Related papers: Factorising Meaning and Form for Intent-Preserving…

Paraphrasing is a useful natural language processing task that can contribute to more diverse generated or translated texts. Natural language inference (NLI) and paraphrasing share some similarities and can benefit from a joint approach. We…

A generate and test algorithm is described which parses a surface form into one or more lexical entries using linearly ordered phonological rules. This algorithm avoids the exponential expansion of search space which a naive parsing…

Document editing has become a pervasive component of the production of information, with version control systems enabling edits to be efficiently stored and applied. In light of this, the task of learning distributed representations of…

When reading a text, it is common to become stuck on unfamiliar words and phrases, such as polysemous words with novel senses, rarely used idioms, internet slang, or emerging entities. If we humans cannot figure out the meaning of those…

We explore the performance of latent variable models for conditional text generation in the context of neural machine translation (NMT). Similar to Zhang et al., we augment the encoder-decoder NMT paradigm by introducing a continuous latent…

Users may strive to formulate an adequate textual query for their information need. Search engines assist the users by presenting query suggestions. To preserve the original search intent, suggestions should be context-aware and account for…

Paraphrases are texts that convey the same meaning while using different words or sentence structures. It can be used as an automatic data augmentation tool for many Natural Language Processing tasks, especially when dealing with…

A method is given that "inverts" a logic grammar and displays it from the point of view of the logical form, rather than from that of the word string. LR-compiling techniques are used to allow a recursive-descent generation algorithm to…

Lexical simplification (LS) methods based on pretrained language models have made remarkable progress, generating potential substitutes for a complex word through analysis of its contextual surroundings. However, these methods require…

Constrained decoding approaches aim to control the meaning or style of text generated by the pre-trained large language models (LLMs or also PLMs) for various tasks at inference time. However, these methods often guide plausible…

We present an unsupervised method to obtain disentangled representations of sentences that single out semantic content. Using modified Transformers as building blocks, we train a Variational Autoencoder to translate the sentence to a fixed…

Probing is widely used to study which features can be decoded from language model representations. However, the common decoding probe approach has two limitations that we aim to solve with our new encoding probe approach: contributions of…

Latent variable generative models have emerged as powerful tools for generative tasks including image and video synthesis. These models are enabled by pretrained autoencoders that map high resolution data into a compressed lower dimensional…

We propose a query-based generative model for solving both tasks of question generation (QG) and question an- swering (QA). The model follows the classic encoder- decoder framework. The encoder takes a passage and a query as input then…

In this paper, we tackle the task of definition modeling, where the goal is to learn to generate definitions of words and phrases. Existing approaches for this task are discriminative, combining distributional and lexical semantics in an…

Interpreting and understanding the predictions made by deep learning models poses a formidable challenge due to their inherently opaque nature. Many previous efforts aimed at explaining these predictions rely on input features,…

Recent methods for learning vector space representations of words have succeeded in capturing fine-grained semantic and syntactic regularities using vector arithmetic. However, these vector space representations (created through large-scale…

Diffusion models have achieved great success in modeling continuous data modalities such as images, audio, and video, but have seen limited use in discrete domains such as language. Recent attempts to adapt diffusion to language have…

Paraphrase generation, a.k.a. paraphrasing, is a common and important task in natural language processing. Emotional paraphrasing, which changes the emotion embodied in a piece of text while preserving its meaning, has many potential…

Semantic parsing is challenging due to the structure gap and the semantic gap between utterances and logical forms. In this paper, we propose an unsupervised semantic parsing method - Synchronous Semantic Decoding (SSD), which can…