Related papers: Discourse Level Factors for Sentence Deletion in T…

English proficiency assessments have become a necessary metric for filtering and selecting prospective candidates for both academia and industry. With the rise in demand for such assessments, it has become increasingly necessary to have the…

This report explores the use of paragraph break probability estimates to help predict the location of sentence breaks in English natural language text. We show that a sentence break predictor based almost solely on paragraph break…

The wave of pre-training language models has been continuously improving the quality of the machine-generated conversations, however, some of the generated responses still suffer from excessive repetition, sometimes repeating words from…

Dropped Pronouns (DP) in which pronouns are frequently dropped in the source language but should be retained in the target language are challenge in machine translation. In response to this problem, we propose a semi-supervised approach to…

Abstractive text summarization aims to shorten long text documents into a human readable form that contains the most important facts from the original document. However, the level of actual abstraction as measured by novel phrases that do…

As research on machine translation moves to translating text beyond the sentence level, it remains unclear how effective automatic evaluation metrics are at scoring longer translations. In this work, we first propose a method for creating…

Sentence splitting is a major simplification operator. Here we present a simple and efficient splitting algorithm based on an automatic semantic parser. After splitting, the text is amenable for further fine-tuned simplification operations.…

We leverage generative large language models for language learning applications, focusing on estimating the difficulty of foreign language texts and simplifying them to lower difficulty levels. We frame both tasks as prediction problems and…

The standard approach to assess reliability of automatic speech transcriptions is through the use of confidence scores. If accurate, these scores provide a flexible mechanism to flag transcription errors for upstream and downstream…

Common language models typically predict the next word given the context. In this work, we propose a method that improves language modeling by learning to align the given context and the following phrase. The model does not require any…

Automatic evaluation remains an open research question in Natural Language Generation. In the context of Sentence Simplification, this is particularly challenging: the task requires by nature to replace complex words with simpler ones that…

In this paper, we present the SimDoc system, a simplification model considering simplicity, readability, and discourse aspects, such as coherence. In the past decade, the progress of the Text Simplification (TS) field has been mostly shown…

We introduce an evaluation methodology for reading comprehension tasks based on the intuition that certain examples, by the virtue of their linguistic complexity, consistently yield lower scores regardless of model size or architecture. We…

Determining semantic similarity between academic documents is crucial to many tasks such as plagiarism detection, automatic technical survey and semantic search. Current studies mostly focus on semantic similarity between concepts,…

One popular method for quantitatively evaluating the utility of sentence embeddings involves using them in downstream language processing tasks that require sentence representations as input. One simple such task is classification, where…

We propose new static word embeddings optimised for sentence semantic representation. We first extract word embeddings from a pre-trained Sentence Transformer, and improve them with sentence-level principal component analysis, followed by…

Inferring the probability distribution of sentences or word sequences is a key process in natural language processing. While word-level language models (LMs) have been widely adopted for computing the joint probabilities of word sequences,…

The problem of accurately predicting relative reading difficulty across a set of sentences arises in a number of important natural language applications, such as finding and curating effective usage examples for intelligent language…

Automated multi-document extractive text summarization is a widely studied research problem in the field of natural language understanding. Such extractive mechanisms compute in some form the worthiness of a sentence to be included into the…

As natural language processing methods are increasingly deployed in real-world scenarios such as healthcare, legal systems, and social science, it becomes necessary to recognize the role they potentially play in shaping social biases and…