Related papers: Generative Pretraining for Paraphrase Evaluation
Neural dialogue response generation has gained much popularity in recent years. Maximum Likelihood Estimation (MLE) objective is widely adopted in existing dialogue model learning. However, models trained with MLE objective function are…
An interpretable system for open-domain reasoning needs to express its reasoning process in a transparent form. Natural language is an attractive representation for this purpose -- it is both highly expressive and easy for humans to…
Algorithms for text-generation in dialogue can be misguided. For example, in task-oriented settings, reinforcement learning that optimizes only task-success can lead to abysmal lexical diversity. We hypothesize this is due to poor…
Representation learning for text via pretraining a language model on a large corpus has become a standard starting point for building NLP systems. This approach stands in contrast to autoencoders, also trained on raw text, but with the…
Computer-assisted methods have emerged as valuable tools for retrosynthesis analysis. However, quantifying the plausibility of generated retrosynthesis routes remains a challenging task. We introduce Retro-BLEU, a statistical metric adapted…
Evaluating AMR parsing accuracy involves comparing pairs of AMR graphs. The major evaluation metric, SMATCH (Cai and Knight, 2013), searches for one-to-one mappings between the nodes of two AMRs with a greedy hill-climbing algorithm, which…
Open Information Extraction models have shown promising results with sufficient supervision. However, these models face a fundamental challenge that the syntactic distribution of training data is partially observable in comparison to the…
Natural language context-such as instructions, knowledge, or feedback-contains rich signal for adapting language models. While in-context learning provides adaptation via the prompt, parametric learning persists into model weights and can…
In recent years, a significant number of high-quality pretrained models have emerged, greatly impacting Natural Language Understanding (NLU), Natural Language Generation (NLG), and Text Representation tasks. Traditionally, these models are…
We propose a novel monolingual sentence paraphrasing method for augmenting the training data for statistical machine translation systems "for free" -- by creating it from data that is already available rather than having to create more…
Question generation is a conditioned language generation task that consists in generating a context-aware question given a context and the targeted answer. Train language modelling with a mere likelihood maximization has been widely used…
Speech large language models (LLMs) observe paralinguistic cues such as prosody, emotion, and non-verbal sounds--crucial for intent understanding. However, leveraging these cues faces challenges: limited training data, annotation…
We consider the problem of making efficient use of heterogeneous training data in neural machine translation (NMT). Specifically, given a training dataset with a sentence-level feature such as noise, we seek an optimal curriculum, or order…
Pre-training models have been proved effective for a wide range of natural language processing tasks. Inspired by this, we propose a novel dialogue generation pre-training framework to support various kinds of conversations, including…
Popular Neural Machine Translation model training uses strategies like backtranslation to improve BLEU scores, requiring large amounts of additional data and training. We introduce a class of conditional generative-discriminative hybrid…
Paraphrasing exemplifies the ability to abstract semantic content from surface forms. Recent work on automatic paraphrasing is dominated by methods leveraging Machine Translation (MT) as an intermediate step. This contrasts with humans, who…
LaTeX is suitable for creating specially formatted documents in science, technology, mathematics, and computer science. Although the use of mathematical expressions in LaTeX format along with language models is increasing, there are no…
While pre-trained language models have obtained state-of-the-art performance for several natural language understanding tasks, they are quite opaque in terms of their decision-making process. While some recent works focus on rationalizing…
Leveraging multilingual parallel texts to automatically generate paraphrases has drawn much attention as size of high-quality paraphrase corpus is limited. Round-trip translation, also known as the pivoting method, is a typical approach to…
Although neural-based machine translation evaluation metrics, such as COMET or BLEURT, have achieved strong correlations with human judgements, they are sometimes unreliable in detecting certain phenomena that can be considered as critical…