Related papers: Toward Improving Coherence and Diversity of Slogan…
Recently, open-domain dialogue systems have attracted growing attention. Most of them use the sequence-to-sequence (Seq2Seq) architecture to generate responses. However, traditional Seq2Seq-based open-domain dialogue models tend to generate…
Is it possible to train a general metric for evaluating text generation quality without human annotated ratings? Existing learned metrics either perform unsatisfactorily across text generation tasks or require human ratings for training on…
In language processing, training data with extremely large variance may lead to difficulty in the language model's convergence. It is difficult for the network parameters to adapt sentences with largely varied semantics or grammatical…
Conditional story generation and contextual text continuation have become increasingly popular topics in NLP community. Existing models are often prone to output paragraphs of texts that gradually diverge from the given prompt. Although the…
Transformer-based models have made tremendous impacts in natural language generation. However the inference speed is a bottleneck due to large model size and intensive computing involved in auto-regressive decoding process. We develop…
Despite the effectiveness of sequence-to-sequence framework on the task of Short-Text Conversation (STC), the issue of under-exploitation of training data (i.e., the supervision signals from query text is \textit{ignored}) still remains…
Prior studies on text-to-text generation typically assume that the model could figure out what to attend to in the input and what to include in the output via seq2seq learning, with only the parallel training data and no additional…
The encoder-decoder framework has achieved promising process for many sequence generation tasks, such as neural machine translation and text summarization. Such a framework usually generates a sequence token by token from left to right,…
Machine learning models are powerful but fallible. Generating adversarial examples - inputs deliberately crafted to cause model misclassification or other errors - can yield important insight into model assumptions and vulnerabilities.…
To ensure large language models (LLMs) are used safely, one must reduce their propensity to hallucinate or to generate unacceptable answers. A simple and often used strategy is to first let the LLM generate multiple hypotheses and then…
Pre-trained sequence-to-sequence (seq-to-seq) models have significantly improved the accuracy of several language generation tasks, including abstractive summarization. Although the fluency of abstractive summarization has been greatly…
Recently, various neural encoder-decoder models pioneered by Seq2Seq framework have been proposed to achieve the goal of generating more abstractive summaries by learning to map input text to output text. At a high level, such neural models…
We consider the problem of crystal materials generation using language models (LMs). A key step is to convert 3D crystal structures into 1D sequences to be processed by LMs. Prior studies used the crystallographic information framework…
This paper proposes a novel Sequence-to-Sequence (Seq2Seq) model integrating the structure of Hidden Semi-Markov Models (HSMMs) into its attention mechanism. In speech synthesis, it has been shown that methods based on Seq2Seq models using…
Deep-learning models for language generation tasks tend to produce repetitive output. Various methods have been proposed to encourage lexical diversity during decoding, but this often comes at a cost to the perceived fluency and adequacy of…
Sequence-to-sequence (seq2seq) models are competitive with hybrid models for automatic speech recognition (ASR) tasks when large amounts of training data are available. However, data sparsity and domain adaptation are more problematic for…
Many existing conversation models that are based on the encoder-decoder framework have focused on ways to make the encoder more complicated to enrich the context vectors so as to increase the diversity and informativeness of generated…
Hierarchical Text Classification (HTC) is a challenging task where a document can be assigned to multiple hierarchically structured categories within a taxonomy. The majority of prior studies consider HTC as a flat multi-label…
Researchers have recently started investigating deep neural networks for dialogue applications. In particular, generative sequence-to-sequence (Seq2Seq) models have shown promising results for unstructured tasks, such as word-level dialogue…
Diversity is a long-studied topic in information retrieval that usually refers to the requirement that retrieved results should be non-repetitive and cover different aspects. In a conversational setting, an additional dimension of diversity…