Related papers: Prompt-based Learning for Text Readability Assessm…

Modern task-oriented semantic parsing approaches typically use seq2seq transformers to map textual utterances to semantic frames comprised of intents and slots. While these models are empirically strong, their specific strengths and…

This paper introduces a novel approach for identifying the possible large language models (LLMs) involved in text generation. Instead of adding an additional classification layer to a base LM, we reframe the classification task as a…

Textbook question answering (TQA) is a complex task, requiring the interpretation of complex multimodal context. Although recent advances have improved overall performance, they often encounter difficulties in educational settings where…

Simultaneous machine translation (SiMT) outputs translation while reading the source sentence. Unlike conventional sequence-to-sequence (seq2seq) training, existing SiMT methods adopt the prefix-to-prefix (prefix2prefix) training, where the…

This work proposes a novel adaptation of a pretrained sequence-to-sequence model to the task of document ranking. Our approach is fundamentally different from a commonly-adopted classification-based formulation of ranking, based on…

Text classification is a fundamental problem in information retrieval with many real-world applications, such as predicting the topics of online articles and the categories of e-commerce product descriptions. However, low-resource text…

Graph-to-text generation aims to generate fluent texts from graph-based data. In this paper, we investigate two recently proposed pretrained language models (PLMs) and analyze the impact of different task-adaptive pretraining strategies for…

Recently, prompt learning has emerged as the state-of-the-art (SOTA) for fair text-to-image (T2I) generation. Specifically, this approach leverages readily available reference images to learn inclusive prompts for each target Sensitive…

We propose to model the text classification process as a sequential decision process. In this process, an agent learns to classify documents into topics while reading the document sentences sequentially and learns to stop as soon as enough…

Semantic parsing has emerged as a significant and powerful paradigm for natural language interface and question answering systems. Traditional methods of building a semantic parser rely on high-quality lexicons, hand-crafted grammars and…

In this paper, we present a denoising sequence-to-sequence (seq2seq) autoencoder via contrastive learning for abstractive text summarization. Our model adopts a standard Transformer-based architecture with a multi-layer bi-directional…

Recent studies on AMR-to-text generation often formalize the task as a sequence-to-sequence (seq2seq) learning problem by converting an Abstract Meaning Representation (AMR) graph into a word sequence. Graph structures are further modeled…

Language model based pre-trained models such as BERT have provided significant gains across different NLP tasks. In this paper, we study different types of transformer based pre-trained models such as auto-regressive models (GPT-2),…

We compare sequential fine-tuning with a model for multi-task learning in the context where we are interested in boosting performance on two tasks, one of which depends on the other. We test these models on the FigLang2022 shared task which…

The success of a text simplification system heavily depends on the quality and quantity of complex-simple sentence pairs in the training corpus, which are extracted by aligning sentences between parallel articles. To evaluate and improve…

This paper considers the problem of document ranking in information retrieval systems by Learning to Rank. We propose ConvRankNet combining a Siamese Convolutional Neural Network encoder and the RankNet ranking model which could be trained…

Automatic Readability Assessment (ARA), the task of assigning a reading level to a text, is traditionally treated as a classification problem in NLP research. In this paper, we propose the first neural, pairwise ranking approach to ARA and…

We present a set of novel neural supervised and unsupervised approaches for determining the readability of documents. In the unsupervised setting, we leverage neural language models, whereas in the supervised setting, three different neural…

Recent advances in End-to-End (E2E) Spoken Language Understanding (SLU) have been primarily due to effective pretraining of speech representations. One such pretraining paradigm is the distillation of semantic knowledge from…

We address the challenge of building domain-specific knowledge models for industrial use cases, where labelled data and taxonomic information is initially scarce. Our focus is on inductive link prediction models as a basis for practical…