Related papers: Candidate Fusion: Integrating Language Modelling i…
Name matching is a key component of systems for entity resolution or record linkage. Alternative spellings of the same names are a com- mon occurrence in many applications. We use the largest collection of genealogy person records in the…
Recently, Transformer-based encoder-decoder models have demonstrated strong performance in multilingual speech recognition. However, the decoder's autoregressive nature and large size introduce significant bottlenecks during inference.…
The risk of language models reproducing copyrighted material from their training data has led to the development of various protective measures. Among these, inference-time strategies that impose constraints via post-processing have shown…
The sequence to sequence architecture is widely used in the response generation and neural machine translation to model the potential relationship between two sentences. It typically consists of two parts: an encoder that reads from the…
Recently, significant improvements have been achieved in various natural language processing tasks using neural sequence-to-sequence models. While aiming for the best generation quality is important, ultimately it is also necessary to…
A handwritten word recognition system comes with issues such as lack of large and diverse datasets. It is necessary to resolve such issues since millions of official documents can be digitized by training deep learning models using a large…
Candidate generation is a crucial module in entity linking. It also plays a key role in multiple NLP tasks that have been proven to beneficially leverage knowledge bases. Nevertheless, it has often been overlooked in the monolingual English…
Supporting the current trend in the AI community, we present the AI Journey 2021 Challenge called Fusion Brain, the first competition which is targeted to make the universal architecture which could process different modalities (in this…
Grammatical error correction can be viewed as a low-resource sequence-to-sequence task, because publicly available parallel corpora are limited. To tackle this challenge, we first generate erroneous versions of large unannotated corpora…
Sequence discriminative training is a great tool to improve the performance of an automatic speech recognition system. It does, however, necessitate a sum over all possible word sequences, which is intractable to compute in practice.…
How to leverage dynamic contextual information in end-to-end speech recognition has remained an active research area. Previous solutions to this problem were either designed for specialized use cases that did not generalize well to…
Recent advances in large language models have facilitated the development of unified speech language models (SLMs) capable of supporting multiple speech tasks within a shared architecture. However, tasks such as automatic speech recognition…
In countries that speak multiple main languages, mixing up different languages within a conversation is commonly called code-switching. Previous works addressing this challenge mainly focused on word-level aspects such as word embeddings.…
The advent of large language models (LLMs) has significantly advanced artificial intelligence (AI) in software engineering (SE), with source code embeddings playing a crucial role in tasks such as source code clone detection and source code…
Recent advancements in large language models have demonstrated that extended inference through techniques can markedly improve performance, yet these gains come with increased computational costs and the propagation of inherent biases found…
Designing machine intelligence to converse with a human user necessarily requires an understanding of how humans participate in conversation, and thus conversation modeling is an important task in natural language processing. New…
Advancements in Natural Language Processing have enabled specialized language models, but integrating domain-specific knowledge into general-purpose models in multilingual settings remains challenging, particularly for technical vocabulary.…
Topic modelling is a pivotal unsupervised machine learning technique for extracting valuable insights from large document collections. Existing neural topic modelling methods often encode contextual information of documents, while ignoring…
Code generation aims to automatically generate code snippets of specific programming language according to natural language descriptions. The continuous advancements in deep learning, particularly pre-trained models, have empowered the code…
Named entity recognition (NER) and relation extraction (RE) are two important tasks in information extraction and retrieval (IE \& IR). Recent work has demonstrated that it is beneficial to learn these tasks jointly, which avoids the…