Related papers: Context-Aware Transformer Pre-Training for Answer …
Language models (LMs) pretrained on a large text corpus and fine-tuned on a downstream text corpus and fine-tuned on a downstream task becomes a de facto training strategy for several natural language processing (NLP) tasks. Recently, an…
Autoregressive language models, pretrained using large text corpora to do well on next word prediction, have been successful at solving many downstream tasks, even with zero-shot usage. However, there is little theoretical understanding of…
This paper presents a comprehensive study on resume classification to reduce the time and labor needed to screen an overwhelming number of applications significantly, while improving the selection of suitable candidates. A total of 6,492…
Automatic speech recognition (ASR) system is becoming a ubiquitous technology. Although its accuracy is closing the gap with that of human level under certain settings, one area that can further improve is to incorporate user-specific…
Text simplification is crucial for improving accessibility and comprehension for English as a Second Language (ESL) learners. This study goes a step further and aims to facilitate ESL learners' language acquisition by simplification.…
Creating Automatic Speech Recognition (ASR) systems that are robust and resilient to classroom conditions is paramount to the development of AI tools to aid teachers and students. In this work, we study the efficacy of continued pretraining…
Semantic segmentation is still a challenging task for parsing diverse contexts in different scenes, thus the fixed classifier might not be able to well address varying feature distributions during testing. Different from the mainstream…
Automatic speech recognition (ASR) systems often make unrecoverable errors due to subsystem pruning (acoustic, language and pronunciation models); for example pruning words due to acoustics using short-term context, prior to rescoring with…
Current answer sentence selection (AS2) applied in open-domain question answering (ODQA) selects answers by ranking a large set of possible candidates, i.e., sentences, extracted from the retrieved text. In this paper, we present…
Context-aware machine translation models are designed to leverage contextual information, but often fail to do so. As a result, they inaccurately disambiguate pronouns and polysemous words that require context for resolution. In this paper,…
Recent work in neural machine translation has demonstrated both the necessity and feasibility of using inter-sentential context -- context from sentences other than those currently being translated. However, while many current methods…
We formulate long-context language modeling as a problem in continual learning rather than architecture design. Under this formulation, we only use a standard architecture -- a Transformer with sliding-window attention. However, our model…
Current ASR systems are mainly trained and evaluated at the utterance level. Long range cross utterance context can be incorporated. A key task is to derive a suitable compact representation of the most relevant history contexts. In…
Large language model (LLM) applications such as agents and domain-specific reasoning increasingly rely on context adaptation: modifying inputs with instructions, strategies, or evidence, rather than weight updates. Prior approaches improve…
We study the phenomenon of \textit{in-context learning} (ICL) exhibited by large language models, where they can adapt to a new learning task, given a handful of labeled examples, without any explicit parameter optimization. Our goal is to…
A straightforward approach to context-aware neural machine translation consists in feeding the standard encoder-decoder architecture with a window of consecutive sentences, formed by the current sentence and a number of sentences from its…
Conventional spoken language translation (SLT) systems are pipeline based systems, where we have an Automatic Speech Recognition (ASR) system to convert the modality of source from speech to text and a Machine Translation (MT) systems to…
The task of predicting dialog acts (DA) based on conversational dialog is a key component in the development of conversational agents. Accurately predicting DAs requires a precise modeling of both the conversation and the global tag…
Speech models have long been known to overfit individual speakers for many classification tasks. This leads to poor generalization in settings where the speakers are out-of-domain or out-of-distribution, as is common in production…
Autoregressive language models (LMs) generate one token at a time, yet human reasoning operates over higher-level abstractions - sentences, propositions, and concepts. This contrast raises a central question- Can LMs likewise learn to…