in the vocabulary is represented by a fixed-dimension embedding vector that can be added or removed independently of the rest of the system. The approach is potentially an elegant…
Recognition and retrieval of textual content from the large document collections have been a powerful use case for the document image analysis community. Often the word is the basic unit for recognition as well as retrieval. Systems that…
In Word Sense Disambiguation (WSD), the predominant approach generally involves a supervised system trained on sense annotated corpora. The limited quantity of such corpora however restricts the coverage and the performance of these…
Natural language processing systems often struggle with out-of-vocabulary (OOV) terms, which do not appear in training data. Blends, such as "innoventor", are one particularly challenging class of OOV, as they are formed by fusing together…
Scene text recognition has attracted increasing interest in recent years due to its wide range of applications in multilingual translation, autonomous driving, etc. In this report, we describe our solution to the Out of Vocabulary Scene…
Machine translation models have discrete vocabularies and commonly use subword segmentation techniques to achieve an 'open vocabulary.' This approach relies on consistent and correct underlying unicode sequences, and makes models…
Verbal omissions are complex syntactic phenomena in VP coordination structures. They occur when verbs and (some of) their arguments are omitted from subsequent clauses after being explicitly stated in an initial clause. Recovering these…
Open-vocabulary segmentation is the task of segmenting anything that can be named in an image. Recently, large-scale vision-language modelling has led to significant advances in open-vocabulary segmentation, but at the cost of gargantuan…
Neural machine translation (NMT) models typically operate with a fixed vocabulary, but translation is an open-vocabulary problem. Previous work addresses the translation of out-of-vocabulary words by backing off to a dictionary. In this…
Conversational agents are usually designed for closed-world environments. Unfortunately, users can behave unexpectedly. Based on the open-world environment, we often encounter the situation that the training and test data are sampled from…
The advent of social media in recent years has fed into some highly undesirable phenomena such as proliferation of offensive language, hate speech, sexist remarks, etc. on the Internet. In light of this, there have been several efforts to…
Speech foundation models (SFMs), such as Open Whisper-Style Speech Models (OWSM), are trained on massive datasets to achieve accurate automatic speech recognition. However, even SFMs struggle to accurately recognize rare and unseen words.…
Recent advancements in pre-trained vision-language models, such as CLIP, have enabled the segmentation of arbitrary concepts solely from textual inputs, a process commonly referred to as open-vocabulary semantic segmentation (OVS). However,…