Related papers: Term Set Expansion based on Multi-Context Term Emb…

Word embedding methods revolve around learning continuous distributed vector representations of words with neural networks, which can capture semantic and/or syntactic cues, and in turn be used to induce similarity measures among words,…

We propose a design pattern for tackling text ranking problems, dubbed "Expando-Mono-Duo", that has been empirically validated for a number of ad hoc retrieval tasks in different domains. At the core, our design relies on pretrained…

We introduce two pre-trained retrieval focused multilingual sentence encoding models, respectively based on the Transformer and CNN model architectures. The models embed text from 16 languages into a single semantic space using a multi-task…

Lexical semantic resources, like WordNet, are often used in real applications of natural language document processing. For example, we integrated GermaNet in our document suite XDOC of processing of German forensic autopsy protocols. In…

Spoken language understanding is typically based on pipeline architectures including speech recognition and natural language understanding steps. These components are optimized independently to allow usage of available data, but the overall…

End-to-end text spotting is a vital computer vision task that aims to integrate scene text detection and recognition into a unified framework. Typical methods heavily rely on Region-of-Interest (RoI) operations to extract local features and…

Despite prosody is related to the linguistic information up to the discourse structure, most text-to-speech (TTS) systems only take into account that within each sentence, which makes it challenging when converting a paragraph of texts into…

Due to the great potential in facilitating software development, code generation has attracted increasing attention recently. Generally, dominant models are Seq2Tree models, which convert the input natural language description into a…

Training Large Language Models (LLMs) with Group Relative Policy Optimization (GRPO) encounters a significant challenge: models often fail to produce accurate responses, particularly in small-scale architectures. This limitation not only…

Inspired by a previous attempt to answer crossword questions using neural networks (Hill, Cho, Korhonen, & Bengio, 2015), this dissertation implements extensions to improve the performance of this existing definition model on the task of…

Conventional text classification models make a bag-of-words assumption reducing text into word occurrence counts per document. Recent algorithms such as word2vec are capable of learning semantic meaning and similarity between words in an…

Prompt tuning has achieved remarkable progress in vision-language models (VLMs) and is recently being adopted for audio-language models (ALMs). However, its generalization ability in ALMs remains largely underexplored. We observe that…

In the last two decades, automatic extractive text summarization on lectures has demonstrated to be a useful tool for collecting key phrases and sentences that best represent the content. However, many current approaches utilize dated…

The Center for Expanded Data Annotation and Retrieval (CEDAR) aims to revolutionize the way that metadata describing scientific experiments are authored. The software we have developed--the CEDAR Workbench--is a suite of Web-based tools and…

Learning effective representations of sentences is one of the core missions of natural language understanding. Existing models either train on a vast amount of text, or require costly, manually curated sentence relation datasets. We show…

Neural language models are a powerful tool to embed words into semantic vector spaces. However, learning such models generally relies on the availability of abundant and diverse training examples. In highly specialised domains this…

Many downstream NLP tasks have shown significant improvement through continual pre-training, transfer learning and multi-task learning. State-of-the-art approaches in Word Sense Disambiguation today benefit from some of these approaches in…

We present a family of neural-network--inspired models for computing continuous word representations, specifically designed to exploit both monolingual and multilingual text. This framework allows us to perform unsupervised training of…

We present a system for bottom-up cumulative learning of myriad concepts corresponding to meaningful character strings, and their part-related and prediction edges. The learning is self-supervised in that the concepts discovered are used as…

Search engine has become a fundamental component in various web and mobile applications. Retrieving relevant documents from the massive datasets is challenging for a search engine system, especially when faced with verbose or tail queries.…