Related papers: Modeling Confidence in Sequence-to-Sequence Models
As large language models (LLMs) grow in parameter size and capabilities, such as interaction through prompting, they open up new ways of interfacing with automatic speech recognition (ASR) systems beyond rescoring n-best lists. This work…
Document-level machine translation incorporates inter-sentential dependencies into the translation of a source sentence. In this paper, we propose a new framework to model cross-sentence dependencies by training neural machine translation…
In the field of natural language processing, correction of performance assessment for chance agreement plays a crucial role in evaluating the reliability of annotations. However, there is a notable dearth of research focusing on chance…
Sequence-to-sequence models with an implicit alignment mechanism (e.g. attention) are closing the performance gap towards traditional hybrid hidden Markov models (HMM) for the task of automatic speech recognition. One important factor to…
Discourse coherence plays an important role in the translation of one text. However, the previous reported models most focus on improving performance over individual sentence while ignoring cross-sentence links and dependencies, which…
Recent advances in Multi-modal Large Language Models (MLLMs) have predominantly focused on enhancing visual perception to improve accuracy. However, a critical question remains unexplored: Do models know when they do not know? Through a…
When evaluating the performance of automatic speech recognition models, usually word error rate within a certain dataset is used. Special care must be taken in understanding the dataset in order to report realistic performance numbers. We…
Differently from the traditional statistical MT that decomposes the translation task into distinct separately learned components, neural machine translation uses a single neural network to model the entire translation process. Despite…
Uncertainty estimation is important for ensuring safety and robustness of AI systems. While most research in the area has focused on un-structured prediction tasks, limited work has investigated general uncertainty estimation approaches for…
Recent advancements in Large Language Models (LLMs) have created new opportunities to enhance performance on complex reasoning tasks by leveraging test-time computation. However, existing scaling methods have key limitations: parallel…
Neural sequence-to-sequence text-to-speech synthesis (TTS) can produce high-quality speech directly from text or simple linguistic features such as phonemes. Unlike traditional pipeline TTS, the neural sequence-to-sequence TTS does not…
Semantic matching is of central importance to many natural language tasks \cite{bordes2014semantic,RetrievalQA}. A successful matching algorithm needs to adequately model the internal structures of language objects and the interaction…
Objective and scalable measurement of teaching quality is a persistent challenge in education. While Large Language Models (LLMs) offer potential, general-purpose models have struggled to reliably apply complex, authentic classroom…
Domain adaptation allows generative language models to address specific flaws caused by the domain shift of their application. However, the traditional adaptation by further training on in-domain data rapidly weakens the model's ability to…
A great deal of recent research effort on speech spoofing countermeasures has been invested into back-end neural networks and training criteria. We contribute to this effort with a comparative perspective in this study. Our comparison of…
This paper addresses an important problem in Example-Based Machine Translation (EBMT), namely how to measure similarity between a sentence fragment and a set of stored examples. A new method is proposed that measures similarity according to…
To maintain user trust, large language models (LLMs) should signal low confidence on examples where they are incorrect, instead of misleading the user. The standard approach of estimating confidence is to use the softmax probabilities of…
Prior to deep learning the semantic parsing community has been interested in understanding and modeling the range of possible word alignments between natural language sentences and their corresponding meaning representations.…
Sentence embedding is an important research topic in natural language processing. It is essential to generate a good embedding vector that fully reflects the semantic meaning of a sentence in order to achieve an enhanced performance for…
Techniques for multi-lingual and cross-lingual speech recognition can help in low resource scenarios, to bootstrap systems and enable analysis of new languages and domains. End-to-end approaches, in particular sequence-based techniques, are…